Sign in

CAViT: Contextual Alignment Vision Transformer for Video Object Re-identification.

Jinlin WuLingxiao HeWu LiuYang YangZhen LeiTao MeiStan Z. Li
Published in: ECCV (14) (2022)
Keyphrases
  • video objects
  • video sequences
  • computer vision
  • vision system
  • compressed domain
  • video streams
  • video analysis
  • object based video
  • object detection
  • keywords
  • object recognition
  • image quality
  • bayesian framework