M3TR: Multi-modal Multi-label Recognition with Transformer.
Jiawei ZhaoYifan ZhaoJia LiPublished in: ACM Multimedia (2021)
Keyphrases
- multi modal
- multi label
- image annotation
- multi label classification
- text categorization
- image classification
- graph cuts
- multi label learning
- binary classification
- object recognition
- class labels
- automatic image annotation
- text classification
- multi modality
- action recognition
- feature extraction
- high dimensional
- semantic concepts
- learning algorithm
- label assignment
- image representation
- visual features
- multi class
- knn
- training data
- similarity measure