Skip to content

Latest commit

 

History

28 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Static for Dynamic: Towards a Deeper Understanding of Dynamic Facial Expressions Using Static Expression Data

Link to IEEE Xplore, Link to Arxiv)
Yin Chen$^{†}$, Jia Li$^{†∗}$, Yu Zhang, Zhenzhen Hu, Shiguang Shan, Meng Wang, and Richang Hong

image

📰 News

[2026.08.12] 🎉🎉Our new paper SSM has been accepted by IEEE Transactions on Affective Computing! A novel Structured Semantic Mapping framework for bidirectional learning between Facial Action Units and Facial Expressions under heterogeneous datasets.

[2026.08.09] 🎉🎉 Our new paper CLAIP-Emo has been accepted by IEEE Signal Processing Letters! A simple yet very powerful audiovisual emotion recognition framework utilizing CLIP and CLAP with lightweight fine-tuning.

[2026.7.18] 🎉🎉🚀🚀Our work S2D was selected as the 2025 Best Paper Award (the only one!), for IEEE Transactions on Affective Computing by the IEEE Computer Society Publications Board.

image

[2025.9.17] Our previous work S2D has been recognized as a Highly Cited Paper by Clarivate.

[2025.9.17] The code and pre-trained models are available.

[2025.9.15] The paper is accepted by the IEEE Transactions on Affective Computing.

[2024.9.5] Code and pre-trained models will be released here.

🚀 Main Results

image image image

Pre-Training and Fine-Tune

1、 Download the pre-trained weights from Huggingface, and move it to the [finetune/checkpoints/pretrain/voxceleb2+AffectNet] directory.

2、 Run the following command to pre-train or fine-tune the model on the target dataset.

# create the envs
conda create -n s4d python=3.9
conda activate s4d
pip install -r requirements.txt

# pre-train
cd pretrain/omnivision &&  OMP_NUM_THREADS=1 HYDRA_FULL_ERROR=1 python train_app_submitit.py +experiments=videomae/videomae_base_vox2_affectnet

# fine-tune
cd finetune && bash run.sh

✏️ Citation

If you find this work helpful, please consider citing:

@ARTICLE{10663980,
  author={Chen, Yin and Li, Jia and Shan, Shiguang and Wang, Meng and Hong, Richang},
  journal={IEEE Transactions on Affective Computing}, 
  title={From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videos}, 
  year={2024},
  volume={},
  number={},
  pages={1-15},
  keywords={Adaptation models;Videos;Computational modeling;Feature extraction;Transformers;Task analysis;Face recognition;Dynamic facial expression recognition;emotion ambiguity;model adaptation;transfer learning},
  doi={10.1109/TAFFC.2024.3453443}}

@ARTICLE{11207542,
  author={Chen, Yin and Li, Jia and Zhang, Yu and Hu, Zhenzhen and Shan, Shiguang and Wang, Meng and Hong, Richang},
  journal={IEEE Transactions on Affective Computing}, 
  title={Static for Dynamic: Towards a Deeper Understanding of Dynamic Facial Expressions Using Static Expression Data}, 
  year={2025},
  volume={},
  number={},
  pages={1-15},
  keywords={Videos;Adaptation models;Face recognition;Transformers;Semantics;Multitasking;Computer vision;Spatiotemporal phenomena;Correlation;Emotion recognition;Dynamic facial expression recognition;mixture of experts;self-supervised learning;vision transformer},
  doi={10.1109/TAFFC.2025.3623135}}

}

@article{chen2026claip,
  title={CLAIP-Emo: Parameter-Efficient Adaptation of Language-Supervised Models for In-the-Wild Audiovisual Emotion Recognition},
  author={Chen, Yin and Li, Jia and Hu, Jinpeng and Hu, Zhenzhen and Hong, Richang},
  journal={IEEE Signal Processing Letters},
  year={2026},
  publisher={IEEE}
}

Star History

Star History Chart

About

[TAFFC 2025] The offical implementation of paper: Static for Dynamic: Towards a Deeper Understanding of Dynamic Facial Expressions Using Static Expression Data

Topics

Resources

Stars

69 stars

Watchers

2 watching

Forks

Releases

Packages

Contributors

Languages