VRDFormer: End-to-End Video Visual Relation Detection with Transformers.

Sipeng Zheng Shizhe Chen Qin Jin

Published in: CVPR (2022)

Keyphrases

end to end
scalable video
text localization and recognition
video sequences
multipath
admission control
video streams
video content
ad hoc networks
real time
video data
visual information
congestion control
video frames
video analysis
wireless ad hoc networks
high bandwidth
computational complexity
internet protocol