LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval.
Siqi SunYen-Chun ChenLinjie LiShuohang WangYuwei FangJingjing LiuPublished in: NAACL-HLT (2021)
Keyphrases
- text retrieval
- image retrieval
- object retrieval
- low level
- image content
- information retrieval
- visually similar
- image features
- visual concepts
- visual features
- image representation
- document collections
- web images
- text queries
- visual information
- image regions
- retrieval model
- retrieval systems
- image collections
- image classification
- inverted file
- visual similarity
- relevant documents
- probabilistic model
- similarity measure
- medical image retrieval
- text representation
- multimedia