Probing Visual-Audio Representation for Video Highlight Detection via Hard-Pairs Guided Contrastive Learning.
Shuaicheng LiFeng ZhangKunlin YangLingbo LiuShinan LiuJun HouShuai YiPublished in: CoRR (2022)
Keyphrases
- learning process
- reinforcement learning
- learning algorithm
- visual learning
- visual analysis
- multimedia
- video streams
- visual representation
- soccer video
- real time
- supervised learning
- visual data
- pairwise
- low level
- object detection
- image classification
- visual features
- video data
- visual information
- event detection
- learning tasks