nips nips2008 nips2008-207 nips2008-207-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Geremy Heitz, Gal Elidan, Benjamin Packer, Daphne Koller
Abstract: Discriminative tasks, including object categorization and detection, are central components of high-level computer vision. Sometimes, however, we are interested in more refined aspects of the object in an image, such as pose or particular regions. In this paper we develop a method (LOOPS) for learning a shape and image feature model that can be trained on a particular object class, and used to outline instances of the class in novel images. Furthermore, while the training data consists of uncorresponded outlines, the resulting LOOPS model contains a set of landmark points that appear consistently across instances, and can be accurately localized in an image. Our model achieves state-of-the-art results in precisely outlining objects that exhibit large deformations and articulations in cluttered natural images. These localizations can then be used to address a range of tasks, including descriptive classification, search, and clustering. 1
[1] D. Anguelov, P. Srinivasan, D. Koller, S. Thrun, J. Rodgers, and J. Davis. Scape: shape completion and animation of people. SIGGRAPH, ’05. 3
[2] A. Bar-Hillel, T. Hertz, D. Weinshall. Efficient learning of relational object class models. ICCV, ’05. 2
[3] A. Berg, T. Berg, and J. Malik. Shape matching and object recognition using low distortion correspondence. CVPR, ’05. 2, 8
[4] T. Cootes, G. Edwards, and C. Taylor. Active appearance models. ECCV, ’98. 1, 2, 3, 4
[5] G. Elidan, G. Heitz, and D. Koller. Learning object shape: From cartoons to images. CVPR, ’06. 3
[6] G. Elidan, I. McGraw, and D. Koller. Residual belief propagation: Informed scheduling for async. message passing. UAI, ’06. 4
[7] L. Fei-Fei and P. Perona. A bayesian hier. model for learning natural scene categories. CVPR, ’05. 6
[8] L. Fei-Fei, R. Fergus, and P. Perona. Learning generative visual models from few training examples: an incremental bayesian approach tested on 101 object categories. CVPR, ’04. 4, 7
[9] P. Felzenszwalb and D. Huttenlocher. Efficient matching of pictorial structures. CVPR, ’00. 1
[10] P. Felzenszwalb and J. Schwartz. Hierarchical matching of deformable shapes. CVPR, ’07.
[11] R. Fergus, P. Perona, and A. Zisserman. Object class recognition by unsupervised scale-invariant learning. CVPR, ’03. 2
[12] V. Ferrari, F. Jurie, and C. Schmid. Accurate object detection with deformable shape models learnt from images. CVPR, ’07. 2, 5, 8
[13] G. Heitz, G. Elidan, B. Packer, and D. Koller. Shape-based object localization for descriptive classification. Technical report, available at http://ai.stanford.edu/˜gaheitz/Research/Loops/TR.pdf 4
[14] A. Hill and C. Taylor. Non-rigid corresp. for automatic landmark identification. BMVC, ’96. 2
[15] A. Holub and P. Perona. A discriminative framework for modeling object class. CVPR, ’05.
[16] D. Lowe. Distinctive image features from scale-invariant keypoints. IJCV, ’03. 3, 4
[17] A. Opelt, A. Pinz, and A. Zisserman. Incremental learning of object detectors using a visual shape alphabet. CVPR, ’06. 2, 3, 8
[18] J. Pearl. Probabilistic Reasoning in Intelligent Systems. Morgan Kaufmann, ’88. 3
[19] M. Prasad and A. Fitzgibbon. Single view reconstruction of curved surfaces. CVPR 2006, ’06. 5, 8
[20] J. Sethian. Level Set Methods and Fast Marching Methods. Cambridge, ’98. 2
[21] J. Shotton, A. Blake, and R. Cipolla. Contour-based learning for object detection. ICCV, ’05. 2, 8
[22] A. Torralba, K. Murphy, and W. Freeman. Contextual models for object detection using boosted random fields. NIPS, ’05. 3, 6 8