Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,77 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- KlingTeam/Emo-CFG
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
base_model:
|
| 8 |
+
- Qwen/Qwen2.5-VL-7B-Instruct
|
| 9 |
+
pipeline_tag: video-text-to-text
|
| 10 |
+
---
|
| 11 |
+
<div align=center>
|
| 12 |
+
<img src="assets/logo.png" width=15%>
|
| 13 |
+
<h1>VidEmo: Affective-Tree Reasoning for Emotion-Centric Video Foundation Models</h1>
|
| 14 |
+
|
| 15 |
+
<div class="is-size-5 publication-authors">
|
| 16 |
+
<span class="author-block">
|
| 17 |
+
<a href="https://zzcheng.top/" target="_blank">Zhicheng Zhang</a><sup>1,β </sup>,
|
| 18 |
+
</span>
|
| 19 |
+
<span class="author-block">
|
| 20 |
+
Weicheng Wang<sup>1</sup>,
|
| 21 |
+
</span>
|
| 22 |
+
<span class="author-block">
|
| 23 |
+
<a href="https://yongjie-zhu.github.io/" target="_blank">Yongjie Zhu</a><sup>3,β‘</sup>,
|
| 24 |
+
</span>
|
| 25 |
+
<span class="author-block">
|
| 26 |
+
Wenyu Qin<sup>3</sup>,
|
| 27 |
+
</span>
|
| 28 |
+
<span class="author-block">
|
| 29 |
+
<a href="https://scholar.google.com/citations?user=P6MraaYAAAAJ&hl=en/" target="_blank">Pengfei Wan</a><sup>3</sup>,
|
| 30 |
+
</span>
|
| 31 |
+
<span class="author-block">
|
| 32 |
+
Di Zhang<sup>3</sup>,
|
| 33 |
+
</span>
|
| 34 |
+
<span class="author-block">
|
| 35 |
+
<a href="https://cv.nankai.edu.cn/" target="_blank">Jufeng Yang</a><sup>1,2,β</sup>
|
| 36 |
+
</span>
|
| 37 |
+
</div>
|
| 38 |
+
|
| 39 |
+
<!-- Institution -->
|
| 40 |
+
<div class="is-size-5 publication-authors">
|
| 41 |
+
<sup>1</sup><span class="author-block">Nankai University</span>
|
| 42 |
+
<sup>2</sup><span class="author-block">Pengcheng Laboratory</span>
|
| 43 |
+
<sup>3</sup><span class="author-block">Kuaishou Technology</span>
|
| 44 |
+
</div>
|
| 45 |
+
<div class="is-size-5 publication-authors">
|
| 46 |
+
<sup>β </sup><span class="author-block">Work done at KlingAI</span>
|
| 47 |
+
<sup>β‘</sup><span class="author-block">Project Leader</span>
|
| 48 |
+
<sup>β</sup><span class="author-block">Corresponding Author</span>
|
| 49 |
+
</div>
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
**π Accepted by [NeurIPS 2025](https://neurips.cc/virtual/2025/loc/san-diego/poster/115267) π**
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
<a href="https://arxiv.org/abs/2511.02712" target="_blank">
|
| 57 |
+
<img alt="arXiv" src="https://img.shields.io/badge/arXiv-Kling--VidEmo-red?logo=arxiv" height="25" />
|
| 58 |
+
</a>
|
| 59 |
+
<a href="https://zzcheng.top/VidEmo" target="_blank">
|
| 60 |
+
<img alt="Website" src="https://img.shields.io/badge/π_Website-Homepage-blue.svg" height="25" />
|
| 61 |
+
</a>
|
| 62 |
+
<a href="https://github.com/KlingTeam/VidEmo" target="_blank">
|
| 63 |
+
<img alt="Github" src="https://img.shields.io/badge/βοΈ_Github-Code-white.svg" height="25" />
|
| 64 |
+
</a>
|
| 65 |
+
<a href="https://zzcheng.top/assets/pdf/2025_NeurIPS_VidEmo_poster.pdf" target="_blank">
|
| 66 |
+
<img alt="HF Dataset: Emo-CFG 2.1M" src="https://img.shields.io/badge/π
-Poster-gree.svg" height="25" />
|
| 67 |
+
</a>
|
| 68 |
+
<br>
|
| 69 |
+
<a href="https://huggingface.co/KlingTeam/VidEmo-3B" target="_blank">
|
| 70 |
+
<img alt="HF Model: VidEmo Family" src="https://img.shields.io/badge/%F0%9F%A4%97%20_Model-Kling--VidEmo--3B-ffc107?color=ffc107&logoColor=white" height="25" />
|
| 71 |
+
</a>
|
| 72 |
+
<a href="https://huggingface.co/KlingTeam/VidEmo-7B" target="_blank">
|
| 73 |
+
<img alt="HF Model: VidEmo Family" src="https://img.shields.io/badge/%F0%9F%A4%97%20_Model-Kling--VidEmo--7B-ffc107?color=ffc107&logoColor=white" height="25" />
|
| 74 |
+
</a>
|
| 75 |
+
<a href="https://huggingface.co/datasets/KlingTeam/Emo-CFG" target="_blank">
|
| 76 |
+
<img alt="HF Dataset: Emo-CFG 2.1M" src="https://img.shields.io/badge/%F0%9F%A4%97%20_Data-Emo--CFG--2.1M-ffc107?color=ffc107&logoColor=white" height="25" />
|
| 77 |
+
</a>
|