Incorporating Top-Down Guidance for Extracting Informative Patches for Image Classification.
Shuang BaiTetsuya MatsumotoYoshinori TakeuchiHiroaki KudoNoboru OhnishiPublished in: IEICE Trans. Inf. Syst. (2012)
Keyphrases
- image classification
- image representation
- visual features
- high level
- bag of words
- feature extraction
- multi label
- image features
- data sets
- natural images
- class specific
- data extraction
- image patches
- automatic extraction
- automatically extracting
- visual properties
- information content
- sparse coding
- vector quantization
- higher order
- object detection
- information systems
- machine learning