Login / Signup
GL-RG: Global-Local Representation Granularity for Video Captioning.
Liqi Yan
Qifan Wang
Yiming Cui
Fuli Feng
Xiaojun Quan
Xiangyu Zhang
Dongfang Liu
Published in:
CoRR (2022)
Keyphrases
</>
real time
video sequences
video content
video clips
video data
spatial and temporal
data sets
video representation
real time video
representation scheme
video database
video analysis
multimedia
video surveillance
temporal information
video streams
video shots
motion estimation
low level