Frame- and Segment-Level Features and Candidate Pool Evaluation for Video Caption Generation.
Rakshith ShettyJorma LaaksonenPublished in: ACM Multimedia (2016)
Keyphrases
- key frames
- video retrieval
- video frames
- video segments
- caption text
- feature vectors
- video data
- video clips
- video images
- feature extraction
- temporal coherence
- single frame
- video streams
- visual features
- co occurrence
- video sequences
- multimedia
- low level features
- spatial and temporal
- news video
- image features
- temporal structure
- input video
- temporal continuity