Sign in

SEAL: A Large-scale Video Dataset of Multi-grained Spatio-temporally Action Localization.

Shimin ChenWei LiChen ChenJianyang GuJiaming ChuXunqiang TaoYandong Guo
Published in: CoRR (2022)
Keyphrases
  • video dataset
  • spatio temporally
  • action recognition
  • human actions
  • spatio temporal
  • video sequences
  • video data
  • video frames
  • space time
  • metadata
  • face recognition
  • image retrieval
  • active learning