Face, Body, Voice: Video Person-Clustering with Multiple Modalities.
Andrew BrownVicky KalogeitonAndrew ZissermanPublished in: ICCVW (2021)
Keyphrases
- multiple modalities
- multi modal
- imaging modalities
- multimedia
- multimedia data
- video search
- video sequences
- visual cues
- cross modal
- video data
- human body
- medical images
- high dimensional data
- video frames
- video streams
- low level features
- face images
- facial expressions
- gray level
- video content
- video retrieval
- video analysis