Localizing Events in Videos with Multimodal Queries.
Gengyuan ZhangMang Ling Ada FokYan XiaYansong TangDaniel CremersPhilip H. S. TorrVolker TrespJindong GuPublished in: CoRR (2024)
Keyphrases
- video event
- event recognition
- human activities
- video clips
- event detection
- query processing
- spatio temporal patterns
- video sequences
- video analysis
- range queries
- query language
- database
- video frames
- soccer video
- sports video
- query evaluation
- event models
- web search engines
- data sources
- database queries
- unusual events
- spatio temporal
- temporal relations
- efficient processing
- temporal relationships
- complex queries
- activity recognition
- response time
- multi modal
- video event detection
- video content
- video dataset
- temporal structure
- human actions
- query formulation
- temporal patterns
- video surveillance
- query logs
- visual information
- user queries
- action recognition
- search engine