Towards Efficient and Effective Text-to-Video Retrieval with Coarse-to-Fine Visual Representation Learning.
Kaibin TianYanhua ChengYi LiuXinglin HouQuan ChenHan LiPublished in: AAAI (2024)
Keyphrases
- coarse to fine
- video retrieval
- visual representation
- video collections
- learning process
- multiresolution
- object detection
- keywords
- video data
- learning algorithm
- retrieval systems
- user interface
- dynamic programming
- semantic gap
- concept based video retrieval
- concept detection
- content based video retrieval
- hierarchical segmentation
- machine learning
- video shots
- object recognition
- similarity measure
- high level
- multimedia
- computer vision
- information retrieval