Beyond local image features: Scene calssification using supervised semantic representation

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 图像与视频分析团队

	Beyond local image features: Scene calssification using supervised semantic representation
	Chunjie Zhang; Jing Liu; Chao Liang; Jinhui Tang; Hanqing Lu
	2012
会议日期	September 30 - October 3, 2012
会议地点	Lake Buena Vista, Orlando, FL, USA
关键词	Semantic Representation Scene Classification Sparse Supervised Learning
英文摘要	The use of local features for image representation has been proven very effective for a variety of visual tasks such as object localization and scene classification. However, local image features carry little semantic information which is potentially not enough for high level visual tasks. To solve this problem, in this paper, we propose to use a supervised semantic image representation for scene classification, where an image is represented as a response histogram. This response histogram is a combination of the prediction of pre-trained generic object classifiers and classifiers generated by supervised learning. Besides, the use of sparsity constraints makes the proposed representation more efficient and effective to compute. Performances on the UIUC-Sports dataset, the MIT Indoor scene dataset and the Scene-15 dataset demonstrate the effectiveness of the proposed method.
会议录	无
内容类型	会议论文
源URL	[http://ir.ia.ac.cn/handle/173211/13448]
专题	自动化研究所_模式识别国家重点实验室_图像与视频分析团队
通讯作者	Jing Liu
推荐引用方式 GB/T 7714	Chunjie Zhang,Jing Liu,Chao Liang,et al. Beyond local image features: Scene calssification using supervised semantic representation[C]. 见:. Lake Buena Vista, Orlando, FL, USA. September 30 - October 3, 2012.