Multi Modal Fusion for Video Retrieval based on CLIP Guide Feature Alignment.
Guanfeng WuAbbas HaiderIvor T. A. SpenceHui WangPublished in: MVRMLM@ICMR (2024)
Keyphrases
- video retrieval
- video clips
- multi modal fusion
- key frames
- video segments
- visual content
- video database
- video indexing
- content based retrieval
- video data
- concept detection
- video search
- video shots
- video content
- semantic gap
- feature vectors
- video collections
- retrieval systems
- image and video retrieval
- interactive retrieval
- concept based video retrieval
- machine learning
- image features
- semantic video
- semantic video retrieval
- keywords