A Video is Worth 10, 000 Words: Training and Benchmarking with Diverse Captions for Better Long Video Retrieval.
Matthew GwilliamMichael CogswellMeng YeKaran SikkaAbhinav ShrivastavaAjay DivakaranPublished in: CoRR (2023)
Keyphrases
- long video
- video segments
- video clips
- video content
- video indexing
- news video
- scene segmentation
- video retrieval
- video streams
- information retrieval
- video frames
- video sequences
- video database
- retrieval systems
- related documents
- relevance feedback
- textual descriptions
- visual information
- visual content
- event detection
- test collection
- video data
- image retrieval
- key frames
- temporal information
- image database
- keywords
- image search
- video processing
- visual features
- video shots
- image classification
- information retrieval systems
- lecture videos
- low level