Predicting Visual Features From Text for Image and Video Caption Retrieval.
Jianfeng DongXirong LiCees G. M. SnoekPublished in: IEEE Trans. Multim. (2018)
Keyphrases
- visual features
- image retrieval
- text queries
- web images
- image classification
- visual descriptors
- visual and textual features
- key frames
- low level visual features
- image collections
- visual similarity
- visual appearance
- content based video retrieval
- visual information
- visual data
- visual content
- semantic content
- image search
- semantic concepts
- image similarity
- low level features and high level
- semantic gap
- keywords
- textual descriptions
- text retrieval
- image content
- global features
- video shots
- visually similar
- low level features
- cbir systems
- news video
- color histogram
- image annotation
- labeled images
- low level
- image database
- bag of features
- video retrieval
- video database
- multimedia documents
- image features
- textual information
- image representation
- caption text
- visual patterns
- visual concepts
- image data
- relevance feedback
- text information
- audio features
- information retrieval
- input image
- news stories
- content based retrieval
- video clips
- object recognition
- multimedia
- multimedia data
- video frames
- feature selection