Decoupled Spatial Temporal Graphs for Generic Visual Grounding.

Qianyu Feng Yunchao Wei Ming-Ming Cheng Yi Yang

Published in: CoRR (2021)

Keyphrases

spatial temporal
spatial and temporal
temporal information
spatio temporal
visual information
action recognition
high level
video shots
spatial information
visual features
human actions
low level
spatial and temporal information
multimedia
image classification
visual data
video sequences