Login / Signup

Weakly Supervised Video Representation Learning with Unaligned Text for Sequential Videos.

Sixun DongHuazhang HuDongze LianWeixin LuoYicheng QianShenghua Gao
Published in: CoRR (2023)
Keyphrases
  • weakly supervised
  • video representation
  • spatio temporal
  • relation extraction
  • superpixels
  • object class
  • information retrieval
  • viewpoint
  • video analysis
  • semi supervised
  • named entities