Towards Extremely Compact RNNs for Video Recognition with Fully Decomposed Hierarchical Tucker Structure.
Miao YinSiyu LiaoXiao-Yang LiuXiaodong WangBo YuanPublished in: CoRR (2021)
Keyphrases
- video data
- hierarchical structure
- recurrent neural networks
- recognition rate
- hierarchical structures
- object recognition
- video surveillance
- multimedia
- structural analysis
- video frames
- video streams
- real time
- human activities
- spatial and temporal
- hierarchical decomposition
- video analysis
- spatio temporal
- pattern recognition
- feed forward
- unsupervised learning
- recognition algorithm
- fuzzy neural network
- gait recognition
- recognition process
- video sequences
- temporal structure
- computer vision