From Captions to Visual Concepts and Back.
Hao FangSaurabh GuptaForrest N. IandolaRupesh Kumar SrivastavaLi DengPiotr DollárJianfeng GaoXiaodong HeMargaret MitchellJohn C. PlattC. Lawrence ZitnickGeoffrey ZweigPublished in: CoRR (2014)
Keyphrases
- visual concepts
- video content
- visual content
- visual features
- image collections
- image content
- semantic concepts
- visual information
- video data
- video streams
- video retrieval
- image annotation
- semantic gap
- learning tasks
- image retrieval
- key frames
- visual data
- low level
- video sequences
- image representation
- image classification
- low level features
- active learning
- keywords
- image data
- object recognition
- multi modal