Deep Image Annotation and Classification by Fusing Multi-Modal Semantic Topics.
Yongheng ChenFuquan ZhangWanli ZuoPublished in: KSII Trans. Internet Inf. Syst. (2018)
Keyphrases
- multi modal
- image annotation
- image annotation and retrieval
- semantic concepts
- automatic image annotation
- multi label classification
- semantic gap
- image search
- image collections
- single modality
- image classification
- classification accuracy
- visual concepts
- web images
- fusing multiple
- decision trees
- visual features
- machine learning
- information retrieval
- visual similarity
- low level features
- high dimensional
- training set
- high level
- image understanding
- multi label
- supervised learning
- semi supervised
- feature space