ConTra: (Con)text (Tra)nsformer for Cross-Modal Video Retrieval.
Adriano FragomeniMichael WrayDima DamenPublished in: ACCV (4) (2022)
Keyphrases
- video retrieval
- cross modal
- video search
- concept based video retrieval
- multi modal
- multimedia retrieval
- visual content
- content based retrieval
- retrieval systems
- semantic gap
- text retrieval
- video data
- multimedia databases
- video content
- key frames
- visual similarity
- video clips
- image retrieval
- visual data
- text mining
- semantic concepts
- semantic content
- computer vision
- keywords