GCF-Net: Gated Clip Fusion Network for Video Action Recognition.
Jenhao HsiaoJiawei ChenChiu Man HoPublished in: ECCV Workshops (5) (2020)
Keyphrases
- action recognition
- human actions
- action classification
- spatial temporal
- action detection
- video dataset
- recognition of human actions
- recognizing human actions
- bag of words
- motion features
- static images
- spatio temporal interest points
- activity recognition
- video clips
- human detection
- mid level
- computer vision
- human activities
- space time interest points
- body parts
- recognizing actions
- bag of features
- spatio temporal
- human pose
- motion history images
- wireless sensor networks
- multimedia
- video content
- video frames
- key frames
- space time
- action primitives
- object detection
- high level
- video sequences
- sensor networks
- video search
- video retrieval