2011.11.04-稀疏表示跟图像视频标注.pptVIP

稀疏表示与图像视频标注 lihaojie yilei 2011年11月4日 1 Sparsity A signal is sparse if most of its coefficients are (approximately) zero 1. Nonparametric Label-to-Region by Search Xiaobai Liu, Shuicheng Yan, Jiebo Luo, Jinhui Tang, Zhongyang Huang and Hai Jin CVPR 2010 2. Sparse Ensemble Learning for Concept Detection Sheng Tang, Yan-Tao Zheng, Yu Wang, Tat-Seng Chua IEEE Trans. on Multimedia, 2012 4 Nonparametric Label-to-Region by Search Label-to-Region, L2R propagate annotated labels for a given single image from the image-level to their corresponding semantic regions 5 L2R In CV, known as simultaneous object recognition and image segmentation Unsupervised learning methods object localization: image segmentation along with object classification multi-label image segmentation and classification can only handle images either with single major object or with clean background and without occlusions between objects Supervised learning methods, i.e., classifier-based methods, which usually first learn image classifiers to characterize concepts (or keywords) based on the training images, and then identify the images belonging to the specific category E.g., CMRM 6 L2R by Search--Overview Each label of the image is used as query for online image search engines to obtain a set of semantically related and visually similar images Segment both input image and online images returned from image search engine into local atomic image patches to obtain the so-called bag-of-patches (BOP) representation A label-specific feature mining procedure is employed for each label to discover distinctive and descriptive features from the proposed Interpolation SIFT (iSIFT) feature pool. These features are used to discover the patch level label-specific representations 7 L2R by Search--Overview Construct the candidate regions The continuity-biased sparsity prior is introduced to select a small number of patches from the online images with preference to larger patches Use a sparse coding formulation to