Video Caption Dataset for Describing Human Actions in Japanese.
Yutaro ShigetoYuya YoshikawaJiaqing LinAkikazu TakeuchiPublished in: CoRR (2020)
Keyphrases
- human actions
- visual features
- action recognition
- video sequences
- space time
- spatio temporal
- human activities
- human motion
- action classification
- spatial temporal
- video shots
- video database
- recognizing human actions
- activity recognition
- recognition of human actions
- motion recognition
- visual data
- view invariant
- action sequences
- web videos
- image sequences
- action detection
- motion features
- space time interest points
- key frames
- object recognition
- human pose
- video retrieval
- spatial and temporal
- video data
- image retrieval
- news video
- motion capture
- video content
- feature extraction
- action recognition in videos
- computer vision