Update README.md

README.md

@@ -1,3 +1,116 @@
----
-license: apache-2.0
----
+
+---
+license: apache-2.0
+task_categories:
+- video-retrieval
+- image-retrieval
+tags:
+- composed-video-retrieval
+- composed-image-retrieval
+- vision-language
+- pytorch
+- aaai-2026
+---
+
+<a id="top"></a>
+<div align="center">
+  <h1>🎬 (AAAI 2026) ReTrack: Evidence-Driven Dual-Stream Directional Anchor Calibration Network for Composed Video Retrieval (Model Weights)</h1>
+    <div>
+  <a target="_blank" href="https://lee-zixu.github.io/">Zixu&#160;Li</a><sup>1</sup>,
+  <a target="_blank" href="https://faculty.sdu.edu.cn/huyupeng1/zh_CN/index.htm">Yupeng&#160;Hu</a><sup>1&#9993</sup>,
+  <a target="_blank" href="https://zivchen-ty.github.io/">Zhiwei&#160;Chen</a><sup>1</sup>,
+  <a target="_blank" href="https://windlikeo.github.io/HQL.github.io/">Qinlei&#160;Huang</a><sup>1</sup>,
+  Guozhi&#160;Qiu<sup>1</sup>,
+  <a target="_blank" href="https://zhihfu.github.io/">Zhiheng&#160;Fu</a><sup>1</sup>,
+  <a target="_blank" href="https://mengliu1991.github.io">Meng&#160;Liu</a><sup>2</sup>
+  </div>
+  <sup>1</sup>School of Software, Shandong University &#160&#160&#160</span>  <br>
+  <sup>2</sup>School of Computer Science and Technology, Shandong Jianzhu University&#160&#160&#160</span>
+  <br />
+  <sup>&#9993&#160;</sup>Corresponding author&#160;&#160;</span>
+  <br/>
+  <p>
+      <a href="https://aaai.org/Conferences/AAAI-26/"><img src="https://img.shields.io/badge/AAAI-2026-blue.svg?style=flat-square" alt="AAAI 2026"></a>
+      <a href="https://ojs.aaai.org/index.php/AAAI/article/view/39507"><img alt='Paper' src="https://img.shields.io/badge/Paper-AAAI.39507-green.svg?style=flat-square"></a>
+      <a href="https://lee-zixu.github.io/ReTrack.github.io/"><img alt='Project Page' src="https://img.shields.io/badge/Website-orange?style=flat-square"></a>
+      <a href="https://github.com/Lee-zixu/ReTrack"><img alt='GitHub' src="https://img.shields.io/badge/GitHub-Repository-black?style=flat-square&logo=github"></a>
+  </p>
+</div>
+
+This repository hosts the official pre-trained model weights for **ReTrack**, an evidence-driven framework designed to calibrate directional bias in composed features for both Composed Video Retrieval (CVR) and Composed Image Retrieval (CIR) tasks.
+
+---
+
+
+## 📌 Model Information
+
+### 1. Model Name
+**ReTrack** (Evidence-Driven Dual-Stream Directional Anchor Calibration Network) Checkpoints.
+
+### 2. Task Type & Applicable Tasks
+- **Task Type:** Composed Video Retrieval (CVR) and Composed Image Retrieval (CIR).
+- **Applicable Tasks:** Retrieving a target video or image based on a reference visual input combined with a modification text prompt. The model significantly reduces uncertainty caused by highly similar retrieval candidates in multi-modal queries.
+
+### 3. Project Introduction
+**ReTrack** is an advanced open-source PyTorch framework built on top of BLIP-2 (via Salesforce LAVIS) that improves multi-modal query understanding. It features:
+- 🎯 **Dual-Stream Directional Anchor Calibration:** Explicitly identifies and calibrates visual and textual semantic contributions to resolve directional bias.
+- ⚖️ **Reliable Evidence-Driven Alignment:** Leverages Dempster-Shafer Theory to evaluate similarity reliability, minimizing ambiguity among candidates.
+
+### 4. Training Data Source & Hosted Weights
+The framework is trained to support both the **WebVid-CoVR** dataset for video retrieval and the **FashionIQ / CIRR** datasets for image retrieval. 
+
+This Hugging Face repository provides the following pre-trained checkpoint:
+* 📄 `ReTrack-WebVid-Frame1.ckpt`: The checkpoint trained on the WebVid-CoVR dataset (using a 1-frame configuration setting).
+
+---
+
+## 🚀 Usage & Basic Inference
+
+These weights are designed to be evaluated using the highly modular, Hydra-configured [ReTrack GitHub repository](https://github.com/Lee-zixu/ReTrack).
+
+### Step 1: Prepare the Environment
+We recommend using Anaconda. Clone the repository and install dependencies:
+```bash
+git clone https://github.com/iLearn-Lab/AAAI26-ReTrack.git
+cd ReTrack
+conda create -n retrack python=3.8 -y
+conda activate retrack
+conda install pytorch torchvision torchaudio pytorch-cuda=11.8 -c pytorch -c nvidia
+pip install -r requirements.txt
+```
+
+### Step 2: Download Model Weights & Prepare Data
+1. Download `ReTrack-WebVid-Frame1.ckpt` from this Hugging Face repository. 
+2. Place the checkpoint in the appropriate directory as expected by your Hydra configuration (e.g., within a `checkpoints/` folder).
+3. Ensure the WebVid-CoVR dataset is placed under your defined `datasets_dir` in `configs/machine/default.yaml`.
+
+### Step 3: Run Evaluation
+To evaluate the trained CVR model, use `test.py` and specify the path to your downloaded checkpoint via Hydra CLI overrides:
+```bash
+python test.py \
+    model.ckpt_path=/path/to/your/ReTrack-WebVid-Frame1.ckpt \
+    +test=webvid-covr
+```
+*(Refer to the `configs/` directory in the code repository for advanced hyperparameter and path adjustments)*.
+
+---
+
+## ⚠️ Limitations & Notes
+
+- **Configuration:** ReTrack is entirely managed by **Hydra** and **Lightning Fabric**. Make sure you are familiar with overriding configurations via the CLI or modifying the YAML files in the `configs/` directory.
+- **Environment:** The project was specifically developed and evaluated on Python 3.8 and PyTorch 2.1.0; using drastically different versions may yield unexpected behaviors.
+
+---
+
+## 📝⭐️ Citation
+
+If you find our framework, code, or these weights useful in your research, please consider leaving a **Star** ⭐️ on our GitHub repository and citing our AAAI 2026 paper:
+
+```bibtex
+@inproceedings{ReTrack,
+  title={ReTrack: Evidence Driven Dual Stream Directional Anchor Calibration Network for Composed Video Retrieval},
+  author={Li, Zixu and Hu, Yupeng and Chen, Zhiwei and Huang, Qinlei and Qiu, Guozhi and Fu, Zhiheng and Liu, Meng},
+  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
+  year={2026}
+}
+```