GMMFormer: Gaussian-Mixture-Model Based Transformer for Efficient Partially Relevant Video Retrieval.
Yuting WangJinpeng WangBin ChenZiyun ZengShu-Tao XiaPublished in: AAAI (2024)
Keyphrases
- video retrieval
- visual content
- semantic gap
- content based retrieval
- video search
- video data
- retrieval systems
- video indexing
- key frames
- video shots
- video database
- concept based video retrieval
- concept detection
- video content
- interactive retrieval
- semantic concept detection
- video clips
- mixture model
- video sequences
- face recognition
- multimedia
- computer vision