TeachText: CrossModal Generalized Distillation for Text-Video Retrieval.
Ioana CroitoruSimion-Vlad BogolinMarius LeordeanuHailin JinAndrew ZissermanSamuel AlbanieYang LiuPublished in: ICCV (2021)
Keyphrases
- video retrieval
- video search
- concept based video retrieval
- video collections
- video segments
- video database
- visual content
- semantic gap
- content based retrieval
- video content
- video data
- video indexing
- image and video retrieval
- key frames
- concept detection
- information retrieval
- retrieval systems
- video shots
- text mining
- video clips
- content based video retrieval
- text documents
- semantic content
- multimedia
- three dimensional
- video sequences
- multi modal
- image annotation