Delving into Details: Synopsis-to-Detail Networks for Video Recognition.
Shuxian LiangXu ShenJianqiang HuangXian-Sheng HuaPublished in: ECCV (4) (2022)
Keyphrases
- recognition accuracy
- recognition rate
- multimedia
- human activities
- video synopsis
- video content
- video frames
- video sequences
- video streams
- action recognition
- recognition algorithm
- object recognition
- data streams
- automatic recognition
- pattern recognition
- key frames
- feature extraction
- video clips
- video data
- character recognition
- data structure
- human actions
- recognition process
- social networks
- static images
- video database
- hand gestures
- multimedia data
- spatial and temporal
- object detection
- video retrieval
- background subtraction
- network structure
- sliding window
- spatio temporal
- facial actions
- neural network