VOOZH about

URL: https://huggingface.co/KlingTeam/VidEmo-3B

โ‡ฑ KlingTeam/VidEmo-3B ยท Hugging Face


๐Ÿ‘ Image

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

Zhicheng Zhang1,โ€ , Weicheng Wang1, Yongjie Zhu3,โ€ก, Wenyu Qin3, Pengfei Wan3, Di Zhang3, Jufeng Yang1,2,โœ‰
1Nankai University      2Pengcheng Laboratory      3Kuaishou Technology     
โ€ Work done at KlingAI      โ€กProject Leader      โœ‰Corresponding Author     

๐ŸŽ‰ Accepted by NeurIPS 2025 ๐ŸŽ‰

๐Ÿ‘ arXiv
๐Ÿ‘ Website
๐Ÿ‘ Github
๐Ÿ‘ Awesome
๐Ÿ‘ HF Dataset: Emo-CFG 2.1M

๐Ÿ‘ HF Model: VidEmo Family
๐Ÿ‘ HF Model: VidEmo Family
๐Ÿ‘ HF Dataset: Emo-CFG 2.1M
Downloads last month
9
Safetensors
Model size
4B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for KlingTeam/VidEmo-3B

Finetuned
(797)
this model
Quantizations
1 model

Dataset used to train KlingTeam/VidEmo-3B

Paper for KlingTeam/VidEmo-3B