Showing cs.CVShow all
2 papers · 1 filter
cs.CV2025
ReactDiff: Fundamental Multiple Appropriate Facial Reaction Diffusion Model
Luo Cheng, Song Siyang, Yan Siyuan +2
The automatic generation of diverse and human-like facial reactions in dyadic dialogue remains a critical challenge for human-computer interaction systems. Existing methods fail to…
cs.CV2024
Enhancing Vision-Language Models Generalization via Diversity-Driven Novel Feature Synthesis
Siyuan Yan, Cheng Luo, Zhen Yu +1
Vision-language foundation models like CLIP have shown impressive zero-shot generalization, but finetuning on downstream datasets can cause overfitting and loss of its generalizati…