Informative Attention Supervision for Grounded Video Description.
Boyang WanWenhui JiangYuming FangPublished in: ICASSP (2022)
Keyphrases
- multimedia
- video data
- video sequences
- high level
- video content
- video frames
- real time video
- video streams
- real time
- video clips
- visual attention
- content description
- online video
- video shots
- video database
- video analysis
- video retrieval
- video summarization
- video images
- event detection
- input image
- spatial temporal
- learning algorithm
- neural network
- data sets