Visual Commonsense-aware Representation Network for Video Captioning.
Pengpeng ZengHaonan ZhangLianli GaoXiangpeng LiJin QianHeng Tao ShenPublished in: CoRR (2022)
Keyphrases
- visual cues
- visual properties
- visual representation
- video data
- video streams
- multimedia
- visual analysis
- visual features
- visual data
- network model
- computer networks
- video delivery
- video sequences
- temporal information
- network traffic
- video surveillance
- news video
- graphical representation
- real time
- raw image
- network conditions
- image retrieval
- wireless sensor networks
- visual patterns
- visual information
- complex networks
- video analysis
- spatial relations
- video content