--- license: apache-2.0 datasets: - KlingTeam/Emo-CFG language: - en base_model: - Qwen/Qwen2.5-VL-7B-Instruct pipeline_tag: video-text-to-text ---

VidEmo: Affective-Tree Reasoning for Emotion-Centric Video Foundation Models

Zhicheng Zhang1,†, Weicheng Wang1, Yongjie Zhu3,‡, Wenyu Qin3, Pengfei Wan3, Di Zhang3, Jufeng Yang1,2,✉
1Nankai University      2Pengcheng Laboratory      3Kuaishou Technology     
Work done at KlingAI      Project Leader      Corresponding Author     
**🎉 Accepted by [NeurIPS 2025](https://neurips.cc/virtual/2025/loc/san-diego/poster/115267) 🎉** arXiv Website Github Awesome HF Dataset: Emo-CFG 2.1M
HF Model: VidEmo Family HF Model: VidEmo Family HF Dataset: Emo-CFG 2.1M