VideoLSTM Convolves, Attends and Flows for Action Recognition.
Zhenyang LiEfstratios GavvesMihir JainCees G. M. SnoekPublished in: CoRR (2016)
Keyphrases
- action recognition
- human actions
- bag of words
- human detection
- activity recognition
- computer vision
- recognition of human actions
- spatial temporal
- recognizing human actions
- action classification
- body parts
- view invariant
- recognizing actions
- static images
- mid level
- motion features
- action recognition in videos
- image sequences
- high level