HSVLT: Hierarchical Scale-Aware Vision-Language Transformer for Multi-Label Image Classification.
Shuyi OuyangHongyi WangZiwei NiuZhenjia BaiShiao XieYingying XuRuofeng TongYen-Wei ChenLanfen LinPublished in: ACM Multimedia (2023)
Keyphrases
- multi label
- image classification
- hierarchical text categorization
- multi label classification
- binary classification
- image representation
- image annotation
- feature extraction
- classifier training
- bag of words
- multi instance
- text categorization
- computer vision
- image features
- visual features
- multi label learning
- visual words
- text classification
- scene classification
- svm classifier
- max margin
- graph cuts
- neural network
- multiple labels
- protein function prediction
- label assignment
- image processing
- class labels
- data sets
- natural language processing
- natural language
- machine learning
- information retrieval
- data mining
- automatic image annotation
- feature vectors
- data analysis
- support vector
- decision trees