Predicting Visual Features from Text for Image and Video Caption Retrieval.
Jianfeng DongXirong LiCees G. M. SnoekPublished in: CoRR (2017)
Keyphrases
- visual features
- image retrieval
- text queries
- web images
- image classification
- key frames
- image collections
- visual and textual features
- low level visual features
- visual similarity
- visual descriptors
- visual appearance
- visual data
- content based video retrieval
- visual information
- semantic concepts
- visual content
- image similarity
- textual descriptions
- low level features and high level
- semantic gap
- video shots
- semantic content
- keywords
- image search
- text retrieval
- image annotation
- low level
- low level features
- news video
- global features
- color histogram
- bag of features
- labeled images
- image representation
- visually similar
- image content
- visual concepts
- image features
- text information
- cbir systems
- video retrieval
- information retrieval
- image database
- textual information
- video database
- multimedia
- caption text
- video data
- video clips
- video sequences
- textual features
- retrieval systems
- image data
- relevance feedback
- multimedia documents
- video content
- feature extraction
- content based retrieval
- multimedia data
- video frames
- visual patterns
- high level
- bag of words