Video you only look once: Overall temporal convolutions for action recognition.
Longlong JingXiaodong YangYingli TianPublished in: J. Vis. Commun. Image Represent. (2018)
Keyphrases
- action recognition
- spatial temporal
- human actions
- action classification
- motion history images
- action detection
- video dataset
- spatio temporal
- bag of words
- temporal information
- static images
- atomic actions
- activity recognition
- recognizing human actions
- recognition of human actions
- motion features
- human activities
- space time interest points
- spatial and temporal
- human detection
- space time
- computer vision
- body parts
- video content
- video sequences
- temporal structure
- multimedia
- mid level
- recognizing actions
- temporal coherence
- video streams
- bag of features
- motion capture data
- video data
- event recognition
- event detection
- view invariant
- max margin
- image features
- depth sensors
- low level
- action primitives
- human motion
- human pose
- machine learning