Deep learning based audio and video cross-modal recommendation.
Yun TieXiaobing LiTian ZhangCong JinXin ZhaoChu Jie Jiessie TiePublished in: SMC (2022)
Keyphrases
- cross modal
- deep learning
- visual data
- multi modal
- unsupervised learning
- video sequences
- multimedia retrieval
- multimedia
- semantic concepts
- video data
- machine learning
- mental models
- video frames
- video content
- visual information
- multimedia databases
- image retrieval
- multimedia data
- key frames
- weakly supervised
- image data
- computer vision
- video retrieval
- visual features
- object detection
- similarity measure