AV-TAD: Audio-Visual Temporal Action Detection With Transformer.

Yangcheng Li Zefang Yu Suncheng Xiang Ting Liu Yuzhuo Fu

Published in: ICASSP (2023)

Keyphrases

audio visual
action detection
multi modal
visual information
action recognition
spatio temporal
temporal information
object detection
spatial and temporal
visual data
multimedia
atomic actions
temporal relations
pattern search
temporal reasoning
feature selection
space time
high level