SALICON: Reducing the Semantic Gap in Saliency Prediction by Adapting Deep Neural Networks.
Xun HuangChengyao ShenXavier BoixQi ZhaoPublished in: ICCV (2015)
Keyphrases
- semantic gap
- neural network
- low level
- low level features
- video retrieval
- visual features
- semantic information
- multimedia databases
- image content
- semantic concepts
- visual content
- image annotation
- higher level
- high level semantics
- image representation
- information retrieval
- visual information
- video data
- domain knowledge
- multiscale
- high level
- multimedia