Fine-grained Text-Video Retrieval with Frozen Image Encoders.
Zuozhuo DaiFangtao ShaoQingkun SuZilong DongSiyu ZhuPublished in: CoRR (2023)
Keyphrases
- fine grained
- video retrieval
- semantic gap
- content based image
- coarse grained
- key frames
- video search
- image data
- concept based video retrieval
- video collections
- image content
- image features
- image classification
- content based retrieval
- access control
- video data
- image retrieval
- web images
- visual content
- video shots
- video clips
- image regions
- image collections
- retrieval systems
- databases
- semantic information
- image representation
- image database
- low level
- image segmentation
- text documents
- information retrieval systems
- feature vectors
- video sequences
- similarity measure