Generating Semantically Precise Scene Graphs from Textual Descriptions for Improved Image Retrieval.
Sebastian SchusterRanjay KrishnaAngel X. ChangLi Fei-FeiChristopher D. ManningPublished in: VL@EMNLP (2015)
Keyphrases
- image retrieval
- textual descriptions
- semantic information
- image database
- web images
- image search
- image sequences
- visual features
- video sequences
- image representation
- image content
- information retrieval
- visual content
- co occurrence
- bag of words
- visual words
- directed graph
- low level features
- image annotation
- relevance feedback
- semantic representation