Learning from Semantic Alignment between Unpaired Multiviews for Egocentric Video Recognition.
Qitong WangLong ZhaoLiangzhe YuanTing LiuXi PengPublished in: ICCV (2023)
Keyphrases
- visual recognition
- learning process
- reinforcement learning
- learning systems
- online learning
- unsupervised learning
- activity recognition
- learning algorithm
- visual learning
- video sequences
- recognition accuracy
- learning tasks
- pattern recognition
- active learning
- recognition rate
- video content
- supervised learning
- learning stage
- video streams
- real time
- object detection
- prior knowledge
- object recognition
- high level
- machine learning