Rec: Cross-Modal Context Enhanced Micro-Video Recommendation with Mutual Information Maximization.
Qihan DuLi YuHuiyuan LiNingrui OuXinjing GongJunyao XiangPublished in: ICME (2022)
Keyphrases
- cross modal
- multi modal
- multimedia
- visual data
- mutual information maximization
- video sequences
- contextual information
- video data
- multimedia retrieval
- context aware
- video frames
- multimedia databases
- multiple modalities
- video streams
- visual recognition
- mutual information
- multimedia data
- video content
- video retrieval
- image segmentation
- machine learning