Online learnable keyframe extraction in videos and its application with semantic word vector in action recognition.
G. M. Mashrur E ElahiYee-Hong YangPublished in: Pattern Recognit. (2022)
Keyphrases
- action recognition
- video database
- human actions
- action classification
- recognition of human actions
- video dataset
- bag of words
- recognizing human actions
- ucf sports
- view invariant
- human activities
- static images
- activity recognition
- spatio temporal interest points
- recognizing actions
- human detection
- motion features
- spatial temporal
- action detection
- body parts
- video shots
- action recognition in videos
- space time interest points
- video frames
- mid level features
- video content
- semantic information
- video sequences
- computer vision
- caption text
- video clips
- co occurrence
- motion capture data
- low level features
- n gram
- information extraction
- high level
- video data
- video search
- semantic content
- human pose
- semantic concepts
- semantic similarity
- visual words
- feature vectors
- image retrieval