每日Paper进步屋
视频理解 视频理解
2022-07-26 更新Egocentric scene context for human-centric environment understanding from videoAuthors:Tushar Nagarajan,
2022-07-26
视频理解 视频理解
2022-07-21 更新GraphVid: It Only Takes a Few Nodes to Understand a VideoAuthors:Eitan Kosman, Dotan Di Castro We propose
2022-07-21
视频理解 视频理解
2022-07-19 更新Prompting Visual-Language Models for Efficient Video UnderstandingAuthors:Chen Ju, Tengda Han, Kunhao Zheng
2022-07-19
视频理解 视频理解
2022-07-07 更新STVGFormer: Spatio-Temporal Video Grounding with Static-Dynamic Cross-Modal UnderstandingAuthors:Zihang L
2022-07-07
视频理解 视频理解
2022-07-06 更新Federated Self-supervised Learning for Video UnderstandingAuthors:Yasar Abbas Ur Rehman, Yan Gao, Jiajun Sh
2022-07-06
视频理解 视频理解
2022-06-25 更新LAVENDER: Unifying Video-Language Understanding as Masked Language ModelingAuthors:Linjie Li, Zhe Gan, Ke
2022-06-25
视频理解 视频理解
2022-06-07 更新Revisiting the “Video” in Video-Language UnderstandingAuthors:Shyamal Buch, Cristóbal Eyzaguirre, Adrien Ga
2022-06-07
视频理解 视频理解
2022-05-20 更新Free Lunch for Surgical Video Understanding by Distilling Self-SupervisionsAuthors:Xinpeng Ding, Ziwei Li
2022-05-20
视频理解 视频理解
2022-05-03 更新Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural ActivitiesAuthors:Fadime
2022-05-03
7 / 8