Semantic-guided spatio-temporal attention for few-shot action recognition.
Jianyu WangBaolin LiuPublished in: Appl. Intell. (2024)
Keyphrases
- action recognition
- human actions
- spatio temporal
- spatial temporal
- action recognition in videos
- view invariant
- spatio temporal interest points
- video shots
- bag of words
- recognition of human actions
- video sequences
- human detection
- activity recognition
- action classification
- visual features
- body parts
- video database
- video dataset
- spatial and temporal
- recognizing human actions
- static images
- space time
- computer vision
- view invariant action recognition
- semantic concepts
- human activities
- bag of features
- human pose
- mid level
- low level features
- action primitives
- video data
- human motion
- semantic similarity
- recognizing actions
- moving objects
- object recognition
- image sequences