Cross-modal fusion for multi-label image classification with attention mechanism.
Yangtao WangYanzhao XieJiangfeng ZengHanpin WangLisheng FanYufan SongPublished in: Comput. Electr. Eng. (2022)
Keyphrases
- multi label
- image classification
- cross modal
- multi modal
- image annotation
- multi label classification
- visual similarity
- visual features
- bag of words
- image features
- image retrieval
- image representation
- automatic image annotation
- feature extraction
- multimedia databases
- visual attention
- computer vision
- text categorization
- machine learning
- visual words
- scene classification
- low level
- video sequences
- multiscale