LaSe-E2V: Towards Language-guided Semantic-Aware Event-to-Video Reconstruction.
Kanghao ChenHangyu LiJiaZhou ZhouZeyu WangLin WangPublished in: CoRR (2024)
Keyphrases
- event recognition
- event detection
- video event
- video sequences
- video data
- real time
- multimedia
- programming language
- video streams
- video event detection
- temporal structure
- natural language
- video surveillance
- online video
- video segments
- video processing
- video content
- language learning
- key frames
- space time
- video frames
- multimedia data
- video browsing
- complex events
- digital video
- image reconstruction
- spatial and temporal
- video annotation
- high level
- three dimensional
- discrete tomography
- temporal events
- high resolution
- temporal patterns
- video analysis
- video retrieval
- object oriented
- human activities