Self-Supervised Learning of Visual Features through Embedding Images into Text Topic Spaces.
Lluis Gomez-BigordaYash PatelMarçal RusiñolDimosthenis KaratzasC. V. JawaharPublished in: CVPR (2017)
Keyphrases
- visual features
- image classification
- image collections
- web images
- image annotation
- image retrieval
- visual appearance
- image search
- image data
- bridge the semantic gap
- low level visual features
- image features
- input image
- object recognition
- visual information
- visual patterns
- bag of features
- visual similarity
- image database
- visually similar
- text queries
- visual content
- visual data
- keywords
- semantic content
- labeled images
- global features
- information retrieval
- visual and textual features
- semantic gap
- semantic features
- computer vision
- low level features and high level
- multimedia
- visual descriptors
- visual attributes
- text mining
- keypoints
- image content
- cbir systems
- co occurrence
- sample images
- bag of words
- probabilistic latent semantic analysis
- textual features
- active learning
- textual information