Title | Computing importance of 2D contour parts by reconstructability |
Authors | Guo, Ge Wang, Yizhou Jiang, Tingting Yuille, Alan Gao, Wen |
Affiliation | Key Lab of Intelligent Information Processing of CAS, Institute of Computing Technology, CAS, Beijing 100190, China Nat'l Eng. Lab for Video Technology, Sch'l of EECS, Peking University, Beijing 100871, China Graduate University of Chinese Academy of Sciences, Beijing 100039, China Department of Statistics, University of California, Los Angeles, CA 90095-1554, United States |
Issue Date | 2011 |
Citation | 2011 IEEE International Conference on Computer Vision Workshops, ICCV Workshops 2011.Barcelona, Spain. |
Abstract | Part-based representation has become an essential representation for objects. Different parts of a shape have various importance to shape perception. Concerned by the contributions of local parts to the perception of global shapes, we introduce an importance measure of shape parts from the viewpoint of their reconstructability. Given one shape part as a local observation, we estimate the global object shapes through a proposed novel shape reconstruction method. The reconstruction quality is determined by part geometry variation and part uniqueness. Then a conditional entropy formulation is introduced to measure the part importance considering the reconstruction quality, part uniqueness and variation. Extensive experiments demonstrate the benefit of the proposed part importance to object detection applications. Moreover, psychological experiments are conducted to further support the consistency of our importance measure with human perception towards shape parts. ? 2011 IEEE. |
URI | http://hdl.handle.net/20.500.11897/328583 |
DOI | 10.1109/ICCVW.2011.6130410 |
Indexed | EI |
Appears in Collections: | 信息科学技术学院 |