MultiVENT: Multilingual Videos of Events and Aligned Natural Text.
Kate SandersDavid EtterReno KrizBenjamin Van DurmePublished in: NeurIPS (2023)
Keyphrases
- event recognition
- video event
- text generation
- human activities
- video clips
- tv news
- event detection
- spatio temporal patterns
- multi lingual
- video segments
- video dataset
- news stories
- video frames
- temporal relationships
- unusual events
- video collections
- video analysis
- video sequences
- sports video
- video search
- keywords
- text retrieval
- information retrieval
- surveillance videos
- video content
- natural language generation
- text documents
- image sequences
- text mining
- video event detection
- news video
- cross lingual
- photo collections
- machine translation system
- text categorization
- natural language processing
- temporal structure
- temporal events
- information extraction
- digital libraries
- temporal patterns
- cross language
- event models
- action recognition
- video surveillance
- temporal information