Online Learnable Keyframe Extraction in Videos and its Application with Semantic Word Vector in Action Recognition.
G. M. Mashrur E ElahiYee-Hong YangPublished in: CoRR (2020)
Keyphrases
- action recognition
- video database
- human actions
- action classification
- video dataset
- recognition of human actions
- recognizing human actions
- bag of words
- activity recognition
- ucf sports
- human activities
- motion features
- recognizing actions
- view invariant
- static images
- computer vision
- spatio temporal interest points
- video content
- space time interest points
- video shots
- spatial temporal
- video clips
- human detection
- body parts
- semantic similarity
- key frames
- action recognition in videos
- action detection
- semantic information
- video sequences
- high level
- motion history images
- human object interactions
- caption text
- video frames
- mid level features
- n gram
- co occurrence
- information extraction
- machine learning
- feature vectors
- video retrieval
- motion capture data
- low level features
- semantic content
- human pose
- semantic concepts
- video analysis