A UNIFIED FRAMEWORK FOR MASKED AND MASK-FREE FACE RECOGNITION VIA FEATURE RECTIFICATIONShaozhe HaoChaofeng Chenet al.2022ICIP 2022
ComPhy: Compositional Physical Reasoning of Objects and Events from VideosZhenfang ChenKexin Yiet al.2022ICLR 2022
Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and LanguageMingyu DingZhenfang Chenet al.2021NeurIPS 2021
Grounding Physical Object and Event Concepts Through Dynamic Visual ReasoningZhenfang ChenJiayuan Maoet al.2021ICLR 2021