Learning from Semantic Alignment between Unpaired Multiviews for Egocentric Video Recognition.
Qitong WangLong ZhaoLiangzhe YuanTing LiuXi PengPublished in: CoRR (2023)
Keyphrases
- unsupervised learning
- visual learning
- visual recognition
- semantic web
- multimedia
- learning systems
- active learning
- semantic concepts
- recognition rate
- machine learning
- reinforcement learning
- activity recognition
- recognition accuracy
- video data
- computer vision
- character recognition
- recognition algorithm
- semantic network
- video content
- event detection
- feature extraction
- knowledge acquisition
- image classification
- supervised learning
- object detection
- object recognition
- natural language