Deep Adaptively-Enhanced Hashing With Discriminative Similarity Guidance for Unsupervised Cross-Modal Retrieval.
Yufeng ShiYue ZhaoXin LiuFeng ZhengWeihua OuXinge YouQinmu PengPublished in: IEEE Trans. Circuits Syst. Video Technol. (2022)
Keyphrases
- cross modal
- visual similarity
- multi modal
- multimedia retrieval
- semi supervised
- discriminative features
- image retrieval
- multimedia databases
- semantic similarity
- similarity measure
- visual recognition
- visual data
- text retrieval
- visual information
- visual features
- video sequences
- visual content
- supervised learning
- feature selection
- low level features
- distance metric
- edit distance
- dissimilarity measure
- data points
- automatic image annotation
- data structure
- keywords
- high level