Deep Semantic Multimodal Hashing Network for Scalable Image-Text and Video-Text Retrievals.
Lu JinZechao LiJinhui TangPublished in: IEEE Trans. Neural Networks Learn. Syst. (2023)
Keyphrases
- semantic labels
- textual descriptions
- image representation
- image data
- input image
- text retrieval
- web images
- text information
- image content
- semantic information
- semantic content
- semantic representation
- multiscale
- multiple modalities
- single image
- information retrieval
- semantic representations
- low level features
- image retrieval
- rhetorical structure theory
- image regions
- text mining
- image features
- image collections
- linguistic analysis
- text detection
- semantic attributes
- video copy detection
- multimedia documents
- visual concepts
- semantic concepts
- video sequences
- image segmentation
- semantically related
- semantic features
- visual content
- key frames
- image classification
- keywords
- similarity measure
- arabic text
- multimedia