Daily Papers

Cloud cover in multispectral imagery (MSI) significantly hinders early-season crop mapping by corrupting spectral information. Existing Vision Transformer(ViT)-based time-series reconstruction methods, like SMTS-ViT, often employ coarse temporal embeddings that aggregate entire sequences, causing substantial information loss and reducing reconstruction accuracy. To address these limitations, a Video Vision Transformer (ViViT)-based framework with temporal-spatial fusion embedding for MSI reconstruction in cloud-covered regions is proposed in this study. Non-overlapping tubelets are extracted via 3D convolution with constrained temporal span (t=2), ensuring local temporal coherence while reducing cross-day information degradation. Both MSI-only and SAR-MSI fusion scenarios are considered during the experiments. Comprehensive experiments on 2020 Traill County data demonstrate notable performance improvements: MTS-ViViT achieves a 2.23\% reduction in MSE compared to the MTS-ViT baseline, while SMTS-ViViT achieves a 10.33\% improvement with SAR integration over the SMTS-ViT baseline. The proposed framework effectively enhances spectral reconstruction quality for robust agricultural monitoring.

We investigate a challenging task of dynamic scene geometry estimation, which requires representing both spatial and temporal features. Typically, existing methods align the two features into a unified latent space to model scene geometry. However, this unified paradigm suffers from potential mismatched representation due to the heterogeneous nature between spatial and temporal features. In this work, we propose 4D-VGGT, a general foundation model with divide-and-conquer spatiotemporal representation for dynamic scene geometry. Our model is divided into three aspects: 1) Multi-setting input. We design an adaptive visual grid that supports input sequences with arbitrary numbers of views and time steps. 2) Multi-level representation. We propose a cross-view global fusion for spatial representation and a cross-time local fusion for temporal representation. 3) Multi-task prediction. We append multiple task-specific heads to spatiotemporal representations, enabling a comprehensive visual geometry estimation for dynamic scenes. Under this unified framework, these components enhance the feature discriminability and application universality of our model for dynamic scenes. In addition, we integrate multiple geometry datasets to train our model and conduct extensive experiments to verify the effectiveness of our method across various tasks on multiple dynamic scene geometry benchmarks.

We present GDFusion, a temporal fusion method for vision-based 3D semantic occupancy prediction (VisionOcc). GDFusion opens up the underexplored aspects of temporal fusion within the VisionOcc framework, focusing on both temporal cues and fusion strategies. It systematically examines the entire VisionOcc pipeline, identifying three fundamental yet previously overlooked temporal cues: scene-level consistency, motion calibration, and geometric complementation. These cues capture diverse facets of temporal evolution and make distinct contributions across various modules in the VisionOcc framework. To effectively fuse temporal signals across heterogeneous representations, we propose a novel fusion strategy by reinterpreting the formulation of vanilla RNNs. This reinterpretation leverages gradient descent on features to unify the integration of diverse temporal information, seamlessly embedding the proposed temporal cues into the network. Extensive experiments on nuScenes demonstrate that GDFusion significantly outperforms established baselines. Notably, on Occ3D benchmark, it achieves 1.4\%-4.8\% mIoU improvements and reduces memory consumption by 27\%-72\%.

Recent advancements in multimodal large language models (MLLMs) have shown promising results, yet existing approaches struggle to effectively handle both temporal and spatial localization simultaneously. This challenge stems from two key issues: first, incorporating spatial-temporal localization introduces a vast number of coordinate combinations, complicating the alignment of linguistic and visual coordinate representations; second, encoding fine-grained temporal and spatial information during video feature compression is inherently difficult. To address these issues, we propose LLaVA-ST, a MLLM for fine-grained spatial-temporal multimodal understanding. In LLaVA-ST, we propose Language-Aligned Positional Embedding, which embeds the textual coordinate special token into the visual space, simplifying the alignment of fine-grained spatial-temporal correspondences. Additionally, we design the Spatial-Temporal Packer, which decouples the feature compression of temporal and spatial resolutions into two distinct point-to-region attention processing streams. Furthermore, we propose ST-Align dataset with 4.3M training samples for fine-grained spatial-temporal multimodal understanding. With ST-align, we present a progressive training pipeline that aligns the visual and textual feature through sequential coarse-to-fine stages.Additionally, we introduce an ST-Align benchmark to evaluate spatial-temporal interleaved fine-grained understanding tasks, which include Spatial-Temporal Video Grounding (STVG) , Event Localization and Captioning (ELC) and Spatial Video Grounding (SVG). LLaVA-ST achieves outstanding performance on 11 benchmarks requiring fine-grained temporal, spatial, or spatial-temporal interleaving multimodal understanding. Our code, data and benchmark will be released at Our code, data and benchmark will be released at https://github.com/appletea233/LLaVA-ST .

We present a self-supervised Contrastive Video Representation Learning (CVRL) method to learn spatiotemporal visual representations from unlabeled videos. Our representations are learned using a contrastive loss, where two augmented clips from the same short video are pulled together in the embedding space, while clips from different videos are pushed away. We study what makes for good data augmentations for video self-supervised learning and find that both spatial and temporal information are crucial. We carefully design data augmentations involving spatial and temporal cues. Concretely, we propose a temporally consistent spatial augmentation method to impose strong spatial augmentations on each frame of the video while maintaining the temporal consistency across frames. We also propose a sampling-based temporal augmentation method to avoid overly enforcing invariance on clips that are distant in time. On Kinetics-600, a linear classifier trained on the representations learned by CVRL achieves 70.4% top-1 accuracy with a 3D-ResNet-50 (R3D-50) backbone, outperforming ImageNet supervised pre-training by 15.7% and SimCLR unsupervised pre-training by 18.8% using the same inflated R3D-50. The performance of CVRL can be further improved to 72.9% with a larger R3D-152 (2x filters) backbone, significantly closing the gap between unsupervised and supervised video representation learning. Our code and models will be available at https://github.com/tensorflow/models/tree/master/official/.

We present a large-scale study on unsupervised spatiotemporal representation learning from videos. With a unified perspective on four recent image-based frameworks, we study a simple objective that can easily generalize all these methods to space-time. Our objective encourages temporally-persistent features in the same video, and in spite of its simplicity, it works surprisingly well across: (i) different unsupervised frameworks, (ii) pre-training datasets, (iii) downstream datasets, and (iv) backbone architectures. We draw a series of intriguing observations from this study, e.g., we discover that encouraging long-spanned persistency can be effective even if the timespan is 60 seconds. In addition to state-of-the-art results in multiple benchmarks, we report a few promising cases in which unsupervised pre-training can outperform its supervised counterpart. Code is made available at https://github.com/facebookresearch/SlowFast

Recently, large-scale pre-trained language-image models like CLIP have shown extraordinary capabilities for understanding spatial contents, but naively transferring such models to video recognition still suffers from unsatisfactory temporal modeling capabilities. Existing methods insert tunable structures into or in parallel with the pre-trained model, which either requires back-propagation through the whole pre-trained model and is thus resource-demanding, or is limited by the temporal reasoning capability of the pre-trained structure. In this work, we present DiST, which disentangles the learning of spatial and temporal aspects of videos. Specifically, DiST uses a dual-encoder structure, where a pre-trained foundation model acts as the spatial encoder, and a lightweight network is introduced as the temporal encoder. An integration branch is inserted between the encoders to fuse spatio-temporal information. The disentangled spatial and temporal learning in DiST is highly efficient because it avoids the back-propagation of massive pre-trained parameters. Meanwhile, we empirically show that disentangled learning with an extra network for integration benefits both spatial and temporal understanding. Extensive experiments on five benchmarks show that DiST delivers better performance than existing state-of-the-art methods by convincing gaps. When pre-training on the large-scale Kinetics-710, we achieve 89.7% on Kinetics-400 with a frozen ViT-L model, which verifies the scalability of DiST. Codes and models can be found in https://github.com/alibaba-mmai-research/DiST.

Vision-language-action (VLA) models show potential for general robotic tasks, but remain challenging in spatiotemporally coherent manipulation, which requires fine-grained representations. Typically, existing methods embed 3D positions into visual representations to enhance the spatial precision of actions. However, these methods struggle to achieve temporally coherent control over action execution. In this work, we propose VLA-4D, a general VLA model with 4D awareness for spatiotemporally coherent robotic manipulation. Our model is guided by two key designs: 1) 4D-aware visual representation. We extract visual features, embed 1D time into 3D positions for 4D embeddings, and fuse them into a unified visual representation via a cross-attention mechanism. 2) Spatiotemporal action representation. We extend conventional spatial action representations with temporal information to enable the spatiotemporal planning, and align the multimodal representations into the LLM for spatiotemporal action prediction. Within this unified framework, the designed visual and action representations jointly make robotic manipulation spatially-smooth and temporally-coherent. In addition, we extend the VLA dataset with temporal action annotations for fine-tuning our model. Extensive experiments have been conducted to verify the superiority of our method across different tasks of robotic manipulation.

Multimodal large language models (MLLMs) have made remarkable progress in either temporal or spatial localization. However, they struggle to perform spatio-temporal video grounding. This limitation stems from two major challenges. Firstly, it is difficult to extract accurate spatio-temporal information of each frame in the video. Secondly, the substantial number of visual tokens makes it challenging to precisely map visual tokens of each frame to their corresponding spatial coordinates. To address these issues, we introduce SpaceVLLM, a MLLM endowed with spatio-temporal video grounding capability. Specifically, we adopt a set of interleaved Spatio-Temporal Aware Queries to capture temporal perception and dynamic spatial information. Moreover, we propose a Query-Guided Space Decoder to establish a corresponding connection between the queries and spatial coordinates. Additionally, due to the lack of spatio-temporal datasets, we construct the Unified Spatio-Temporal Grounding (Uni-STG) dataset, comprising 480K instances across three tasks. This dataset fully exploits the potential of MLLM to simultaneously facilitate localization in both temporal and spatial dimensions. Extensive experiments demonstrate that SpaceVLLM achieves the state-of-the-art performance across 11 benchmarks covering temporal, spatial, spatio-temporal and video understanding tasks, highlighting the effectiveness of our approach. Our code, datasets and model will be released at https://github.com/Jayce1kk/SpaceVLLM.

Contrastive language-image pretraining (CLIP) has demonstrated remarkable success in various image tasks. However, how to extend CLIP with effective temporal modeling is still an open and crucial problem. Existing factorized or joint spatial-temporal modeling trades off between the efficiency and performance. While modeling temporal information within straight through tube is widely adopted in literature, we find that simple frame alignment already provides enough essence without temporal attention. To this end, in this paper, we proposed a novel Implicit Learnable Alignment (ILA) method, which minimizes the temporal modeling effort while achieving incredibly high performance. Specifically, for a frame pair, an interactive point is predicted in each frame, serving as a mutual information rich region. By enhancing the features around the interactive point, two frames are implicitly aligned. The aligned features are then pooled into a single token, which is leveraged in the subsequent spatial self-attention. Our method allows eliminating the costly or insufficient temporal self-attention in video. Extensive experiments on benchmarks demonstrate the superiority and generality of our module. Particularly, the proposed ILA achieves a top-1 accuracy of 88.7% on Kinetics-400 with much fewer FLOPs compared with Swin-L and ViViT-H. Code is released at https://github.com/Francis-Rings/ILA .

Long-term temporal fusion is a crucial but often overlooked technique in camera-based Bird's-Eye-View (BEV) 3D perception. Existing methods are mostly in a parallel manner. While parallel fusion can benefit from long-term information, it suffers from increasing computational and memory overheads as the fusion window size grows. Alternatively, BEVFormer adopts a recurrent fusion pipeline so that history information can be efficiently integrated, yet it fails to benefit from longer temporal frames. In this paper, we explore an embarrassingly simple long-term recurrent fusion strategy built upon the LSS-based methods and find it already able to enjoy the merits from both sides, i.e., rich long-term information and efficient fusion pipeline. A temporal embedding module is further proposed to improve the model's robustness against occasionally missed frames in practical scenarios. We name this simple but effective fusing pipeline VideoBEV. Experimental results on the nuScenes benchmark show that VideoBEV obtains leading performance on various camera-based 3D perception tasks, including object detection (55.4% mAP and 62.9% NDS), segmentation (48.6% vehicle mIoU), tracking (54.8% AMOTA), and motion prediction (0.80m minADE and 0.463 EPA). Code will be available.

Egocentric video-language understanding demands both high efficiency and accurate spatial-temporal modeling. Existing approaches face three key challenges: 1) Excessive pre-training cost arising from multi-stage pre-training pipelines, 2) Ineffective spatial-temporal encoding due to manually split 3D rotary positional embeddings that hinder feature interactions, and 3) Imprecise learning objectives in soft-label multi-instance retrieval, which neglect negative pair correlations. In this paper, we introduce EVA02-AT, a suite of EVA02-based video-language foundation models tailored to egocentric video understanding tasks. EVA02-AT first efficiently transfers an image-based CLIP model into a unified video encoder via a single-stage pretraining. Second, instead of applying rotary positional embeddings to isolated dimensions, we introduce spatial-temporal rotary positional embeddings along with joint attention, which can effectively encode both spatial and temporal information on the entire hidden dimension. This joint encoding of spatial-temporal features enables the model to learn cross-axis relationships, which are crucial for accurately modeling motion and interaction in videos. Third, focusing on multi-instance video-language retrieval tasks, we introduce the Symmetric Multi-Similarity (SMS) loss and a novel training framework that advances all soft labels for both positive and negative pairs, providing a more precise learning objective. Extensive experiments on Ego4D, EPIC-Kitchens-100, and Charades-Ego under zero-shot and fine-tuning settings demonstrate that EVA02-AT achieves state-of-the-art performance across diverse egocentric video-language tasks with fewer parameters. Models with our SMS loss also show significant performance gains on multi-instance retrieval benchmarks. Our code and models are publicly available at https://github.com/xqwang14/EVA02-AT .

In this paper we introduce the Temporo-Spatial Vision Transformer (TSViT), a fully-attentional model for general Satellite Image Time Series (SITS) processing based on the Vision Transformer (ViT). TSViT splits a SITS record into non-overlapping patches in space and time which are tokenized and subsequently processed by a factorized temporo-spatial encoder. We argue, that in contrast to natural images, a temporal-then-spatial factorization is more intuitive for SITS processing and present experimental evidence for this claim. Additionally, we enhance the model's discriminative power by introducing two novel mechanisms for acquisition-time-specific temporal positional encodings and multiple learnable class tokens. The effect of all novel design choices is evaluated through an extensive ablation study. Our proposed architecture achieves state-of-the-art performance, surpassing previous approaches by a significant margin in three publicly available SITS semantic segmentation and classification datasets. All model, training and evaluation codes are made publicly available to facilitate further research.

Pre-training on large-scale video data has become a common recipe for learning transferable spatiotemporal representations in recent years. Despite some progress, existing methods are mostly limited to highly curated datasets (e.g., K400) and exhibit unsatisfactory out-of-the-box representations. We argue that it is due to the fact that they only capture pixel-level knowledge rather than spatiotemporal semantics, which hinders further progress in video understanding. Inspired by the great success of image-text pre-training (e.g., CLIP), we take the first step to exploit language semantics to boost transferable spatiotemporal representation learning. We introduce a new pretext task, Turning to Video for Transcript Sorting (TVTS), which sorts shuffled ASR scripts by attending to learned video representations. We do not rely on descriptive captions and learn purely from video, i.e., leveraging the natural transcribed speech knowledge to provide noisy but useful semantics over time. Our method enforces the vision model to contextualize what is happening over time so that it can re-organize the narrative transcripts, and can seamlessly apply to large-scale uncurated video data in the real world. Our method demonstrates strong out-of-the-box spatiotemporal representations on diverse benchmarks, e.g., +13.6% gains over VideoMAE on SSV2 via linear probing. The code is available at https://github.com/TencentARC/TVTS.

Recent progress in using recurrent neural networks (RNNs) for image description has motivated the exploration of their application for video description. However, while images are static, working with videos requires modeling their dynamic temporal structure and then properly integrating that information into a natural language description. In this context, we propose an approach that successfully takes into account both the local and global temporal structure of videos to produce descriptions. First, our approach incorporates a spatial temporal 3-D convolutional neural network (3-D CNN) representation of the short temporal dynamics. The 3-D CNN representation is trained on video action recognition tasks, so as to produce a representation that is tuned to human motion and behavior. Second we propose a temporal attention mechanism that allows to go beyond local temporal modeling and learns to automatically select the most relevant temporal segments given the text-generating RNN. Our approach exceeds the current state-of-art for both BLEU and METEOR metrics on the Youtube2Text dataset. We also present results on a new, larger and more challenging dataset of paired video and natural language descriptions.

Bird's eye view (BEV) representation is a new perception formulation for autonomous driving, which is based on spatial fusion. Further, temporal fusion is also introduced in BEV representation and gains great success. In this work, we propose a new method that unifies both spatial and temporal fusion and merges them into a unified mathematical formulation. The unified fusion could not only provide a new perspective on BEV fusion but also brings new capabilities. With the proposed unified spatial-temporal fusion, our method could support long-range fusion, which is hard to achieve in conventional BEV methods. Moreover, the BEV fusion in our work is temporal-adaptive and the weights of temporal fusion are learnable. In contrast, conventional methods mainly use fixed and equal weights for temporal fusion. Besides, the proposed unified fusion could avoid information lost in conventional BEV fusion methods and make full use of features. Extensive experiments and ablation studies on the NuScenes dataset show the effectiveness of the proposed method and our method gains the state-of-the-art performance in the map segmentation task.

Recent two-stream deep Convolutional Neural Networks (ConvNets) have made significant progress in recognizing human actions in videos. Despite their success, methods extending the basic two-stream ConvNet have not systematically explored possible network architectures to further exploit spatiotemporal dynamics within video sequences. Further, such networks often use different baseline two-stream networks. Therefore, the differences and the distinguishing factors between various methods using Recurrent Neural Networks (RNN) or convolutional networks on temporally-constructed feature vectors (Temporal-ConvNet) are unclear. In this work, we first demonstrate a strong baseline two-stream ConvNet using ResNet-101. We use this baseline to thoroughly examine the use of both RNNs and Temporal-ConvNets for extracting spatiotemporal information. Building upon our experimental results, we then propose and investigate two different networks to further integrate spatiotemporal information: 1) temporal segment RNN and 2) Inception-style Temporal-ConvNet. We demonstrate that using both RNNs (using LSTMs) and Temporal-ConvNets on spatiotemporal feature matrices are able to exploit spatiotemporal dynamics to improve the overall performance. However, each of these methods require proper care to achieve state-of-the-art performance; for example, LSTMs require pre-segmented data or else they cannot fully exploit temporal information. Our analysis identifies specific limitations for each method that could form the basis of future work. Our experimental results on UCF101 and HMDB51 datasets achieve state-of-the-art performances, 94.1% and 69.0%, respectively, without requiring extensive temporal augmentation.

Event cameras offer unique advantages for vision tasks in challenging environments, yet processing asynchronous event streams remains an open challenge. While existing methods rely on specialized architectures or resource-intensive training, the potential of leveraging modern Visual Foundation Models (VFMs) pretrained on image data remains under-explored for event-based vision. To address this, we propose Temporal-Guided VFM (TGVFM), a novel framework that integrates VFMs with our temporal context fusion block seamlessly to bridge this gap. Our temporal block introduces three key components: (1) Long-Range Temporal Attention to model global temporal dependencies, (2) Dual Spatiotemporal Attention for multi-scale frame correlation, and (3) Deep Feature Guidance Mechanism to fuse semantic-temporal features. By retraining event-to-video models on real-world data and leveraging transformer-based VFMs, TGVFM preserves spatiotemporal dynamics while harnessing pretrained representations. Experiments demonstrate SoTA performance across semantic segmentation, depth estimation, and object detection, with improvements of 16%, 21%, and 16% over existing methods, respectively. Overall, this work unlocks the cross-modality potential of image-based VFMs for event-based vision with temporal reasoning. Code is available at https://github.com/XiaRho/TGVFM.

Long video understanding remains a fundamental challenge for multimodal large language models (MLLMs), particularly in tasks requiring precise temporal reasoning and event localization. Existing approaches typically adopt uniform frame sampling and rely on implicit position encodings to model temporal order. However, these methods struggle with long-range dependencies, leading to critical information loss and degraded temporal comprehension. In this paper, we propose Dynamic Absolute Time Enhancement (DATE) that enhances temporal awareness in MLLMs through the Timestamp Injection Mechanism (TIM) and a semantically guided Temporal-Aware Similarity Sampling (TASS) strategy. Specifically, we interleave video frame embeddings with textual timestamp tokens to construct a continuous temporal reference system. We further reformulate the video sampling problem as a vision-language retrieval task and introduce a two-stage algorithm to ensure both semantic relevance and temporal coverage: enriching each query into a descriptive caption to better align with the vision feature, and sampling key event with a similarity-driven temporally regularized greedy strategy. Our method achieves remarkable improvements w.r.t. absolute time understanding and key event localization, resulting in state-of-the-art performance among 7B and 72B models on hour-long video benchmarks. Particularly, our 7B model even exceeds many 72B models on some benchmarks.

We present an unsupervised representation learning approach that compactly encodes the motion dependencies in videos. Given a pair of images from a video clip, our framework learns to predict the long-term 3D motions. To reduce the complexity of the learning framework, we propose to describe the motion as a sequence of atomic 3D flows computed with RGB-D modality. We use a Recurrent Neural Network based Encoder-Decoder framework to predict these sequences of flows. We argue that in order for the decoder to reconstruct these sequences, the encoder must learn a robust video representation that captures long-term motion dependencies and spatial-temporal relations. We demonstrate the effectiveness of our learned temporal representations on activity classification across multiple modalities and datasets such as NTU RGB+D and MSR Daily Activity 3D. Our framework is generic to any input modality, i.e., RGB, Depth, and RGB-D videos.

The alignment of representations from different modalities has recently been shown to provide insights on the structural similarities and downstream capabilities of different encoders across diverse data types. While significant progress has been made in aligning images with text, the temporal nature of video data remains largely unexplored in this context. In this work, we conduct the first comprehensive study of video-text representation alignment, probing the capabilities of modern video and language encoders. Our findings reveal several key insights. First, we demonstrate that cross-modal alignment highly depends on the richness of both visual (static images vs. multi-frame videos) and text (single caption vs. a collection) data provided at test time, especially when using state-of-the-art video encoders. We propose parametric test-time scaling laws that capture this behavior and show remarkable predictive power against empirical observations. Secondly, we investigate the correlation between semantic alignment and performance on both semantic and non-semantic downstream tasks, providing initial evidence that strong alignment against text encoders may be linked to general-purpose video representation and understanding. Finally, we correlate temporal reasoning with cross-modal alignment providing a challenging test-bed for vision and language models. Overall, our work introduces video-text alignment as an informative zero-shot way to probe the representation power of different encoders for spatio-temporal data. Project page can be found at https://video-prh.github.io/

Temporal knowledge graphs represent temporal facts (s,p,o,tau) relating a subject s and an object o via a relation label p at time tau, where tau could be a time point or time interval. Temporal knowledge graphs may exhibit static temporal patterns at distinct points in time and dynamic temporal patterns between different timestamps. In order to learn a rich set of static and dynamic temporal patterns and apply them for inference, several embedding approaches have been suggested in the literature. However, as most of them resort to single underlying embedding spaces, their capability to model all kinds of temporal patterns was severely limited by having to adhere to the geometric property of their one embedding space. We lift this limitation by an embedding approach that maps temporal facts into a product space of several heterogeneous geometric subspaces with distinct geometric properties, i.e.\ Complex, Dual, and Split-complex spaces. In addition, we propose a temporal-geometric attention mechanism to integrate information from different geometric subspaces conveniently according to the captured relational and temporal information. Experimental results on standard temporal benchmark datasets favorably evaluate our approach against state-of-the-art models.

3D object detection and occupancy prediction are critical tasks in autonomous driving, attracting significant attention. Despite the potential of recent vision-based methods, they encounter challenges under adverse conditions. Thus, integrating cameras with next-generation 4D imaging radar to achieve unified multi-task perception is highly significant, though research in this domain remains limited. In this paper, we propose Doracamom, the first framework that fuses multi-view cameras and 4D radar for joint 3D object detection and semantic occupancy prediction, enabling comprehensive environmental perception. Specifically, we introduce a novel Coarse Voxel Queries Generator that integrates geometric priors from 4D radar with semantic features from images to initialize voxel queries, establishing a robust foundation for subsequent Transformer-based refinement. To leverage temporal information, we design a Dual-Branch Temporal Encoder that processes multi-modal temporal features in parallel across BEV and voxel spaces, enabling comprehensive spatio-temporal representation learning. Furthermore, we propose a Cross-Modal BEV-Voxel Fusion module that adaptively fuses complementary features through attention mechanisms while employing auxiliary tasks to enhance feature quality. Extensive experiments on the OmniHD-Scenes, View-of-Delft (VoD), and TJ4DRadSet datasets demonstrate that Doracamom achieves state-of-the-art performance in both tasks, establishing new benchmarks for multi-modal 3D perception. Code and models will be publicly available.

Denoising diffusion probabilistic models that were initially proposed for realistic image generation have recently shown success in various perception tasks (e.g., object detection and image segmentation) and are increasingly gaining attention in computer vision. However, extending such models to multi-frame human pose estimation is non-trivial due to the presence of the additional temporal dimension in videos. More importantly, learning representations that focus on keypoint regions is crucial for accurate localization of human joints. Nevertheless, the adaptation of the diffusion-based methods remains unclear on how to achieve such objective. In this paper, we present DiffPose, a novel diffusion architecture that formulates video-based human pose estimation as a conditional heatmap generation problem. First, to better leverage temporal information, we propose SpatioTemporal Representation Learner which aggregates visual evidences across frames and uses the resulting features in each denoising step as a condition. In addition, we present a mechanism called Lookup-based MultiScale Feature Interaction that determines the correlations between local joints and global contexts across multiple scales. This mechanism generates delicate representations that focus on keypoint regions. Altogether, by extending diffusion models, we show two unique characteristics from DiffPose on pose estimation task: (i) the ability to combine multiple sets of pose estimates to improve prediction accuracy, particularly for challenging joints, and (ii) the ability to adjust the number of iterative steps for feature refinement without retraining the model. DiffPose sets new state-of-the-art results on three benchmarks: PoseTrack2017, PoseTrack2018, and PoseTrack21.

Egocentric gaze anticipation serves as a key building block for the emerging capability of Augmented Reality. Notably, gaze behavior is driven by both visual cues and audio signals during daily activities. Motivated by this observation, we introduce the first model that leverages both the video and audio modalities for egocentric gaze anticipation. Specifically, we propose a Contrastive Spatial-Temporal Separable (CSTS) fusion approach that adopts two modules to separately capture audio-visual correlations in spatial and temporal dimensions, and applies a contrastive loss on the re-weighted audio-visual features from fusion modules for representation learning. We conduct extensive ablation studies and thorough analysis using two egocentric video datasets: Ego4D and Aria, to validate our model design. We demonstrate the audio improves the performance by +2.5% and +2.4% on the two datasets. Our model also outperforms the prior state-of-the-art methods by at least +1.9% and +1.6%. Moreover, we provide visualizations to show the gaze anticipation results and provide additional insights into audio-visual representation learning. The code and data split are available on our website (https://bolinlai.github.io/CSTS-EgoGazeAnticipation/).

We present SS4D, a native 4D generative model that synthesizes dynamic 3D objects directly from monocular video. Unlike prior approaches that construct 4D representations by optimizing over 3D or video generative models, we train a generator directly on 4D data, achieving high fidelity, temporal coherence, and structural consistency. At the core of our method is a compressed set of structured spacetime latents. Specifically, (1) To address the scarcity of 4D training data, we build on a pre-trained single-image-to-3D model, preserving strong spatial consistency. (2) Temporal consistency is enforced by introducing dedicated temporal layers that reason across frames. (3) To support efficient training and inference over long video sequences, we compress the latent sequence along the temporal axis using factorized 4D convolutions and temporal downsampling blocks. In addition, we employ a carefully designed training strategy to enhance robustness against occlusion

There has been tremendous progress in multimodal Large Language Models (LLMs). Recent works have extended these models to video input with promising instruction following capabilities. However, an important missing piece is temporal localization. These models cannot accurately answer the "When?" questions. We identify three key aspects that limit their temporal localization capabilities: (i) time representation, (ii) architecture, and (iii) data. We address these shortcomings by proposing Language Instructed Temporal-Localization Assistant (LITA) with the following features: (1) We introduce time tokens that encode timestamps relative to the video length to better represent time in videos. (2) We introduce SlowFast tokens in the architecture to capture temporal information at fine temporal resolution. (3) We emphasize temporal localization data for LITA. In addition to leveraging existing video datasets with timestamps, we propose a new task, Reasoning Temporal Localization (RTL), along with the dataset, ActivityNet-RTL, for learning and evaluating this task. Reasoning temporal localization requires both the reasoning and temporal localization of Video LLMs. LITA demonstrates strong performance on this challenging task, nearly doubling the temporal mean intersection-over-union (mIoU) of baselines. In addition, we show that our emphasis on temporal localization also substantially improves video-based text generation compared to existing Video LLMs, including a 36% relative improvement of Temporal Understanding. Code is available at: https://github.com/NVlabs/LITA

Contrastive learning methods have significantly narrowed the gap between supervised and unsupervised learning on computer vision tasks. In this paper, we explore their application to geo-located datasets, e.g. remote sensing, where unlabeled data is often abundant but labeled data is scarce. We first show that due to their different characteristics, a non-trivial gap persists between contrastive and supervised learning on standard benchmarks. To close the gap, we propose novel training methods that exploit the spatio-temporal structure of remote sensing data. We leverage spatially aligned images over time to construct temporal positive pairs in contrastive learning and geo-location to design pre-text tasks. Our experiments show that our proposed method closes the gap between contrastive and supervised learning on image classification, object detection and semantic segmentation for remote sensing. Moreover, we demonstrate that the proposed method can also be applied to geo-tagged ImageNet images, improving downstream performance on various tasks. Project Webpage can be found at this link geography-aware-ssl.github.io.

Spatio-temporal grounding describes the task of localizing events in space and time, e.g., in video data, based on verbal descriptions only. Models for this task are usually trained with human-annotated sentences and bounding box supervision. This work addresses this task from a multimodal supervision perspective, proposing a framework for spatio-temporal action grounding trained on loose video and subtitle supervision only, without human annotation. To this end, we combine local representation learning, which focuses on leveraging fine-grained spatial information, with a global representation encoding that captures higher-level representations and incorporates both in a joint approach. To evaluate this challenging task in a real-life setting, a new benchmark dataset is proposed providing dense spatio-temporal grounding annotations in long, untrimmed, multi-action instructional videos for over 5K events. We evaluate the proposed approach and other methods on the proposed and standard downstream tasks showing that our method improves over current baselines in various settings, including spatial, temporal, and untrimmed multi-action spatio-temporal grounding.

This paper presents VideoLoom, a unified Video Large Language Model (Video LLM) for joint spatial-temporal understanding. To facilitate the development of fine-grained spatial and temporal localization capabilities, we curate LoomData-8.7k, a human-centric video dataset with temporally grounded and spatially localized captions. With this, VideoLoom achieves state-of-the-art or highly competitive performance across a variety of spatial and temporal benchmarks (e.g., 63.1 J&F on ReVOS for referring video object segmentation, and 48.3 R1@0.7 on Charades-STA for temporal grounding). In addition, we introduce LoomBench, a novel benchmark consisting of temporal, spatial, and compositional video-question pairs, enabling a comprehensive evaluation of Video LLMs from diverse aspects. Collectively, these contributions offer a universal and effective suite for joint spatial-temporal video understanding, setting a new standard in multimodal intelligence.

Several video understanding tasks, such as natural language temporal video grounding, temporal activity localization, and audio description generation, require "temporally dense" reasoning over frames sampled at high temporal resolution. However, computing frame-level features for these tasks is computationally expensive given the temporal resolution requirements. In this paper, we make three contributions to reduce the cost of computing features for temporally dense tasks. First, we introduce a vision transformer (ViT) architecture, dubbed ResidualViT, that leverages the large temporal redundancy in videos to efficiently compute temporally dense frame-level features. Our architecture incorporates (i) learnable residual connections that ensure temporal consistency across consecutive frames and (ii) a token reduction module that enhances processing speed by selectively discarding temporally redundant information while reusing weights of a pretrained foundation model. Second, we propose a lightweight distillation strategy to approximate the frame-level features of the original foundation model. Finally, we evaluate our approach across four tasks and five datasets, in both zero-shot and fully supervised settings, demonstrating significant reductions in computational cost (up to 60%) and improvements in inference speed (up to 2.5x faster), all while closely approximating the accuracy of the original foundation model.

Many motion-centric video analysis tasks, such as atomic actions, detecting atypical motor behavior in individuals with autism, or analyzing articulatory motion in real-time MRI of human speech, require efficient and interpretable temporal modeling. Capturing temporal dynamics is a central challenge in video analysis, often requiring significant computational resources and fine-grained annotations that are not widely available. This paper presents MOOSE (Motion Flow Over Spatial Space), a novel temporally-centric video encoder explicitly integrating optical flow with spatial embeddings to model temporal information efficiently, inspired by human perception of motion. Unlike prior models, MOOSE takes advantage of rich, widely available pre-trained visual and optical flow encoders instead of training video models from scratch. This significantly reduces computational complexity while enhancing temporal interpretability. Our primary contributions includes (1) proposing a computationally efficient temporally-centric architecture for video understanding (2) demonstrating enhanced interpretability in modeling temporal dynamics; and (3) achieving state-of-the-art performance on diverse benchmarks, including clinical, medical, and standard action recognition datasets, confirming the broad applicability and effectiveness of our approach.

Although contrastive and other representation-learning methods have long been explored in vision and NLP, their adoption in modern time series forecasters remains limited. We believe they hold strong promise for this domain. To unlock this potential, we explicitly align past and future representations, thereby bridging the distributional gap between input histories and future targets. To this end, we introduce TimeAlign, a lightweight, plug-and-play framework that establishes a new representation paradigm, distinct from contrastive learning, by aligning auxiliary features via a simple reconstruction task and feeding them back into any base forecaster. Extensive experiments across eight benchmarks verify its superior performance. Further studies indicate that the gains arise primarily from correcting frequency mismatches between historical inputs and future outputs. Additionally, we provide two theoretical justifications for how reconstruction improves forecasting generalization and how alignment increases the mutual information between learned representations and predicted targets. The code is available at https://github.com/TROUBADOUR000/TimeAlign.

Temporal modelling is the key for efficient video action recognition. While understanding temporal information can improve recognition accuracy for dynamic actions, removing temporal redundancy and reusing past features can significantly save computation leading to efficient action recognition. In this paper, we introduce an adaptive temporal fusion network, called AdaFuse, that dynamically fuses channels from current and past feature maps for strong temporal modelling. Specifically, the necessary information from the historical convolution feature maps is fused with current pruned feature maps with the goal of improving both recognition accuracy and efficiency. In addition, we use a skipping operation to further reduce the computation cost of action recognition. Extensive experiments on Something V1 & V2, Jester and Mini-Kinetics show that our approach can achieve about 40% computation savings with comparable accuracy to state-of-the-art methods. The project page can be found at https://mengyuest.github.io/AdaFuse/

3D visual perception tasks, including 3D detection and map segmentation based on multi-camera images, are essential for autonomous driving systems. In this work, we present a new framework termed BEVFormer, which learns unified BEV representations with spatiotemporal transformers to support multiple autonomous driving perception tasks. In a nutshell, BEVFormer exploits both spatial and temporal information by interacting with spatial and temporal space through predefined grid-shaped BEV queries. To aggregate spatial information, we design spatial cross-attention that each BEV query extracts the spatial features from the regions of interest across camera views. For temporal information, we propose temporal self-attention to recurrently fuse the history BEV information. Our approach achieves the new state-of-the-art 56.9\% in terms of NDS metric on the nuScenes test set, which is 9.0 points higher than previous best arts and on par with the performance of LiDAR-based baselines. We further show that BEVFormer remarkably improves the accuracy of velocity estimation and recall of objects under low visibility conditions. The code is available at https://github.com/zhiqi-li/BEVFormer.

Vision-language models (VLMs) have demonstrated strong performance in 2D scene understanding and generation, but extending this unification to the physical world remains an open challenge. Existing 3D and 4D approaches typically embed scene geometry into autoregressive model for semantic understanding and diffusion model for content generation. This paradigm gap prevents a single model from jointly handling both tasks, especially in dynamic 4D settings where spatiotemporal modeling is critical. We propose Uni4D-LLM, the first unified VLM framework with spatiotemporal awareness for 4D scene understanding and generation. Our design is guided by two key insights: 1) Unification requires a shared representation. We extract semantic features for understanding and noisy-injected appearance features for generation, incorporate 4D geometric cues, and fuse them into a spatiotemporal-aware visual representation through adaptive cross-attention. 2) Unification requires a shared architecture. Both autoregression and diffusion are built on Transformer backbones, and this enables integration into a single LLM with task-specific heads. By aligning visual and linguistic representations, our Uni4D-LLM produces predictions for both understanding and generation within one Transformer-based framework. We further apply instruction fine-tuning on diverse 4D vision-language datasets to improve generalization across tasks. Extensive experiments on multiple benchmarks demonstrate that Uni4D-LLM achieves competitive or superior results compared to state-of-the-art models and offers the first true unification of 4D scene understanding and generation.

Applying Multimodal Large Language Models (MLLMs) to video understanding presents significant challenges due to the need to model temporal relations across frames. Existing approaches adopt either implicit temporal modeling, relying solely on the LLM decoder, or explicit temporal modeling, employing auxiliary temporal encoders. To investigate this debate between the two paradigms, we propose the Stackable Temporal Encoder (STE). STE enables flexible explicit temporal modeling with adjustable temporal receptive fields and token compression ratios. Using STE, we systematically compare implicit and explicit temporal modeling across dimensions such as overall performance, token compression effectiveness, and temporal-specific understanding. We also explore STE's design considerations and broader impacts as a plug-in module and in image modalities. Our findings emphasize the critical role of explicit temporal modeling, providing actionable insights to advance video MLLMs.

This paper presents a simple yet effective approach to modeling space-time correspondences in the context of video object segmentation. Unlike most existing approaches, we establish correspondences directly between frames without re-encoding the mask features for every object, leading to a highly efficient and robust framework. With the correspondences, every node in the current query frame is inferred by aggregating features from the past in an associative fashion. We cast the aggregation process as a voting problem and find that the existing inner-product affinity leads to poor use of memory with a small (fixed) subset of memory nodes dominating the votes, regardless of the query. In light of this phenomenon, we propose using the negative squared Euclidean distance instead to compute the affinities. We validated that every memory node now has a chance to contribute, and experimentally showed that such diversified voting is beneficial to both memory efficiency and inference accuracy. The synergy of correspondence networks and diversified voting works exceedingly well, achieves new state-of-the-art results on both DAVIS and YouTubeVOS datasets while running significantly faster at 20+ FPS for multiple objects without bells and whistles.

In this research, we present a novel approach to motion customization in video generation, addressing the widespread gap in the thorough exploration of motion representation within video generative models. Recognizing the unique challenges posed by video's spatiotemporal nature, our method introduces Motion Embeddings, a set of explicit, temporally coherent one-dimensional embeddings derived from a given video. These embeddings are designed to integrate seamlessly with the temporal transformer modules of video diffusion models, modulating self-attention computations across frames without compromising spatial integrity. Our approach offers a compact and efficient solution to motion representation and enables complex manipulations of motion characteristics through vector arithmetic in the embedding space. Furthermore, we identify the Temporal Discrepancy in video generative models, which refers to variations in how different motion modules process temporal relationships between frames. We leverage this understanding to optimize the integration of our motion embeddings. Our contributions include the introduction of a tailored motion embedding for customization tasks, insights into the temporal processing differences in video models, and a demonstration of the practical advantages and effectiveness of our method through extensive experiments.

The capabilities of large language models (LLMs) have sparked debate over whether such systems just learn an enormous collection of superficial statistics or a coherent model of the data generating process -- a world model. We find evidence for the latter by analyzing the learned representations of three spatial datasets (world, US, NYC places) and three temporal datasets (historical figures, artworks, news headlines) in the Llama-2 family of models. We discover that LLMs learn linear representations of space and time across multiple scales. These representations are robust to prompting variations and unified across different entity types (e.g. cities and landmarks). In addition, we identify individual ``space neurons'' and ``time neurons'' that reliably encode spatial and temporal coordinates. Our analysis demonstrates that modern LLMs acquire structured knowledge about fundamental dimensions such as space and time, supporting the view that they learn not merely superficial statistics, but literal world models.

Text-to-video retrieval requires precise alignment between language and temporally rich video signals. Existing methods predominantly exploit visual cues and often overlook complementary audio semantics or adopt coarse fusion strategies, leading to suboptimal multimodal representations. We present GAID, a framework that jointly address this gap via two key components: (i) a Frame-level Gated Fusion (FGF) that adaptively integrates audio and visual features under textual guidance, enabling fine-grained temporal alignment; and (ii) a Directional Adaptive Semantic Perturbation (DASP) that injects structure-aware perturbations into text embeddings, enhancing robustness and discrimination without incurring multi-pass inference. These modules complement each other -- fusion reduces modality gaps while perturbation regularizes cross-modal matching -- yielding more stable and expressive representations. Extensive experiments on MSR-VTT, DiDeMo, LSMDC, and VATEX show consistent state-of-the-art results across all retrieval metrics with notable efficiency gains. Our code is available at https://github.com/YangBowenn/GAID.

Large video-language models (LVLMs) have shown remarkable performance across various video-language tasks. However, they encounter significant challenges when processing long videos because of the large number of video frames involved. Downsampling long videos in either space or time can lead to visual hallucinations, making it difficult to accurately interpret long videos. Motivated by human hierarchical temporal search strategies, we propose TimeSearch, a novel framework enabling LVLMs to understand long videos in a human-like manner. TimeSearch integrates two human-like primitives into a unified autoregressive LVLM: 1) Spotlight efficiently identifies relevant temporal events through a Temporal-Augmented Frame Representation (TAFR), explicitly binding visual features with timestamps; 2) Reflection evaluates the correctness of the identified events, leveraging the inherent temporal self-reflection capabilities of LVLMs. TimeSearch progressively explores key events and prioritizes temporal search based on reflection confidence. Extensive experiments on challenging long-video benchmarks confirm that TimeSearch substantially surpasses previous state-of-the-art, improving the accuracy from 41.8\% to 51.5\% on the LVBench. Additionally, experiments on temporal grounding demonstrate that appropriate TAFR is adequate to effectively stimulate the surprising temporal grounding ability of LVLMs in a simpler yet versatile manner, which improves mIoU on Charades-STA by 11.8\%. The code will be released.

Previous text-guided video editing methods often suffer from temporal inconsistency, motion distortion, and-most notably-limited domain transformation. We attribute these limitations to insufficient modeling of spatiotemporal pixel relevance during the editing process. To address this, we propose STR-Match, a training-free video editing algorithm that produces visually appealing and spatiotemporally coherent videos through latent optimization guided by our novel STR score. The score captures spatiotemporal pixel relevance across adjacent frames by leveraging 2D spatial attention and 1D temporal modules in text-to-video (T2V) diffusion models, without the overhead of computationally expensive 3D attention mechanisms. Integrated into a latent optimization framework with a latent mask, STR-Match generates temporally consistent and visually faithful videos, maintaining strong performance even under significant domain transformations while preserving key visual attributes of the source. Extensive experiments demonstrate that STR-Match consistently outperforms existing methods in both visual quality and spatiotemporal consistency.

We present Spatial Region 3D (SR-3D) aware vision-language model that connects single-view 2D images and multi-view 3D data through a shared visual token space. SR-3D supports flexible region prompting, allowing users to annotate regions with bounding boxes, segmentation masks on any frame, or directly in 3D, without the need for exhaustive multi-frame labeling. We achieve this by enriching 2D visual features with 3D positional embeddings, which allows the 3D model to draw upon strong 2D priors for more accurate spatial reasoning across frames, even when objects of interest do not co-occur within the same view. Extensive experiments on both general 2D vision language and specialized 3D spatial benchmarks demonstrate that SR-3D achieves state-of-the-art performance, underscoring its effectiveness for unifying 2D and 3D representation space on scene understanding. Moreover, we observe applicability to in-the-wild videos without sensory 3D inputs or ground-truth 3D annotations, where SR-3D accurately infers spatial relationships and metric measurements.

Recent advancements in text-to-image (T2I) generation using diffusion models have enabled cost-effective video-editing applications by leveraging pre-trained models, eliminating the need for resource-intensive training. However, the frame-independence of T2I generation often results in poor temporal consistency. Existing methods address this issue through temporal layer fine-tuning or inference-based temporal propagation, but these approaches suffer from high training costs or limited temporal coherence. To address these challenges, we propose a General and Efficient Adapter (GE-Adapter) that integrates temporal-spatial and semantic consistency with Baliteral DDIM inversion. This framework introduces three key components: (1) Frame-based Temporal Consistency Blocks (FTC Blocks) to capture frame-specific features and enforce smooth inter-frame transitions via temporally-aware loss functions; (2) Channel-dependent Spatial Consistency Blocks (SCD Blocks) employing bilateral filters to enhance spatial coherence by reducing noise and artifacts; and (3) Token-based Semantic Consistency Module (TSC Module) to maintain semantic alignment using shared prompt tokens and frame-specific tokens. Our method significantly improves perceptual quality, text-image alignment, and temporal coherence, as demonstrated on the MSR-VTT dataset. Additionally, it achieves enhanced fidelity and frame-to-frame coherence, offering a practical solution for T2V editing.

Spatio-temporal video grounding (STVG) aims at localizing the spatio-temporal tube of a video, as specified by the input text query. In this paper, we utilize multimodal large language models (MLLMs) to explore a zero-shot solution in STVG. We reveal two key insights about MLLMs: (1) MLLMs tend to dynamically assign special tokens, referred to as grounding tokens, for grounding the text query; and (2) MLLMs often suffer from suboptimal grounding due to the inability to fully integrate the cues in the text query (e.g., attributes, actions) for inference. Based on these insights, we propose a MLLM-based zero-shot framework for STVG, which includes novel decomposed spatio-temporal highlighting (DSTH) and temporal-augmented assembling (TAS) strategies to unleash the reasoning ability of MLLMs. The DSTH strategy first decouples the original query into attribute and action sub-queries for inquiring the existence of the target both spatially and temporally. It then uses a novel logit-guided re-attention (LRA) module to learn latent variables as spatial and temporal prompts, by regularizing token predictions for each sub-query. These prompts highlight attribute and action cues, respectively, directing the model's attention to reliable spatial and temporal related visual regions. In addition, as the spatial grounding by the attribute sub-query should be temporally consistent, we introduce the TAS strategy to assemble the predictions using the original video frames and the temporal-augmented frames as inputs to help improve temporal consistency. We evaluate our method on various MLLMs, and show that it outperforms SOTA methods on three common STVG benchmarks. The code will be available at https://github.com/zaiquanyang/LLaVA_Next_STVG.

Understanding videos requires more than answering open ended questions, it demands the ability to pinpoint when events occur and how entities interact across time. While recent Video LLMs have achieved remarkable progress in holistic reasoning, they remain coarse in temporal perception: timestamps are encoded only implicitly, frame level features are weak in capturing continuity, and language vision alignment often drifts from the entities of interest. In this paper, we present Grounded VideoDiT, a Video LLM designed to overcome these limitations by introducing three key innovations. First, a Diffusion Temporal Latent (DTL) encoder enhances boundary sensitivity and maintains temporal consistency. Second, object grounded representations explicitly bind query entities to localized visual evidence, strengthening alignment. Third, a mixed token scheme with discrete temporal tokens provides explicit timestamp modeling, enabling fine grained temporal reasoning. Together, these designs equip Grounded VideoDiT with robust grounding capabilities, as validated by state of the art results on Charades STA, NExT GQA, and multiple VideoQA benchmarks.

We present a novel technique for self-supervised video representation learning by: (a) decoupling the learning objective into two contrastive subtasks respectively emphasizing spatial and temporal features, and (b) performing it hierarchically to encourage multi-scale understanding. Motivated by their effectiveness in supervised learning, we first introduce spatial-temporal feature learning decoupling and hierarchical learning to the context of unsupervised video learning. We show by experiments that augmentations can be manipulated as regularization to guide the network to learn desired semantics in contrastive learning, and we propose a way for the model to separately capture spatial and temporal features at multiple scales. We also introduce an approach to overcome the problem of divergent levels of instance invariance at different hierarchies by modeling the invariance as loss weights for objective re-weighting. Experiments on downstream action recognition benchmarks on UCF101 and HMDB51 show that our proposed Hierarchically Decoupled Spatial-Temporal Contrast (HDC) makes substantial improvements over directly learning spatial-temporal features as a whole and achieves competitive performance when compared with other state-of-the-art unsupervised methods. Code will be made available.

In text-video retrieval, recent works have benefited from the powerful learning capabilities of pre-trained text-image foundation models (e.g., CLIP) by adapting them to the video domain. A critical problem for them is how to effectively capture the rich semantics inside the video using the image encoder of CLIP. To tackle this, state-of-the-art methods adopt complex cross-modal modeling techniques to fuse the text information into video frame representations, which, however, incurs severe efficiency issues in large-scale retrieval systems as the video representations must be recomputed online for every text query. In this paper, we discard this problematic cross-modal fusion process and aim to learn semantically-enhanced representations purely from the video, so that the video representations can be computed offline and reused for different texts. Concretely, we first introduce a spatial-temporal "Prompt Cube" into the CLIP image encoder and iteratively switch it within the encoder layers to efficiently incorporate the global video semantics into frame representations. We then propose to apply an auxiliary video captioning objective to train the frame representations, which facilitates the learning of detailed video semantics by providing fine-grained guidance in the semantic space. With a naive temporal fusion strategy (i.e., mean-pooling) on the enhanced frame representations, we obtain state-of-the-art performances on three benchmark datasets, i.e., MSR-VTT, MSVD, and LSMDC.

Next-generation AI companions must go beyond general video understanding to resolve spatial and temporal references in dynamic, real-world environments. Existing Video Large Language Models (Video LLMs), while capable of coarse-level comprehension, struggle with fine-grained, spatiotemporal reasoning, especially when user queries rely on time-based event references for temporal anchoring, or gestural cues for spatial anchoring to clarify object references and positions. To bridge this critical gap, we introduce Strefer, a synthetic instruction data generation framework designed to equip Video LLMs with spatiotemporal referring and reasoning capabilities. Strefer produces diverse instruction-tuning data using a data engine that pseudo-annotates temporally dense, fine-grained video metadata, capturing rich spatial and temporal information in a structured manner, including subjects, objects, their locations as masklets, and their action descriptions and timelines. Our approach enhances the ability of Video LLMs to interpret spatial and temporal references, fostering more versatile, space-time-aware reasoning essential for real-world AI companions. Without using proprietary models, costly human annotation, or the need to annotate large volumes of new videos, experimental evaluations show that models trained with data produced by Strefer outperform baselines on tasks requiring spatial and temporal disambiguation. Additionally, these models exhibit enhanced space-time-aware reasoning, establishing a new foundation for perceptually grounded, instruction-tuned Video LLMs.

The correlation between the vision and text is essential for video moment retrieval (VMR), however, existing methods heavily rely on separate pre-training feature extractors for visual and textual understanding. Without sufficient temporal boundary annotations, it is non-trivial to learn universal video-text alignments. In this work, we explore multi-modal correlations derived from large-scale image-text data to facilitate generalisable VMR. To address the limitations of image-text pre-training models on capturing the video changes, we propose a generic method, referred to as Visual-Dynamic Injection (VDI), to empower the model's understanding of video moments. Whilst existing VMR methods are focusing on building temporal-aware video features, being aware of the text descriptions about the temporal changes is also critical but originally overlooked in pre-training by matching static images with sentences. Therefore, we extract visual context and spatial dynamic information from video frames and explicitly enforce their alignments with the phrases describing video changes (e.g. verb). By doing so, the potentially relevant visual and motion patterns in videos are encoded in the corresponding text embeddings (injected) so to enable more accurate video-text alignments. We conduct extensive experiments on two VMR benchmark datasets (Charades-STA and ActivityNet-Captions) and achieve state-of-the-art performances. Especially, VDI yields notable advantages when being tested on the out-of-distribution splits where the testing samples involve novel scenes and vocabulary.

Existing video-language pre-training methods primarily focus on instance-level alignment between video clips and captions via global contrastive learning but neglect rich fine-grained local information in both videos and text, which is of importance to downstream tasks requiring temporal localization and semantic reasoning. A powerful model is expected to be capable of capturing region-object correspondences and recognizing scene changes in a video clip, reflecting spatial and temporal granularity, respectively. To strengthen model's understanding into such fine-grained details, we propose a simple yet effective video-language modeling framework, S-ViLM, by exploiting the intrinsic structures of these two modalities. It includes two novel designs, inter-clip spatial grounding and intra-clip temporal grouping, to promote learning region-object alignment and temporal-aware features, simultaneously. Comprehensive evaluations demonstrate that S-ViLM performs favorably against existing approaches in learning more expressive representations. Specifically, S-ViLM surpasses the state-of-the-art methods substantially on four representative downstream tasks, covering text-video retrieval, video question answering, video action recognition, and temporal action localization.

Large Multimodal Models (LMMs) have achieved remarkable progress in aligning and generating content across text and image modalities. However, the potential of using non-visual, continuous sequential, as a conditioning signal for high-fidelity image generation remains largely unexplored. Furthermore, existing methods that convert series into "pseudo-images" for temporal forecasting fail to establish semantic-level alignment. In this paper, we propose TimeArtist, a temporal-visual conversion framework that pioneers semantic-level alignment between time series fluctuations and visual concepts. It pioneers a "warmup-align" paradigm: first, a dual-autoencoder and shared quantizer are self-supervised trained on large-scale datasets to learn modality-shared representations. Then, the encoders and quantizer are frozen, and a projection is introduced to align temporal and visual samples at the representation level. TimeArtist establishes a versatile cross-modal framework, enabling high-quality, diverse image generation directly from time series, while capturing temporal fluctuation patterns to render images as styles transfer. Extensive experiments show that TimeArtist achieves satisfactory performance in image generation metrics, while also attaining superior results in zero-shot temporal tasks. Our work establishes a new paradigm for cross-modal generation, bridging the gap between temporal dynamics and visual semantics.

Contrastive language-image pre-training aligns the features of text-image pairs in a common latent space via distinct encoders for each modality. While this approach achieves impressive performance in several zero-shot tasks, it cannot natively handle multimodal inputs, i.e., encoding image and text into a single feature vector. As a remedy, it is common practice to use additional modules to merge the features extracted by the unimodal encoders. In this work, we present FuseLIP, an alternative architecture for multimodal embedding. Leveraging recent progress in discrete image tokenizers, we propose to use a single transformer model which operates on an extended vocabulary of text and image tokens. This early fusion approach allows the different modalities to interact at each depth of encoding and obtain richer representations compared to common late fusion. We collect new datasets for multimodal pre-training and evaluation, designing challenging tasks for multimodal encoder models. We show that FuseLIP outperforms other approaches in multimodal embedding tasks such as VQA and text-guided image transformation retrieval, while being comparable to baselines on unimodal tasks.

We present VideoFactory, an innovative framework for generating high-quality open-domain videos. VideoFactory excels in producing high-definition (1376x768), widescreen (16:9) videos without watermarks, creating an engaging user experience. Generating videos guided by text instructions poses significant challenges, such as modeling the complex relationship between space and time, and the lack of large-scale text-video paired data. Previous approaches extend pretrained text-to-image generation models by adding temporal 1D convolution/attention modules for video generation. However, these approaches overlook the importance of jointly modeling space and time, inevitably leading to temporal distortions and misalignment between texts and videos. In this paper, we propose a novel approach that strengthens the interaction between spatial and temporal perceptions. In particular, we utilize a swapped cross-attention mechanism in 3D windows that alternates the "query" role between spatial and temporal blocks, enabling mutual reinforcement for each other. To fully unlock model capabilities for high-quality video generation, we curate a large-scale video dataset called HD-VG-130M. This dataset comprises 130 million text-video pairs from the open-domain, ensuring high-definition, widescreen and watermark-free characters. Objective metrics and user studies demonstrate the superiority of our approach in terms of per-frame quality, temporal correlation, and text-video alignment, with clear margins.

Temporal interpolation often plays a crucial role to learn meaningful representations in dynamic scenes. In this paper, we propose a novel method to train spatiotemporal neural radiance fields of dynamic scenes based on temporal interpolation of feature vectors. Two feature interpolation methods are suggested depending on underlying representations, neural networks or grids. In the neural representation, we extract features from space-time inputs via multiple neural network modules and interpolate them based on time frames. The proposed multi-level feature interpolation network effectively captures features of both short-term and long-term time ranges. In the grid representation, space-time features are learned via four-dimensional hash grids, which remarkably reduces training time. The grid representation shows more than 100 times faster training speed than the previous neural-net-based methods while maintaining the rendering quality. Concatenating static and dynamic features and adding a simple smoothness term further improve the performance of our proposed models. Despite the simplicity of the model architectures, our method achieved state-of-the-art performance both in rendering quality for the neural representation and in training speed for the grid representation.

Sounding Video Generation (SVG) remains a challenging task due to the inherent structural misalignment between audio and video, as well as the high computational cost of multimodal data processing. In this paper, we introduce ProAV-DiT, a Projected Latent Diffusion Transformer designed for efficient and synchronized audio-video generation. To address structural inconsistencies, we preprocess raw audio into video-like representations, aligning both the temporal and spatial dimensions between audio and video. At its core, ProAV-DiT adopts a Multi-scale Dual-stream Spatio-Temporal Autoencoder (MDSA), which projects both modalities into a unified latent space using orthogonal decomposition, enabling fine-grained spatiotemporal modeling and semantic alignment. To further enhance temporal coherence and modality-specific fusion, we introduce a multi-scale attention mechanism, which consists of multi-scale temporal self-attention and group cross-modal attention. Furthermore, we stack the 2D latents from MDSA into a unified 3D latent space, which is processed by a spatio-temporal diffusion Transformer. This design efficiently models spatiotemporal dependencies, enabling the generation of high-fidelity synchronized audio-video content while reducing computational overhead. Extensive experiments conducted on standard benchmarks demonstrate that ProAV-DiT outperforms existing methods in both generation quality and computational efficiency.

This paper studies a conceptually simple extension of Masked Autoencoders (MAE) to spatiotemporal representation learning from videos. We randomly mask out spacetime patches in videos and learn an autoencoder to reconstruct them in pixels. Interestingly, we show that our MAE method can learn strong representations with almost no inductive bias on spacetime (only except for patch and positional embeddings), and spacetime-agnostic random masking performs the best. We observe that the optimal masking ratio is as high as 90% (vs. 75% on images), supporting the hypothesis that this ratio is related to information redundancy of the data. A high masking ratio leads to a large speedup, e.g., > 4x in wall-clock time or even more. We report competitive results on several challenging video datasets using vanilla Vision Transformers. We observe that MAE can outperform supervised pre-training by large margins. We further report encouraging results of training on real-world, uncurated Instagram data. Our study suggests that the general framework of masked autoencoding (BERT, MAE, etc.) can be a unified methodology for representation learning with minimal domain knowledge.

Self-supervised methods have shown remarkable progress in learning high-level semantics and low-level temporal correspondence. Building on these results, we take one step further and explore the possibility of integrating these two features to enhance object-centric representations. Our preliminary experiments indicate that query slot attention can extract different semantic components from the RGB feature map, while random sampling based slot attention can exploit temporal correspondence cues between frames to assist instance identification. Motivated by this, we propose a novel semantic-aware masked slot attention on top of the fused semantic features and correspondence maps. It comprises two slot attention stages with a set of shared learnable Gaussian distributions. In the first stage, we use the mean vectors as slot initialization to decompose potential semantics and generate semantic segmentation masks through iterative attention. In the second stage, for each semantics, we randomly sample slots from the corresponding Gaussian distribution and perform masked feature aggregation within the semantic area to exploit temporal correspondence patterns for instance identification. We adopt semantic- and instance-level temporal consistency as self-supervision to encourage temporally coherent object-centric representations. Our model effectively identifies multiple object instances with semantic structure, reaching promising results on unsupervised video object discovery. Furthermore, we achieve state-of-the-art performance on dense label propagation tasks, demonstrating the potential for object-centric analysis. The code is released at https://github.com/shvdiwnkozbw/SMTC.

Recent advances in video-based multimodal large language models (Video-LLMs) have significantly improved video understanding by processing videos as sequences of image frames. However, many existing methods treat frames independently in the vision backbone, lacking explicit temporal modeling, which limits their ability to capture dynamic patterns and efficiently handle long videos. To address these limitations, we introduce STORM (Spatiotemporal TOken Reduction for Multimodal LLMs), a novel architecture incorporating a dedicated temporal encoder between the image encoder and the LLM. Our temporal encoder leverages the Mamba State Space Model to integrate temporal information into image tokens, generating enriched representations that preserve inter-frame dynamics across the entire video sequence. This enriched encoding not only enhances video reasoning capabilities but also enables effective token reduction strategies, including test-time sampling and training-based temporal and spatial pooling, substantially reducing computational demands on the LLM without sacrificing key temporal information. By integrating these techniques, our approach simultaneously reduces training and inference latency while improving performance, enabling efficient and robust video understanding over extended temporal contexts. Extensive evaluations show that STORM achieves state-of-the-art results across various long video understanding benchmarks (more than 5\% improvement on MLVU and LongVideoBench) while reducing the computation costs by up to 8times and the decoding latency by 2.4-2.9times for the fixed numbers of input frames. Project page is available at https://research.nvidia.com/labs/lpr/storm

Event cameras capture motion dynamics, offering a unique modality with great potential in various computer vision tasks. However, RGB-Event fusion faces three intrinsic misalignments: (i) temporal, (ii) spatial, and (iii) modal misalignment. Existing voxel grid representations neglect temporal correlations between consecutive event windows, and their formulation with simple accumulation of asynchronous and sparse events is incompatible with the synchronous and dense nature of RGB modality. To tackle these challenges, we propose a novel event representation, Motion-enhanced Event Tensor (MET), which transforms sparse event voxels into a dense and temporally coherent form by leveraging dense optical flows and event temporal features. In addition, we introduce a Frequency-aware Bidirectional Flow Aggregation Module (BFAM) and a Temporal Fusion Module (TFM). BFAM leverages the frequency domain and MET to mitigate modal misalignment, while bidirectional flow aggregation and temporal fusion mechanisms resolve spatiotemporal misalignment. Experimental results on two large-scale datasets demonstrate that our framework significantly outperforms state-of-the-art RGB-Event semantic segmentation approaches. Our code is available at: https://github.com/zyaocoder/BRENet.

Camera-based 3D semantic scene completion (SSC) is pivotal for predicting complicated 3D layouts with limited 2D image observations. The existing mainstream solutions generally leverage temporal information by roughly stacking history frames to supplement the current frame, such straightforward temporal modeling inevitably diminishes valid clues and increases learning difficulty. To address this problem, we present HTCL, a novel Hierarchical Temporal Context Learning paradigm for improving camera-based semantic scene completion. The primary innovation of this work involves decomposing temporal context learning into two hierarchical steps: (a) cross-frame affinity measurement and (b) affinity-based dynamic refinement. Firstly, to separate critical relevant context from redundant information, we introduce the pattern affinity with scale-aware isolation and multiple independent learners for fine-grained contextual correspondence modeling. Subsequently, to dynamically compensate for incomplete observations, we adaptively refine the feature sampling locations based on initially identified locations with high affinity and their neighboring relevant regions. Our method ranks 1^{st} on the SemanticKITTI benchmark and even surpasses LiDAR-based methods in terms of mIoU on the OpenOccupancy benchmark. Our code is available on https://github.com/Arlo0o/HTCL.

Temporal reasoning is a critical challenge in video-language understanding, as it requires models to align semantic concepts consistently across time. While existing large vision-language models (LVLMs) and large language models (LLMs) excel at static tasks, they struggle to capture dynamic interactions and temporal dependencies in video sequences. In this work, we propose Temporal Semantic Alignment via Dynamic Prompting (TSADP), a novel framework that enhances temporal reasoning capabilities through dynamic task-specific prompts and temporal contrastive learning. TSADP leverages a Dynamic Prompt Generator (DPG) to encode fine-grained temporal relationships and a Temporal Contrastive Loss (TCL) to align visual and textual embeddings across time. We evaluate our method on the VidSitu dataset, augmented with enriched temporal annotations, and demonstrate significant improvements over state-of-the-art models in tasks such as Intra-Video Entity Association, Temporal Relationship Understanding, and Chronology Prediction. Human evaluations further confirm TSADP's ability to generate coherent and semantically accurate descriptions. Our analysis highlights the robustness, efficiency, and practical utility of TSADP, making it a step forward in the field of video-language understanding.

Spatio-temporal localization is vital for precise interactions across diverse domains, from biological research to autonomous navigation and interactive interfaces. Current video-based approaches, while proficient in tracking, lack the sophisticated reasoning capabilities of large language models, limiting their contextual understanding and generalization. We introduce VideoMolmo, a large multimodal model tailored for fine-grained spatio-temporal pointing conditioned on textual descriptions. Building upon the Molmo architecture, VideoMolmo incorporates a temporal module utilizing an attention mechanism to condition each frame on preceding frames, ensuring temporal consistency. Additionally, our novel temporal mask fusion pipeline employs SAM2 for bidirectional point propagation, significantly enhancing coherence across video sequences. This two-step decomposition, i.e., first using the LLM to generate precise pointing coordinates, then relying on a sequential mask-fusion module to produce coherent segmentation, not only simplifies the task for the language model but also enhances interpretability. Due to the lack of suitable datasets, we curate a comprehensive dataset comprising 72k video-caption pairs annotated with 100k object points. To evaluate the generalization of VideoMolmo, we introduce VPoS-Bench, a challenging out-of-distribution benchmark spanning five real-world scenarios: Cell Tracking, Egocentric Vision, Autonomous Driving, Video-GUI Interaction, and Robotics. We also evaluate our model on Referring Video Object Segmentation (Refer-VOS) and Reasoning VOS tasks. In comparison to existing models, VideoMolmo substantially improves spatio-temporal pointing accuracy and reasoning capability. Our code and models are publicly available at https://github.com/mbzuai-oryx/VideoMolmo.

Incorporating spatial information, particularly those influenced by climate, weather, and demographic factors, is crucial for improving underwriting precision and enhancing risk management in insurance. However, spatial data are often unstructured, high-dimensional, and difficult to integrate into predictive models. Embedding methods are needed to convert spatial data into meaningful representations for modelling tasks. We propose a novel multi-view contrastive learning framework for generating spatial embeddings that combine information from multiple spatial data sources. To train the model, we construct a spatial dataset that merges satellite imagery and OpenStreetMap features across Europe. The framework aligns these spatial views with coordinate-based encodings, producing low-dimensional embeddings that capture both spatial structure and contextual similarity. Once trained, the model generates embeddings directly from latitude-longitude pairs, enabling any dataset with coordinates to be enriched with meaningful spatial features without requiring access to the original spatial inputs. In a case study on French real estate prices, we compare models trained on raw coordinates against those using our spatial embeddings as inputs. The embeddings consistently improve predictive accuracy across generalised linear, additive, and boosting models, while providing interpretable spatial effects and demonstrating transferability to unseen regions.

Spatially dense self-supervised learning is a rapidly growing problem domain with promising applications for unsupervised segmentation and pretraining for dense downstream tasks. Despite the abundance of temporal data in the form of videos, this information-rich source has been largely overlooked. Our paper aims to address this gap by proposing a novel approach that incorporates temporal consistency in dense self-supervised learning. While methods designed solely for images face difficulties in achieving even the same performance on videos, our method improves not only the representation quality for videos-but also images. Our approach, which we call time-tuning, starts from image-pretrained models and fine-tunes them with a novel self-supervised temporal-alignment clustering loss on unlabeled videos. This effectively facilitates the transfer of high-level information from videos to image representations. Time-tuning improves the state-of-the-art by 8-10% for unsupervised semantic segmentation on videos and matches it for images. We believe this method paves the way for further self-supervised scaling by leveraging the abundant availability of videos. The implementation can be found here : https://github.com/SMSD75/Timetuning

Building on the success of 3D Gaussian Splatting (3DGS) in static 3D scene representation, its extension to dynamic scenes, commonly referred to as 4DGS or dynamic 3DGS, has attracted increasing attention. However, designing more compact and efficient deformation schemes together with rate-distortion-optimized compression strategies for dynamic 3DGS representations remains an underexplored area. Prior methods either rely on space-time 4DGS with overspecified, short-lived Gaussian primitives or on canonical 3DGS with deformation that lacks explicit temporal control. To address this, we present TED-4DGS, a temporally activated and embedding-based deformation scheme for rate-distortion-optimized 4DGS compression that unifies the strengths of both families. TED-4DGS is built on a sparse anchor-based 3DGS representation. Each canonical anchor is assigned learnable temporal-activation parameters to specify its appearance and disappearance transitions over time, while a lightweight per-anchor temporal embedding queries a shared deformation bank to produce anchor-specific deformation. For rate-distortion compression, we incorporate an implicit neural representation (INR)-based hyperprior to model anchor attribute distributions, along with a channel-wise autoregressive model to capture intra-anchor correlations. With these novel elements, our scheme achieves state-of-the-art rate-distortion performance on several real-world datasets. To the best of our knowledge, this work represents one of the first attempts to pursue a rate-distortion-optimized compression framework for dynamic 3DGS representations.

We present SpaceTimePilot, a video diffusion model that disentangles space and time for controllable generative rendering. Given a monocular video, SpaceTimePilot can independently alter the camera viewpoint and the motion sequence within the generative process, re-rendering the scene for continuous and arbitrary exploration across space and time. To achieve this, we introduce an effective animation time-embedding mechanism in the diffusion process, allowing explicit control of the output video's motion sequence with respect to that of the source video. As no datasets provide paired videos of the same dynamic scene with continuous temporal variations, we propose a simple yet effective temporal-warping training scheme that repurposes existing multi-view datasets to mimic temporal differences. This strategy effectively supervises the model to learn temporal control and achieve robust space-time disentanglement. To further enhance the precision of dual control, we introduce two additional components: an improved camera-conditioning mechanism that allows altering the camera from the first frame, and CamxTime, the first synthetic space-and-time full-coverage rendering dataset that provides fully free space-time video trajectories within a scene. Joint training on the temporal-warping scheme and the CamxTime dataset yields more precise temporal control. We evaluate SpaceTimePilot on both real-world and synthetic data, demonstrating clear space-time disentanglement and strong results compared to prior work. Project page: https://zheninghuang.github.io/Space-Time-Pilot/ Code: https://github.com/ZheningHuang/spacetimepilot

This paper studies referring video object segmentation (RVOS) by boosting video-level visual-linguistic alignment. Recent approaches model the RVOS task as a sequence prediction problem and perform multi-modal interaction as well as segmentation for each frame separately. However, the lack of a global view of video content leads to difficulties in effectively utilizing inter-frame relationships and understanding textual descriptions of object temporal variations. To address this issue, we propose Semantic-assisted Object Cluster (SOC), which aggregates video content and textual guidance for unified temporal modeling and cross-modal alignment. By associating a group of frame-level object embeddings with language tokens, SOC facilitates joint space learning across modalities and time steps. Moreover, we present multi-modal contrastive supervision to help construct well-aligned joint space at the video level. We conduct extensive experiments on popular RVOS benchmarks, and our method outperforms state-of-the-art competitors on all benchmarks by a remarkable margin. Besides, the emphasis on temporal coherence enhances the segmentation stability and adaptability of our method in processing text expressions with temporal variations. Code will be available.

We propose the first framework capable of computing a 4D spatio-temporal grid of video frames and 3D Gaussian particles for each time step using a feed-forward architecture. Our architecture has two main components, a 4D video model and a 4D reconstruction model. In the first part, we analyze current 4D video diffusion architectures that perform spatial and temporal attention either sequentially or in parallel within a two-stream design. We highlight the limitations of existing approaches and introduce a novel fused architecture that performs spatial and temporal attention within a single layer. The key to our method is a sparse attention pattern, where tokens attend to others in the same frame, at the same timestamp, or from the same viewpoint. In the second part, we extend existing 3D reconstruction algorithms by introducing a Gaussian head, a camera token replacement algorithm, and additional dynamic layers and training. Overall, we establish a new state of the art for 4D generation, improving both visual quality and reconstruction capability.

In this work, we identify an inherent bias in prevailing LVLM architectures toward the language modality, largely resulting from the common practice of simply appending visual embeddings to the input text sequence. To address this, we propose a simple yet effective method that refines textual embeddings by integrating average-pooled visual features. Our approach demonstrably improves visual grounding and significantly reduces hallucinations on established benchmarks. While average pooling offers a straightforward, robust, and efficient means of incorporating visual information, we believe that more sophisticated fusion methods could further enhance visual grounding and cross-modal alignment. Given that the primary focus of this work is to highlight the modality imbalance and its impact on hallucinations -- and to show that refining textual embeddings with visual information mitigates this issue -- we leave exploration of advanced fusion strategies for future work.

This work aims to learn a high-quality text-to-video (T2V) generative model by leveraging a pre-trained text-to-image (T2I) model as a basis. It is a highly desirable yet challenging task to simultaneously a) accomplish the synthesis of visually realistic and temporally coherent videos while b) preserving the strong creative generation nature of the pre-trained T2I model. To this end, we propose LaVie, an integrated video generation framework that operates on cascaded video latent diffusion models, comprising a base T2V model, a temporal interpolation model, and a video super-resolution model. Our key insights are two-fold: 1) We reveal that the incorporation of simple temporal self-attentions, coupled with rotary positional encoding, adequately captures the temporal correlations inherent in video data. 2) Additionally, we validate that the process of joint image-video fine-tuning plays a pivotal role in producing high-quality and creative outcomes. To enhance the performance of LaVie, we contribute a comprehensive and diverse video dataset named Vimeo25M, consisting of 25 million text-video pairs that prioritize quality, diversity, and aesthetic appeal. Extensive experiments demonstrate that LaVie achieves state-of-the-art performance both quantitatively and qualitatively. Furthermore, we showcase the versatility of pre-trained LaVie models in various long video generation and personalized video synthesis applications.

We present the task of Spatio-Temporal Video Question Answering, which requires intelligent systems to simultaneously retrieve relevant moments and detect referenced visual concepts (people and objects) to answer natural language questions about videos. We first augment the TVQA dataset with 310.8K bounding boxes, linking depicted objects to visual concepts in questions and answers. We name this augmented version as TVQA+. We then propose Spatio-Temporal Answerer with Grounded Evidence (STAGE), a unified framework that grounds evidence in both spatial and temporal domains to answer questions about videos. Comprehensive experiments and analyses demonstrate the effectiveness of our framework and how the rich annotations in our TVQA+ dataset can contribute to the question answering task. Moreover, by performing this joint task, our model is able to produce insightful and interpretable spatio-temporal attention visualizations. Dataset and code are publicly available at: http: //tvqa.cs.unc.edu, https://github.com/jayleicn/TVQAplus

Temporal Action Detection (TAD) focuses on detecting pre-defined actions, while Moment Retrieval (MR) aims to identify the events described by open-ended natural language within untrimmed videos. Despite that they focus on different events, we observe they have a significant connection. For instance, most descriptions in MR involve multiple actions from TAD. In this paper, we aim to investigate the potential synergy between TAD and MR. Firstly, we propose a unified architecture, termed Unified Moment Detection (UniMD), for both TAD and MR. It transforms the inputs of the two tasks, namely actions for TAD or events for MR, into a common embedding space, and utilizes two novel query-dependent decoders to generate a uniform output of classification score and temporal segments. Secondly, we explore the efficacy of two task fusion learning approaches, pre-training and co-training, in order to enhance the mutual benefits between TAD and MR. Extensive experiments demonstrate that the proposed task fusion learning scheme enables the two tasks to help each other and outperform the separately trained counterparts. Impressively, UniMD achieves state-of-the-art results on three paired datasets Ego4D, Charades-STA, and ActivityNet. Our code is available at https://github.com/yingsen1/UniMD.

Popular representation learning methods encourage feature invariance under transformations applied at the input. However, in 3D perception tasks like object localization and segmentation, outputs are naturally equivariant to some transformations, such as rotation. Using pre-training loss functions that encourage equivariance of features under certain transformations provides a strong self-supervision signal while also retaining information of geometric relationships between transformed feature representations. This can enable improved performance in downstream tasks that are equivariant to such transformations. In this paper, we propose a spatio-temporal equivariant learning framework by considering both spatial and temporal augmentations jointly. Our experiments show that the best performance arises with a pre-training approach that encourages equivariance to translation, scaling, and flip, rotation and scene flow. For spatial augmentations, we find that depending on the transformation, either a contrastive objective or an equivariance-by-classification objective yields best results. To leverage real-world object deformations and motion, we consider sequential LiDAR scene pairs and develop a novel 3D scene flow-based equivariance objective that leads to improved performance overall. We show our pre-training method for 3D object detection which outperforms existing equivariant and invariant approaches in many settings.

With the release of large-scale motion datasets with textual annotations, the task of establishing a robust latent space for language and 3D human motion has recently witnessed a surge of interest. Methods have been proposed to convert human motion and texts into features to achieve accurate correspondence between them. Despite these efforts to align language and motion representations, we claim that the temporal element is often overlooked, especially for compound actions, resulting in chronological inaccuracies. To shed light on the temporal alignment in motion-language latent spaces, we propose Chronologically Accurate Retrieval (CAR) to evaluate the chronological understanding of the models. We decompose textual descriptions into events, and prepare negative text samples by shuffling the order of events in compound action descriptions. We then design a simple task for motion-language models to retrieve the more likely text from the ground truth and its chronologically shuffled version. CAR reveals many cases where current motion-language models fail to distinguish the event chronology of human motion, despite their impressive performance in terms of conventional evaluation metrics. To achieve better temporal alignment between text and motion, we further propose to use these texts with shuffled sequence of events as negative samples during training to reinforce the motion-language models. We conduct experiments on text-motion retrieval and text-to-motion generation using the reinforced motion-language models, which demonstrate improved performance over conventional approaches, indicating the necessity to consider temporal elements in motion-language alignment.

Leveraging temporal information has been regarded as essential for developing video understanding models. However, how to properly incorporate temporal information into the recent successful instance discrimination based contrastive self-supervised learning (CSL) framework remains unclear. As an intuitive solution, we find that directly applying temporal augmentations does not help, or even impair video CSL in general. This counter-intuitive observation motivates us to re-design existing video CSL frameworks, for better integration of temporal knowledge. To this end, we present Temporal-aware Contrastive self-supervised learningTaCo, as a general paradigm to enhance video CSL. Specifically, TaCo selects a set of temporal transformations not only as strong data augmentation but also to constitute extra self-supervision for video understanding. By jointly contrasting instances with enriched temporal transformations and learning these transformations as self-supervised signals, TaCo can significantly enhance unsupervised video representation learning. For instance, TaCo demonstrates consistent improvement in downstream classification tasks over a list of backbones and CSL approaches. Our best model achieves 85.1% (UCF-101) and 51.6% (HMDB-51) top-1 accuracy, which is a 3% and 2.4% relative improvement over the previous state-of-the-art.

Despite advances in general video understanding, Video Large Language Models (Video-LLMs) face challenges in precise temporal localization due to discrete time representations and limited temporally aware datasets. Existing methods for temporal expression either conflate time with text-based numerical values, add a series of dedicated temporal tokens, or regress time using specialized temporal grounding heads. To address these issues, we introduce DisTime, a lightweight framework designed to enhance temporal comprehension in Video-LLMs. DisTime employs a learnable token to create a continuous temporal embedding space and incorporates a Distribution-based Time Decoder that generates temporal probability distributions, effectively mitigating boundary ambiguities and maintaining temporal continuity. Additionally, the Distribution-based Time Encoder re-encodes timestamps to provide time markers for Video-LLMs. To overcome temporal granularity limitations in existing datasets, we propose an automated annotation paradigm that combines the captioning capabilities of Video-LLMs with the localization expertise of dedicated temporal models. This leads to the creation of InternVid-TG, a substantial dataset with 1.25M temporally grounded events across 179k videos, surpassing ActivityNet-Caption by 55 times. Extensive experiments demonstrate that DisTime achieves state-of-the-art performance across benchmarks in three time-sensitive tasks while maintaining competitive performance in Video QA tasks. Code and data are released at https://github.com/josephzpng/DisTime.

Deep saliency prediction algorithms complement the object recognition features, they typically rely on additional information, such as scene context, semantic relationships, gaze direction, and object dissimilarity. However, none of these models consider the temporal nature of gaze shifts during image observation. We introduce a novel saliency prediction model that learns to output saliency maps in sequential time intervals by exploiting human temporal attention patterns. Our approach locally modulates the saliency predictions by combining the learned temporal maps. Our experiments show that our method outperforms the state-of-the-art models, including a multi-duration saliency model, on the SALICON benchmark. Our code will be publicly available on GitHub.

In this paper, we propose PETRv2, a unified framework for 3D perception from multi-view images. Based on PETR, PETRv2 explores the effectiveness of temporal modeling, which utilizes the temporal information of previous frames to boost 3D object detection. More specifically, we extend the 3D position embedding (3D PE) in PETR for temporal modeling. The 3D PE achieves the temporal alignment on object position of different frames. A feature-guided position encoder is further introduced to improve the data adaptability of 3D PE. To support for multi-task learning (e.g., BEV segmentation and 3D lane detection), PETRv2 provides a simple yet effective solution by introducing task-specific queries, which are initialized under different spaces. PETRv2 achieves state-of-the-art performance on 3D object detection, BEV segmentation and 3D lane detection. Detailed robustness analysis is also conducted on PETR framework. We hope PETRv2 can serve as a strong baseline for 3D perception. Code is available at https://github.com/megvii-research/PETR.

In this work, we build a simple but strong baseline for sounding video generation. Given base diffusion models for audio and video, we integrate them with additional modules into a single model and train it to make the model jointly generate audio and video. To enhance alignment between audio-video pairs, we introduce two novel mechanisms in our model. The first one is timestep adjustment, which provides different timestep information to each base model. It is designed to align how samples are generated along with timesteps across modalities. The second one is a new design of the additional modules, termed Cross-Modal Conditioning as Positional Encoding (CMC-PE). In CMC-PE, cross-modal information is embedded as if it represents temporal position information, and the embeddings are fed into the model like positional encoding. Compared with the popular cross-attention mechanism, CMC-PE provides a better inductive bias for temporal alignment in the generated data. Experimental results validate the effectiveness of the two newly introduced mechanisms and also demonstrate that our method outperforms existing methods.

Recent DiT-based text-to-image models increasingly adopt LLMs as text encoders, yet text conditioning remains largely static and often utilizes only a single LLM layer, despite pronounced semantic hierarchy across LLM layers and non-stationary denoising dynamics over both diffusion time and network depth. To better match the dynamic process of DiT generation and thereby enhance the diffusion model's generative capability, we introduce a unified normalized convex fusion framework equipped with lightweight gates to systematically organize multi-layer LLM hidden states via time-wise, depth-wise, and joint fusion. Experiments establish Depth-wise Semantic Routing as the superior conditioning strategy, consistently improving text-image alignment and compositional generation (e.g., +9.97 on the GenAI-Bench Counting task). Conversely, we find that purely time-wise fusion can paradoxically degrade visual generation fidelity. We attribute this to a train-inference trajectory mismatch: under classifier-free guidance, nominal timesteps fail to track the effective SNR, causing semantically mistimed feature injection during inference. Overall, our results position depth-wise routing as a strong and effective baseline and highlight the critical need for trajectory-aware signals to enable robust time-dependent conditioning.

Long-context video understanding in multimodal large language models (MLLMs) faces a critical challenge: balancing computational efficiency with the retention of fine-grained spatio-temporal patterns. Existing approaches (e.g., sparse sampling, dense sampling with low resolution, and token compression) suffer from significant information loss in temporal dynamics, spatial details, or subtle interactions, particularly in videos with complex motion or varying resolutions. To address this, we propose Mavors, a novel framework that introduces Multi-granularity video representation for holistic long-video modeling. Specifically, Mavors directly encodes raw video content into latent representations through two core components: 1) an Intra-chunk Vision Encoder (IVE) that preserves high-resolution spatial features via 3D convolutions and Vision Transformers, and 2) an Inter-chunk Feature Aggregator (IFA) that establishes temporal coherence across chunks using transformer-based dependency modeling with chunk-level rotary position encodings. Moreover, the framework unifies image and video understanding by treating images as single-frame videos via sub-image decomposition. Experiments across diverse benchmarks demonstrate Mavors' superiority in maintaining both spatial fidelity and temporal continuity, significantly outperforming existing methods in tasks requiring fine-grained spatio-temporal reasoning.

Current video-based Masked Autoencoders (MAEs) primarily focus on learning effective spatiotemporal representations from a visual perspective, which may lead the model to prioritize general spatial-temporal patterns but often overlook nuanced semantic attributes like specific interactions or sequences that define actions - such as action-specific features that align more closely with human cognition for space-time correspondence. This can limit the model's ability to capture the essence of certain actions that are contextually rich and continuous. Humans are capable of mapping visual concepts, object view invariance, and semantic attributes available in static instances to comprehend natural dynamic scenes or videos. Existing MAEs for videos and static images rely on separate datasets for videos and images, which may lack the rich semantic attributes necessary for fully understanding the learned concepts, especially when compared to using video and corresponding sampled frame images together. To this end, we propose CrossVideoMAE an end-to-end self-supervised cross-modal contrastive learning MAE that effectively learns both video-level and frame-level rich spatiotemporal representations and semantic attributes. Our method integrates mutual spatiotemporal information from videos with spatial information from sampled frames within a feature-invariant space, while encouraging invariance to augmentations within the video domain. This objective is achieved through jointly embedding features of visible tokens and combining feature correspondence within and across modalities, which is critical for acquiring rich, label-free guiding signals from both video and frame image modalities in a self-supervised manner. Extensive experiments demonstrate that our approach surpasses previous state-of-the-art methods and ablation studies validate the effectiveness of our approach.

High-quality video inpainting that completes missing regions in video frames is a promising yet challenging task. State-of-the-art approaches adopt attention models to complete a frame by searching missing contents from reference frames, and further complete whole videos frame by frame. However, these approaches can suffer from inconsistent attention results along spatial and temporal dimensions, which often leads to blurriness and temporal artifacts in videos. In this paper, we propose to learn a joint Spatial-Temporal Transformer Network (STTN) for video inpainting. Specifically, we simultaneously fill missing regions in all input frames by self-attention, and propose to optimize STTN by a spatial-temporal adversarial loss. To show the superiority of the proposed model, we conduct both quantitative and qualitative evaluations by using standard stationary masks and more realistic moving object masks. Demo videos are available at https://github.com/researchmm/STTN.

Satellite image time-series analysis demands fine-grained spatial-temporal reasoning, which remains a challenge for existing multimodal large language models (MLLMs). In this work, we study the capabilities of MLLMs on a novel task that jointly targets temporal change understanding and future scene generation, aiming to assess their potential for modeling complex multimodal dynamics over time. We propose TAMMs, a Temporal-Aware Multimodal Model for satellite image change understanding and forecasting, which enhances frozen MLLMs with lightweight temporal modules for structured sequence encoding and contextual prompting. To guide future image generation, TAMMs introduces a Semantic-Fused Control Injection (SFCI) mechanism that adaptively combines high-level semantic reasoning and structural priors within an enhanced ControlNet. This dual-path conditioning enables temporally consistent and semantically grounded image synthesis. Experiments demonstrate that TAMMs outperforms strong MLLM baselines in both temporal change understanding and future image forecasting tasks, highlighting how carefully designed temporal reasoning and semantic fusion can unlock the full potential of MLLMs for spatio-temporal understanding.

Understanding the structure of complex activities in untrimmed videos is a challenging task in the area of action recognition. One problem here is that this task usually requires a large amount of hand-annotated minute- or even hour-long video data, but annotating such data is very time consuming and can not easily be automated or scaled. To address this problem, this paper proposes an approach for the unsupervised learning of actions in untrimmed video sequences based on a joint visual-temporal embedding space. To this end, we combine a visual embedding based on a predictive U-Net architecture with a temporal continuous function. The resulting representation space allows detecting relevant action clusters based on their visual as well as their temporal appearance. The proposed method is evaluated on three standard benchmark datasets, Breakfast Actions, INRIA YouTube Instructional Videos, and 50 Salads. We show that the proposed approach is able to provide a meaningful visual and temporal embedding out of the visual cues present in contiguous video frames and is suitable for the task of unsupervised temporal segmentation of actions.

Efficient understanding of long-form videos remains a significant challenge in computer vision. In this work, we revisit temporal search paradigms for long-form video understanding, studying a fundamental issue pertaining to all state-of-the-art (SOTA) long-context vision-language models (VLMs). In particular, our contributions are two-fold: First, we formulate temporal search as a Long Video Haystack problem, i.e., finding a minimal set of relevant frames (typically one to five) among tens of thousands of frames from real-world long videos given specific queries. To validate our formulation, we create LV-Haystack, the first benchmark containing 3,874 human-annotated instances with fine-grained evaluation metrics for assessing keyframe search quality and computational efficiency. Experimental results on LV-Haystack highlight a significant research gap in temporal search capabilities, with SOTA keyframe selection methods achieving only 2.1% temporal F1 score on the LVBench subset. Next, inspired by visual search in images, we re-think temporal searching and propose a lightweight keyframe searching framework, T*, which casts the expensive temporal search as a spatial search problem. T* leverages superior visual localization capabilities typically used in images and introduces an adaptive zooming-in mechanism that operates across both temporal and spatial dimensions. Our extensive experiments show that when integrated with existing methods, T* significantly improves SOTA long-form video understanding performance. Specifically, under an inference budget of 32 frames, T* improves GPT-4o's performance from 50.5% to 53.1% and LLaVA-OneVision-72B's performance from 56.5% to 62.4% on LongVideoBench XL subset. Our PyTorch code, benchmark dataset and models are included in the Supplementary material.

The recent advancement in video temporal grounding (VTG) has significantly enhanced fine-grained video understanding, primarily driven by multimodal large language models (MLLMs). With superior multimodal comprehension and reasoning abilities, VTG approaches based on MLLMs (VTG-MLLMs) are gradually surpassing traditional fine-tuned methods. They not only achieve competitive performance but also excel in generalization across zero-shot, multi-task, and multi-domain settings. Despite extensive surveys on general video-language understanding, comprehensive reviews specifically addressing VTG-MLLMs remain scarce. To fill this gap, this survey systematically examines current research on VTG-MLLMs through a three-dimensional taxonomy: 1) the functional roles of MLLMs, highlighting their architectural significance; 2) training paradigms, analyzing strategies for temporal reasoning and task adaptation; and 3) video feature processing techniques, which determine spatiotemporal representation effectiveness. We further discuss benchmark datasets, evaluation protocols, and summarize empirical findings. Finally, we identify existing limitations and propose promising research directions. For additional resources and details, readers are encouraged to visit our repository at https://github.com/ki-lw/Awesome-MLLMs-for-Video-Temporal-Grounding.

Composed Video Retrieval (CoVR) retrieves a target video given a query video and a modification text describing the intended change. Existing CoVR benchmarks emphasize appearance shifts or coarse event changes and therefore do not test the ability to capture subtle, fast-paced temporal differences. We introduce TF-CoVR, the first large-scale benchmark dedicated to temporally fine-grained CoVR. TF-CoVR focuses on gymnastics and diving and provides 180K triplets drawn from FineGym and FineDiving. Previous CoVR benchmarks focusing on temporal aspect, link each query to a single target segment taken from the same video, limiting practical usefulness. In TF-CoVR, we instead construct each <query, modification> pair by prompting an LLM with the label differences between clips drawn from different videos; every pair is thus associated with multiple valid target videos (3.9 on average), reflecting real-world tasks such as sports-highlight generation. To model these temporal dynamics we propose TF-CoVR-Base, a concise two-stage training framework: (i) pre-train a video encoder on fine-grained action classification to obtain temporally discriminative embeddings; (ii) align the composed query with candidate videos using contrastive learning. We conduct the first comprehensive study of image, video, and general multimodal embedding (GME) models on temporally fine-grained composed retrieval in both zero-shot and fine-tuning regimes. On TF-CoVR, TF-CoVR-Base improves zero-shot mAP@50 from 5.92 (LanguageBind) to 7.51, and after fine-tuning raises the state-of-the-art from 19.83 to 25.82.

Accurate recognition of sign language in healthcare communication poses a significant challenge, requiring frameworks that can accurately interpret complex multimodal gestures. To deal with this, we propose FusionEnsemble-Net, a novel attention-based ensemble of spatiotemporal networks that dynamically fuses visual and motion data to enhance recognition accuracy. The proposed approach processes RGB video and range Doppler map radar modalities synchronously through four different spatiotemporal networks. For each network, features from both modalities are continuously fused using an attention-based fusion module before being fed into an ensemble of classifiers. Finally, the outputs of these four different fused channels are combined in an ensemble classification head, thereby enhancing the model's robustness. Experiments demonstrate that FusionEnsemble-Net outperforms state-of-the-art approaches with a test accuracy of 99.44% on the large-scale MultiMeDaLIS dataset for Italian Sign Language. Our findings indicate that an ensemble of diverse spatiotemporal networks, unified by attention-based fusion, yields a robust and accurate framework for complex, multimodal isolated gesture recognition tasks. The source code is available at: https://github.com/rezwanh001/Multimodal-Isolated-Italian-Sign-Language-Recognition.

Our work explores temporal self-supervision for GAN-based video generation tasks. While adversarial training successfully yields generative models for a variety of areas, temporal relationships in the generated data are much less explored. Natural temporal changes are crucial for sequential generation tasks, e.g. video super-resolution and unpaired video translation. For the former, state-of-the-art methods often favor simpler norm losses such as L^2 over adversarial training. However, their averaging nature easily leads to temporally smooth results with an undesirable lack of spatial detail. For unpaired video translation, existing approaches modify the generator networks to form spatio-temporal cycle consistencies. In contrast, we focus on improving learning objectives and propose a temporally self-supervised algorithm. For both tasks, we show that temporal adversarial learning is key to achieving temporally coherent solutions without sacrificing spatial detail. We also propose a novel Ping-Pong loss to improve the long-term temporal consistency. It effectively prevents recurrent networks from accumulating artifacts temporally without depressing detailed features. Additionally, we propose a first set of metrics to quantitatively evaluate the accuracy as well as the perceptual quality of the temporal evolution. A series of user studies confirm the rankings computed with these metrics. Code, data, models, and results are provided at https://github.com/thunil/TecoGAN. The project page https://ge.in.tum.de/publications/2019-tecogan-chu/ contains supplemental materials.

Information retrieval is indispensable for today's Internet applications, yet traditional semantic matching techniques often fall short in capturing the fine-grained cross-modal interactions required for complex queries. Although late-fusion two-tower architectures attempt to bridge this gap by independently encoding visual and textual data before merging them at a high level, they frequently overlook the subtle interplay essential for comprehensive understanding. In this work, we rigorously assess these limitations and introduce a unified retrieval framework that fuses visual and textual cues from the ground up, enabling early cross-modal interactions for enhancing context interpretation. Through a two-stage training process--comprising post-training adaptation followed by instruction tuning--we adapt MLLMs as retrievers using a simple one-tower architecture. Our approach outperforms conventional methods across diverse retrieval scenarios, particularly when processing complex multi-modal inputs. Notably, the joint fusion encoder yields greater improvements on tasks that require modality fusion compared to those that do not, underscoring the transformative potential of early integration strategies and pointing toward a promising direction for contextually aware and effective information retrieval.

Recent works have successfully extended large-scale text-to-image models to the video domain, producing promising results but at a high computational cost and requiring a large amount of video data. In this work, we introduce ConditionVideo, a training-free approach to text-to-video generation based on the provided condition, video, and input text, by leveraging the power of off-the-shelf text-to-image generation methods (e.g., Stable Diffusion). ConditionVideo generates realistic dynamic videos from random noise or given scene videos. Our method explicitly disentangles the motion representation into condition-guided and scenery motion components. To this end, the ConditionVideo model is designed with a UNet branch and a control branch. To improve temporal coherence, we introduce sparse bi-directional spatial-temporal attention (sBiST-Attn). The 3D control network extends the conventional 2D controlnet model, aiming to strengthen conditional generation accuracy by additionally leveraging the bi-directional frames in the temporal domain. Our method exhibits superior performance in terms of frame consistency, clip score, and conditional accuracy, outperforming other compared methods.

Models based on deep convolutional networks have dominated recent image interpretation tasks; we investigate whether models which are also recurrent, or "temporally deep", are effective for tasks involving sequences, visual and otherwise. We develop a novel recurrent convolutional architecture suitable for large-scale visual learning which is end-to-end trainable, and demonstrate the value of these models on benchmark video recognition tasks, image description and retrieval problems, and video narration challenges. In contrast to current models which assume a fixed spatio-temporal receptive field or simple temporal averaging for sequential processing, recurrent convolutional models are "doubly deep"' in that they can be compositional in spatial and temporal "layers". Such models may have advantages when target concepts are complex and/or training data are limited. Learning long-term dependencies is possible when nonlinearities are incorporated into the network state updates. Long-term RNN models are appealing in that they directly can map variable-length inputs (e.g., video frames) to variable length outputs (e.g., natural language text) and can model complex temporal dynamics; yet they can be optimized with backpropagation. Our recurrent long-term models are directly connected to modern visual convnet models and can be jointly trained to simultaneously learn temporal dynamics and convolutional perceptual representations. Our results show such models have distinct advantages over state-of-the-art models for recognition or generation which are separately defined and/or optimized.

Vision-Language Models (VLMs) are a new family of models that align image content with natural language. Existing approaches typically fuse either (a) early: by mixing tokens/features inside the encoders, or (b) late: by comparing pooled embeddings. Many methods also tie fusion to an autoregressive decoder. However, the hidden states of both modalities already carry rich, modality-specific structure (spatial layout in vision; syntax and semantics in text), so directly aligning these states is a natural way to match what the two modalities "think". We propose a lightweight fusion module: a few cross-only, bidirectional attention layers placed near the top of both encoders. Each layer projects the vision and text encoder hidden-state sequences into a shared space, attends across modalities, and sends gated residual updates back, with simple stabilizers to improve alignment. The encoders remain non-causal and strong for understanding, while generation stays cleanly decoupled via an optional decoder. Across standard retrieval, VQA, and visual reasoning benchmarks, BRIDGE outperforms comparable VLMs while preserving the bi-encoder efficiency of contrastive models. We make our code publicly available at https://github.com/jfeinashley/BRIDGE.

The rapid advancement of Large Multimodal Models (LMMs) for 2D images and videos has motivated extending these models to understand 3D scenes, aiming for human-like visual-spatial intelligence. Nevertheless, achieving deep spatial understanding comparable to human capabilities poses significant challenges in model encoding and data acquisition. Existing methods frequently depend on external depth sensors for geometry capture or utilize off-the-shelf algorithms for pre-constructing 3D maps, thereby limiting their scalability, especially with prevalent monocular video inputs and for time-sensitive applications. In this work, we introduce VLM-3R, a unified framework for Vision-Language Models (VLMs) that incorporates 3D Reconstructive instruction tuning. VLM-3R processes monocular video frames by employing a geometry encoder to derive implicit 3D tokens that represent spatial understanding. Leveraging our Spatial-Visual-View Fusion and over 200K curated 3D reconstructive instruction tuning question-answer (QA) pairs, VLM-3R effectively aligns real-world spatial context with language instructions. This enables monocular 3D spatial assistance and embodied reasoning. To facilitate the evaluation of temporal reasoning, we introduce the Vision-Spatial-Temporal Intelligence benchmark, featuring over 138.6K QA pairs across five distinct tasks focused on evolving spatial relationships. Extensive experiments demonstrate that our model, VLM-3R, not only facilitates robust visual-spatial reasoning but also enables the understanding of temporal 3D context changes, excelling in both accuracy and scalability.

Despite progress in video-language modeling, the computational challenge of interpreting long-form videos in response to task-specific linguistic queries persists, largely due to the complexity of high-dimensional video data and the misalignment between language and visual cues over space and time. To tackle this issue, we introduce a novel approach called Language-guided Spatial-Temporal Prompt Learning (LSTP). This approach features two key components: a Temporal Prompt Sampler (TPS) with optical flow prior that leverages temporal information to efficiently extract relevant video content, and a Spatial Prompt Solver (SPS) that adeptly captures the intricate spatial relationships between visual and textual elements. By harmonizing TPS and SPS with a cohesive training strategy, our framework significantly enhances computational efficiency, temporal understanding, and spatial-temporal alignment. Empirical evaluations across two challenging tasks--video question answering and temporal question grounding in videos--using a variety of video-language pretrainings (VLPs) and large language models (LLMs) demonstrate the superior performance, speed, and versatility of our proposed LSTP paradigm.

By leveraging temporal dependency in video sequences, multi-frame human pose estimation algorithms have demonstrated remarkable results in complicated situations, such as occlusion, motion blur, and video defocus. These algorithms are predominantly based on heatmaps, resulting in high computation and storage requirements per frame, which limits their flexibility and real-time application in video scenarios, particularly on edge devices. In this paper, we develop an efficient and effective video-based human pose regression method, which bypasses intermediate representations such as heatmaps and instead directly maps the input to the output joint coordinates. Despite the inherent spatial correlation among adjacent joints of the human pose, the temporal trajectory of each individual joint exhibits relative independence. In light of this, we propose a novel Decoupled Space-Time Aggregation network (DSTA) to separately capture the spatial contexts between adjacent joints and the temporal cues of each individual joint, thereby avoiding the conflation of spatiotemporal dimensions. Concretely, DSTA learns a dedicated feature token for each joint to facilitate the modeling of their spatiotemporal dependencies. With the proposed joint-wise local-awareness attention mechanism, our method is capable of efficiently and flexibly utilizing the spatial dependency of adjacent joints and the temporal dependency of each joint itself. Extensive experiments demonstrate the superiority of our method. Compared to previous regression-based single-frame human pose estimation methods, DSTA significantly enhances performance, achieving an 8.9 mAP improvement on PoseTrack2017. Furthermore, our approach either surpasses or is on par with the state-of-the-art heatmap-based multi-frame human pose estimation methods. Project page: https://github.com/zgspose/DSTA.

Recent DETR-based video grounding models have made the model directly predict moment timestamps without any hand-crafted components, such as a pre-defined proposal or non-maximum suppression, by learning moment queries. However, their input-agnostic moment queries inevitably overlook an intrinsic temporal structure of a video, providing limited positional information. In this paper, we formulate an event-aware dynamic moment query to enable the model to take the input-specific content and positional information of the video into account. To this end, we present two levels of reasoning: 1) Event reasoning that captures distinctive event units constituting a given video using a slot attention mechanism; and 2) moment reasoning that fuses the moment queries with a given sentence through a gated fusion transformer layer and learns interactions between the moment queries and video-sentence representations to predict moment timestamps. Extensive experiments demonstrate the effectiveness and efficiency of the event-aware dynamic moment queries, outperforming state-of-the-art approaches on several video grounding benchmarks.

Video amodal segmentation is a particularly challenging task in computer vision, which requires to deduce the full shape of an object from the visible parts of it. Recently, some studies have achieved promising performance by using motion flow to integrate information across frames under a self-supervised setting. However, motion flow has a clear limitation by the two factors of moving cameras and object deformation. This paper presents a rethinking to previous works. We particularly leverage the supervised signals with object-centric representation in real-world scenarios. The underlying idea is the supervision signal of the specific object and the features from different views can mutually benefit the deduction of the full mask in any specific frame. We thus propose an Efficient object-centric Representation amodal Segmentation (EoRaS). Specially, beyond solely relying on supervision signals, we design a translation module to project image features into the Bird's-Eye View (BEV), which introduces 3D information to improve current feature quality. Furthermore, we propose a multi-view fusion layer based temporal module which is equipped with a set of object slots and interacts with features from different views by attention mechanism to fulfill sufficient object representation completion. As a result, the full mask of the object can be decoded from image features updated by object slots. Extensive experiments on both real-world and synthetic benchmarks demonstrate the superiority of our proposed method, achieving state-of-the-art performance. Our code will be released at https://github.com/kfan21/EoRaS.

Recognizing interactive action plays an important role in human-robot interaction and collaboration. Previous methods use late fusion and co-attention mechanism to capture interactive relations, which have limited learning capability or inefficiency to adapt to more interacting entities. With assumption that priors of each entity are already known, they also lack evaluations on a more general setting addressing the diversity of subjects. To address these problems, we propose an Interactive Spatiotemporal Token Attention Network (ISTA-Net), which simultaneously model spatial, temporal, and interactive relations. Specifically, our network contains a tokenizer to partition Interactive Spatiotemporal Tokens (ISTs), which is a unified way to represent motions of multiple diverse entities. By extending the entity dimension, ISTs provide better interactive representations. To jointly learn along three dimensions in ISTs, multi-head self-attention blocks integrated with 3D convolutions are designed to capture inter-token correlations. When modeling correlations, a strict entity ordering is usually irrelevant for recognizing interactive actions. To this end, Entity Rearrangement is proposed to eliminate the orderliness in ISTs for interchangeable entities. Extensive experiments on four datasets verify the effectiveness of ISTA-Net by outperforming state-of-the-art methods. Our code is publicly available at https://github.com/Necolizer/ISTA-Net

Learning to reliably perceive and understand the scene is an integral enabler for robots to operate in the real-world. This problem is inherently challenging due to the multitude of object types as well as appearance changes caused by varying illumination and weather conditions. Leveraging complementary modalities can enable learning of semantically richer representations that are resilient to such perturbations. Despite the tremendous progress in recent years, most multimodal convolutional neural network approaches directly concatenate feature maps from individual modality streams rendering the model incapable of focusing only on relevant complementary information for fusion. To address this limitation, we propose a mutimodal semantic segmentation framework that dynamically adapts the fusion of modality-specific features while being sensitive to the object category, spatial location and scene context in a self-supervised manner. Specifically, we propose an architecture consisting of two modality-specific encoder streams that fuse intermediate encoder representations into a single decoder using our proposed self-supervised model adaptation fusion mechanism which optimally combines complementary features. As intermediate representations are not aligned across modalities, we introduce an attention scheme for better correlation. In addition, we propose a computationally efficient unimodal segmentation architecture termed AdapNet++ that incorporates a new encoder with multiscale residual units and an efficient atrous spatial pyramid pooling that has a larger effective receptive field with more than 10x fewer parameters, complemented with a strong decoder with a multi-resolution supervision scheme that recovers high-resolution details. Comprehensive empirical evaluations on several benchmarks demonstrate that both our unimodal and multimodal architectures achieve state-of-the-art performance.

Fine-grained spatio-temporal understanding is essential for video reasoning and embodied AI. Yet, while Multimodal Large Language Models (MLLMs) master static semantics, their grasp of temporal dynamics remains brittle. We present TimeBlind, a diagnostic benchmark for compositional spatio-temporal understanding. Inspired by cognitive science, TimeBlind categorizes fine-grained temporal understanding into three levels: recognizing atomic events, characterizing event properties, and reasoning about event interdependencies. Unlike benchmarks that conflate recognition with temporal reasoning, TimeBlind leverages a minimal-pairs paradigm: video pairs share identical static visual content but differ solely in temporal structure, utilizing complementary questions to neutralize language priors. Evaluating over 20 state-of-the-art MLLMs (e.g., GPT-5, Gemini 3 Pro) on 600 curated instances (2400 video-question pairs), reveals that the Instance Accuracy (correctly distinguishing both videos in a pair) of the best performing MLLM is only 48.2%, far below the human performance (98.2%). These results demonstrate that even frontier models rely heavily on static visual shortcuts rather than genuine temporal logic, positioning TimeBlind as a vital diagnostic tool for next-generation video understanding. Dataset and code are available at https://baiqi-li.github.io/timeblind_project/ .

Our objective is to build a general time-aware video-text embedding model for retrieval. To that end, we propose a simple and efficient recipe, dubbed TARA (Time Aware Retrieval Adaptation), to adapt Multimodal LLMs (MLLMs) to a time-aware video-text embedding model without using any video data at all. For evaluating time-awareness in retrieval, we propose a new benchmark with temporally opposite (chiral) actions as hard negatives and curated splits for chiral and non-chiral actions. We show that TARA outperforms all existing video-text models on this chiral benchmark while also achieving strong results on standard benchmarks. Furthermore, we discover additional benefits of TARA beyond time-awareness: (i) TARA embeddings are negation-aware as shown in NegBench benchmark that evaluates negation in video retrieval, (ii) TARA achieves state of the art performance on verb and adverb understanding in videos. Overall, TARA yields a strong, versatile, time-aware video-text embedding model with state of the art zero-shot performance.

Recently, with the emergence of large language models, multimodal LLMs have demonstrated exceptional capabilities in image and video modalities. Despite advancements in video comprehension, the substantial computational demands of long video sequences lead current video LLMs (Vid-LLMs) to employ compression strategies at both the inter-frame level (e.g., uniform sampling of video frames) and intra-frame level (e.g., condensing all visual tokens of each frame into a limited number). However, this approach often neglects the uneven temporal distribution of critical information across frames, risking the omission of keyframes that contain essential temporal and semantic details. To tackle these challenges, we propose KFFocus, a method designed to efficiently compress video tokens and emphasize the informative context present within video frames. We substitute uniform sampling with a refined approach inspired by classic video compression principles to identify and capture keyframes based on their temporal redundancy. By assigning varying condensation ratios to frames based on their contextual relevance, KFFocus efficiently reduces token redundancy while preserving informative content details. Additionally, we introduce a spatiotemporal modeling module that encodes both the temporal relationships between video frames and the spatial structure within each frame, thus providing Vid-LLMs with a nuanced understanding of spatial-temporal dynamics. Extensive experiments on widely recognized video understanding benchmarks, especially long video scenarios, demonstrate that KFFocus significantly outperforms existing methods, achieving substantial computational efficiency and enhanced accuracy.

Temporal action detection (TAD) involves the localization and classification of action instances within untrimmed videos. While standard TAD follows fully supervised learning with closed-set setting on large training data, recent zero-shot TAD methods showcase the promising open-set setting by leveraging large-scale contrastive visual-language (ViL) pretrained models. However, existing zero-shot TAD methods have limitations on how to properly construct the strong relationship between two interdependent tasks of localization and classification and adapt ViL model to video understanding. In this work, we present ZEETAD, featuring two modules: dual-localization and zero-shot proposal classification. The former is a Transformer-based module that detects action events while selectively collecting crucial semantic embeddings for later recognition. The latter one, CLIP-based module, generates semantic embeddings from text and frame inputs for each temporal unit. Additionally, we enhance discriminative capability on unseen classes by minimally updating the frozen CLIP encoder with lightweight adapters. Extensive experiments on THUMOS14 and ActivityNet-1.3 datasets demonstrate our approach's superior performance in zero-shot TAD and effective knowledge transfer from ViL models to unseen action categories.

We introduce the task of retrieving relevant video moments from a large corpus of untrimmed, unsegmented videos given a natural language query. Our task poses unique challenges as a system must efficiently identify both the relevant videos and localize the relevant moments in the videos. To address these challenges, we propose SpatioTemporal Alignment with Language (STAL), a model that represents a video moment as a set of regions within a series of short video clips and aligns a natural language query to the moment's regions. Our alignment cost compares variable-length language and video features using symmetric squared Chamfer distance, which allows for efficient indexing and retrieval of the video moments. Moreover, aligning language features to regions within a video moment allows for finer alignment compared to methods that extract only an aggregate feature from the entire video moment. We evaluate our approach on two recently proposed datasets for temporal localization of moments in video with natural language (DiDeMo and Charades-STA) extended to our video corpus moment retrieval setting. We show that our STAL re-ranking model outperforms the recently proposed Moment Context Network on all criteria across all datasets on our proposed task, obtaining relative gains of 37% - 118% for average recall and up to 30% for median rank. Moreover, our approach achieves more than 130x faster retrieval and 8x smaller index size with a 1M video corpus in an approximate setting.

Grounding language queries in videos aims at identifying the time interval (or moment) semantically relevant to a language query. The solution to this challenging task demands understanding videos' and queries' semantic content and the fine-grained reasoning about their multi-modal interactions. Our key idea is to recast this challenge into an algorithmic graph matching problem. Fueled by recent advances in Graph Neural Networks, we propose to leverage Graph Convolutional Networks to model video and textual information as well as their semantic alignment. To enable the mutual exchange of information across the modalities, we design a novel Video-Language Graph Matching Network (VLG-Net) to match video and query graphs. Core ingredients include representation graphs built atop video snippets and query tokens separately and used to model intra-modality relationships. A Graph Matching layer is adopted for cross-modal context modeling and multi-modal fusion. Finally, moment candidates are created using masked moment attention pooling by fusing the moment's enriched snippet features. We demonstrate superior performance over state-of-the-art grounding methods on three widely used datasets for temporal localization of moments in videos with language queries: ActivityNet-Captions, TACoS, and DiDeMo.

Video object detection has made significant progress in recent years thanks to convolutional neural networks (CNNs) and vision transformers (ViTs). Typically, CNNs excel at capturing local features but struggle to model global representations. Conversely, ViTs are adept at capturing long-range global features but face challenges in representing local feature details. Off-the-shelf video object detection methods solely rely on CNNs or ViTs to conduct feature aggregation, which hampers their capability to simultaneously leverage global and local information, thereby resulting in limited detection performance. In this paper, we propose a Transformer-GraphFormer Blender Network (TGBFormer) for video object detection, with three key technical improvements to fully exploit the advantages of transformers and graph convolutional networks while compensating for their limitations. First, we develop a spatial-temporal transformer module to aggregate global contextual information, constituting global representations with long-range feature dependencies. Second, we introduce a spatial-temporal GraphFormer module that utilizes local spatial and temporal relationships to aggregate features, generating new local representations that are complementary to the transformer outputs. Third, we design a global-local feature blender module to adaptively couple transformer-based global representations and GraphFormer-based local representations. Extensive experiments demonstrate that our TGBFormer establishes new state-of-the-art results on the ImageNet VID dataset. Particularly, our TGBFormer achieves 86.5% mAP while running at around 41.0 FPS on a single Tesla A100 GPU.

Modeling temporal characteristics plays a significant role in the representation learning of audio waveform. We propose Contrastive Long-form Language-Audio Pretraining (CoLLAP) to significantly extend the perception window for both the input audio (up to 5 minutes) and the language descriptions (exceeding 250 words), while enabling contrastive learning across modalities and temporal dynamics. Leveraging recent Music-LLMs to generate long-form music captions for full-length songs, augmented with musical temporal structures, we collect 51.3K audio-text pairs derived from the large-scale AudioSet training dataset, where the average audio length reaches 288 seconds. We propose a novel contrastive learning architecture that fuses language representations with structured audio representations by segmenting each song into clips and extracting their embeddings. With an attention mechanism, we capture multimodal temporal correlations, allowing the model to automatically weigh and enhance the final fusion score for improved contrastive alignment. Finally, we develop two variants of the CoLLAP model with different types of backbone language models. Through comprehensive experiments on multiple long-form music-text retrieval datasets, we demonstrate consistent performance improvement in retrieval accuracy compared with baselines. We also show the pretrained CoLLAP models can be transferred to various music information retrieval tasks, with heterogeneous long-form multimodal contexts.

Recent advancements in time series forecasting have explored augmenting models with text or vision modalities to improve accuracy. While text provides contextual understanding, it often lacks fine-grained temporal details. Conversely, vision captures intricate temporal patterns but lacks semantic context, limiting the complementary potential of these modalities. To address this, we propose \method, a novel multimodal framework that leverages pre-trained Vision-Language Models (VLMs) to bridge temporal, visual, and textual modalities for enhanced forecasting. Our framework comprises three key components: (1) a Retrieval-Augmented Learner, which extracts enriched temporal features through memory bank interactions; (2) a Vision-Augmented Learner, which encodes time series as informative images; and (3) a Text-Augmented Learner, which generates contextual textual descriptions. These components collaborate with frozen pre-trained VLMs to produce multimodal embeddings, which are then fused with temporal features for final prediction. Extensive experiments demonstrate that Time-VLM achieves superior performance, particularly in few-shot and zero-shot scenarios, thereby establishing a new direction for multimodal time series forecasting. Code is available at https://github.com/CityMind-Lab/ICML25-TimeVLM.

We consider the problem of localizing a spatio-temporal tube in a video corresponding to a given text query. This is a challenging task that requires the joint and efficient modeling of temporal, spatial and multi-modal interactions. To address this task, we propose TubeDETR, a transformer-based architecture inspired by the recent success of such models for text-conditioned object detection. Our model notably includes: (i) an efficient video and text encoder that models spatial multi-modal interactions over sparsely sampled frames and (ii) a space-time decoder that jointly performs spatio-temporal localization. We demonstrate the advantage of our proposed components through an extensive ablation study. We also evaluate our full approach on the spatio-temporal video grounding task and demonstrate improvements over the state of the art on the challenging VidSTG and HC-STVG benchmarks. Code and trained models are publicly available at https://antoyang.github.io/tubedetr.html.

Contrastive language-audio pretraining~(CLAP) has been developed to align the representations of audio and language, achieving remarkable performance in retrieval and classification tasks. However, current CLAP struggles to capture temporal information within audio and text features, presenting substantial limitations for tasks such as audio retrieval and generation. To address this gap, we introduce T-CLAP, a temporal-enhanced CLAP model. We use Large Language Models~(LLMs) and mixed-up strategies to generate temporal-contrastive captions for audio clips from extensive audio-text datasets. Subsequently, a new temporal-focused contrastive loss is designed to fine-tune the CLAP model by incorporating these synthetic data. We conduct comprehensive experiments and analysis in multiple downstream tasks. T-CLAP shows improved capability in capturing the temporal relationship of sound events and outperforms state-of-the-art models by a significant margin.

In this paper, we study the problem of temporal video grounding (TVG), which aims to predict the starting/ending time points of moments described by a text sentence within a long untrimmed video. Benefiting from fine-grained 3D visual features, the TVG techniques have achieved remarkable progress in recent years. However, the high complexity of 3D convolutional neural networks (CNNs) makes extracting dense 3D visual features time-consuming, which calls for intensive memory and computing resources. Towards efficient TVG, we propose a novel text-visual prompting (TVP) framework, which incorporates optimized perturbation patterns (that we call 'prompts') into both visual inputs and textual features of a TVG model. In sharp contrast to 3D CNNs, we show that TVP allows us to effectively co-train vision encoder and language encoder in a 2D TVG model and improves the performance of crossmodal feature fusion using only low-complexity sparse 2D visual features. Further, we propose a Temporal-Distance IoU (TDIoU) loss for efficient learning of TVG. Experiments on two benchmark datasets, Charades-STA and ActivityNet Captions datasets, empirically show that the proposed TVP significantly boosts the performance of 2D TVG (e.g., 9.79% improvement on Charades-STA and 30.77% improvement on ActivityNet Captions) and achieves 5x inference acceleration over TVG using 3D visual features. Codes are available at Open.Intel.

In recent years, analysis of remote sensing data has benefited immensely from borrowing techniques from the broader field of computer vision, such as the use of shared models pre-trained on large and diverse datasets. However, satellite imagery has unique features that are not accounted for in traditional computer vision, such as the existence of multiple revisits of the same location. Here, we explore the best way to use revisits in the framework of fine-tuning pre-trained remote sensing models. We focus on an applied research question of relevance to climate change mitigation -- power substation segmentation -- that is representative of applied uses of pre-trained models more generally. Through extensive tests of different multi-temporal input schemes across diverse model architectures, we find that fusing representations from multiple revisits in the model latent space is superior to other methods of using revisits, including as a form of data augmentation. We also find that a SWIN Transformer-based architecture performs better than U-nets and ViT-based models. We verify the generality of our results on a separate building density estimation task.

Efficient neural representations for dynamic video scenes are critical for applications ranging from video compression to interactive simulations. Yet, existing methods often face challenges related to high memory usage, lengthy training times, and temporal consistency. To address these issues, we introduce a novel neural video representation that combines 3D Gaussian splatting with continuous camera motion modeling. By leveraging Neural ODEs, our approach learns smooth camera trajectories while maintaining an explicit 3D scene representation through Gaussians. Additionally, we introduce a spatiotemporal hierarchical learning strategy, progressively refining spatial and temporal features to enhance reconstruction quality and accelerate convergence. This memory-efficient approach achieves high-quality rendering at impressive speeds. Experimental results show that our hierarchical learning, combined with robust camera motion modeling, captures complex dynamic scenes with strong temporal consistency, achieving state-of-the-art performance across diverse video datasets in both high- and low-motion scenarios.

The scarcity of annotated data in LiDAR point cloud understanding hinders effective representation learning. Consequently, scholars have been actively investigating efficacious self-supervised pre-training paradigms. Nevertheless, temporal information, which is inherent in the LiDAR point cloud sequence, is consistently disregarded. To better utilize this property, we propose an effective pre-training strategy, namely Temporal Masked Auto-Encoders (T-MAE), which takes as input temporally adjacent frames and learns temporal dependency. A SiamWCA backbone, containing a Siamese encoder and a windowed cross-attention (WCA) module, is established for the two-frame input. Considering that the movement of an ego-vehicle alters the view of the same instance, temporal modeling also serves as a robust and natural data augmentation, enhancing the comprehension of target objects. SiamWCA is a powerful architecture but heavily relies on annotated data. Our T-MAE pre-training strategy alleviates its demand for annotated data. Comprehensive experiments demonstrate that T-MAE achieves the best performance on both Waymo and ONCE datasets among competitive self-supervised approaches. Codes will be released at https://github.com/codename1995/T-MAE

In this paper, we explore the visual representations produced from a pre-trained text-to-video (T2V) diffusion model for video understanding tasks. We hypothesize that the latent representation learned from a pretrained generative T2V model encapsulates rich semantics and coherent temporal correspondences, thereby naturally facilitating video understanding. Our hypothesis is validated through the classic referring video object segmentation (R-VOS) task. We introduce a novel framework, termed "VD-IT", tailored with dedicatedly designed components built upon a fixed pretrained T2V model. Specifically, VD-IT uses textual information as a conditional input, ensuring semantic consistency across time for precise temporal instance matching. It further incorporates image tokens as supplementary textual inputs, enriching the feature set to generate detailed and nuanced masks. Besides, instead of using the standard Gaussian noise, we propose to predict the video-specific noise with an extra noise prediction module, which can help preserve the feature fidelity and elevates segmentation quality. Through extensive experiments, we surprisingly observe that fixed generative T2V diffusion models, unlike commonly used video backbones (e.g., Video Swin Transformer) pretrained with discriminative image/video pre-tasks, exhibit better potential to maintain semantic alignment and temporal consistency. On existing standard benchmarks, our VD-IT achieves highly competitive results, surpassing many existing state-of-the-art methods. The code is available at https://github.com/buxiangzhiren/VD-IT.

Integrating CNNs and RNNs to capture spatiotemporal dependencies is a prevalent strategy for spatiotemporal prediction tasks. However, the property of CNNs to learn local spatial information decreases their efficiency in capturing spatiotemporal dependencies, thereby limiting their prediction accuracy. In this paper, we propose a new recurrent cell, SwinLSTM, which integrates Swin Transformer blocks and the simplified LSTM, an extension that replaces the convolutional structure in ConvLSTM with the self-attention mechanism. Furthermore, we construct a network with SwinLSTM cell as the core for spatiotemporal prediction. Without using unique tricks, SwinLSTM outperforms state-of-the-art methods on Moving MNIST, Human3.6m, TaxiBJ, and KTH datasets. In particular, it exhibits a significant improvement in prediction accuracy compared to ConvLSTM. Our competitive experimental results demonstrate that learning global spatial dependencies is more advantageous for models to capture spatiotemporal dependencies. We hope that SwinLSTM can serve as a solid baseline to promote the advancement of spatiotemporal prediction accuracy. The codes are publicly available at https://github.com/SongTang-x/SwinLSTM.