paper-with-me

Papers Object State Change Classification on Ego4D

“Object State Change Classification on Ego4D” 태그가 달린 논문 2편 · 필터 해제

EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens

2022-11-19 · Sunil Hwang, Jaehong Yoon, Youngwan Lee, Sung Ju Hwang

Masked Video Autoencoder (MVA) approaches have demonstrated their potential by significantly outperforming previous video representation learning methods. However, they waste an excessive amount of computations and memor…

Action RecognitionObject State Change ClassificationObject State Change Classification on Ego4DRepresentation Learning+3

Egocentric Video-Language Pretraining

2022-06-03 · Kevin Qinghong Lin, Alex Jinpeng Wang, Mattia Soldan, Michael Wray 외

Video-Language Pretraining (VLP), which aims to learn transferable representation to advance a wide range of video-text downstream tasks, has recently received increasing attention. Best performing works rely on large-sc…

Action RecognitionContrastive LearningMoment QueriesMulti-Instance Retrieval+9
1–2 / 2