Shape matching and object recognition using low distortion correspondences

By Alexander C. Berg, Tamara L. Berg, Jitendra Malik. 2005

1,030 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Character Recognition in Natural Images (2009, background): “Geometric Blur (GB) ( Berg et al., 2005 ) is a feature extractor with a sampling method similar to that of SC, but instead of histogramming points, the region around an interest point is blurred according to the distance from this point.”
SIFT Flow: Dense Correspondence across Scenes and Its Applications (2011, methodology): “Jenny Yuen and Antonio Torralba are with the Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139.”
3D generic object categorization, localization and pose estimation (2007, background): “A matching scheme such as in [1] is also possible.”
Groups of Adjacent Contour Segments for Object Detection (2008, background): “of its edgels Ps ∈ [0, 1 ]. We experimentally observed a considerable improvement over treating”
Scalable Recognition with a Vocabulary Tree (2006, background): “represent an object with descriptors extracted from these local regions [1, 2 , 8, 11, 15, 16, 18].”
Learning to place new objects in a scene (2012, background): “Early work (e.g., Winn et al., 2005; Leibe et al., 2004; Fergus et al., 2003; Berg et al., 2005) tried to solve shape and orientation variability, limited by a single viewpoint.”
Feature Correspondence Via Graph Matching: Models and Global Optimization (2008, positive): “Our approach is most closely related to the work of Berg et al. [ 17 ], and Leordeanu and Hebert [18], who formulate visual correspondence as a graph matching problem by defining an objective including t erms based on appearance similarity as well as geometric compatibility between pairs of correspo”
Image Classification using Random Forests and Ferns (2007, methodology): “This problem has been the subject of many recent papers [14, 15, 16, 26 , 27] using the Pascal Visual Object Classes datasets or the Caltech-101 dataset.”
Unsupervised Learning of Categories from Sets of Partially Matching Image Features (2006, background): “The authors of [2] introduced a powerful recognition algorithm that uses linear programming to solve for approximate correspondences, and they showed how to use the correspondence-based metric to find regions of common spatial support for objects in labeled training examples, thus avoiding the need ”
Shape discovery from unlabeled image collections (2009, background): “The success of recently developed shape matching algorithmsandadvancesin shape descriptors[1, 2 , 25, 10, 21, 7] are promising signs for using shape to recognize and detect objects.”
An Integer Projected Fixed Point Method for Graph Matching and MAP Inference (2009, neutral): “It is a generalization of the classical graph matching problem, formulated as an integer quadratic program [1,3,4,5,7,8,16,17] that takes into consideration both unary and second-order terms reflecting the similarities in local appearance”
Pedestrian Detection via Classification on Riemannian Manifolds (2008, methodology): “Several object detection algorithms were proposed by assembling the detected parts according to spatial relationships in probabilistic frameworks [12], [52], by discriminative approaches [1], [32], or via matching shapes [ 4 ], [24].”
Image Based Localization in Urban Environments (2006, background): “Although in object recognition the true correspondences are often not essential they have been shown to improve recognition [1].”