Comprehensive Visual Grounding for Video Description.
Wenhui JiangYibo ChengLinxin LiuYuming FangYuxin PengYang LiuPublished in: AAAI (2024)
Keyphrases
- visual data
- high level
- video data
- video sequences
- visual cues
- content description
- multimedia
- visual analysis
- video content
- visual information
- visual features
- video search
- mid level
- content based video retrieval
- real time
- low level
- key frames
- video segmentation
- visual concepts
- multimedia data
- visual saliency
- news video
- video processing
- visual input
- eye tracking data
- video indexing
- real time video
- symbolic descriptions
- visual perception
- video database
- video retrieval
- spatial and temporal
- video frames
- space time
- object recognition