Human-like cognition: visual features grouping for hard-to-group text dataset.
Xin LiHangyuan LiuChunfeng TaoRuiyi HanShumin YangPublished in: J. Electronic Imaging (2024)
Keyphrases
- visual features
- keywords
- visual information
- human actions
- web images
- image retrieval
- visual content
- textual features
- semantic content
- image classification
- textual information
- image annotation
- text retrieval
- visual appearance
- low level
- low level features
- information retrieval
- text documents
- bag of features
- image search
- video shots
- semantic gap
- low level visual features
- semantic features
- visual and textual features
- text data
- text mining
- object recognition
- low level features and high level
- image collections
- semantic information
- wordnet
- visual similarity
- face recognition
- image processing
- text queries
- bridge the semantic gap
- search engine