FashionBERT: Text and Image Matching with Adaptive Loss for Cross-modal Retrieval.
Dehong GaoLinbo JinBen ChenMinghui QiuPeng LiYi WeiYi HuHao WangPublished in: CoRR (2020)
Keyphrases
- image matching
- cross modal
- image retrieval
- text retrieval
- multi modal
- multimedia retrieval
- information retrieval
- matching algorithm
- image database
- visual similarity
- multimedia databases
- relevance feedback
- object recognition
- image content
- keypoints
- visual features
- computer vision
- image registration
- image annotation
- multimedia information retrieval
- visual recognition
- information retrieval systems
- web images
- visual data
- text documents
- content based retrieval
- machine learning
- image set
- multimedia
- image segmentation
- retrieval systems
- image sequences
- feature extraction
- multiscale
- pattern recognition
- feature space