TSM: Temporal Shift Module for Efficient and Scalable Video Understanding on Edge DevicesJi LinChuang Ganet al.2022IEEE TPAMI
ComPhy: Compositional Physical Reasoning of Objects and Events from VideosZhenfang ChenKexin Yiet al.2022ICLR 2022
Contact Points Discovery for Soft-Body Manipulations with Differentiable PhysicsSizhe LiZhiao Huanget al.2022ICLR 2022
RISP: Rendering-Invariant State Predictor with Differentiable Simulation and Rendering for Cross-Domain Parameter EstimationPingchuan MaTao Duet al.2022ICLR 2022
FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual RelationsLingjie MeiJiayuan Maoet al.2022ICLR 2022
Purely Attention Based Local Feature Integration for Video ClassificationXiang LongGerard De Meloet al.2022IEEE TPAMI
Text-instance graph: Exploring the relational semantics for text-based visual question answeringXiangpeng LiBo Wuet al.2022Pattern Recognition