Video Sampled Frame Category Aggregation and Consistent Representation for Cross-Modal Retrieval.
Ming JinHuaxiang ZhangLei ZhuJiande SunLi LiuPublished in: IEEE Trans. Circuits Syst. Video Technol. (2023)
Keyphrases
- cross modal
- multi modal
- video frames
- multimedia retrieval
- visual data
- perceptual information
- multimedia databases
- video data
- multimedia
- video content
- image retrieval
- key frames
- visual recognition
- multimedia data
- semantic concepts
- video sequences
- visual similarity
- information retrieval
- document retrieval
- video clips
- video analysis
- language model
- video retrieval
- content based retrieval
- query processing
- low level
- object recognition
- space time
- image database
- visual features