Estimating Human Body Configurations Using Shape Context Matching

By Greg Mori, Jitendra Malik. European Conference on Computer Vision, 2002

480 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/9cc1b4ca121fef59517f24863b113bce3e5acd1a

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Human-Computer Interaction

Citations in the corpus

Articulated Human Detection with Flexible Mixtures of Parts (2013, methodology): “Past work has explored the use of superpixels [28], contours [26], [29], [30], foreground/ background color models [9], [7], edge-based descriptors [31], [32], and gradient descriptors [27], [33].”
MoDeep: A Deep Learning Framework Using Motion Features for Human Pose Estimation (2014, methodology): “Different architectures have since been proposed, including “shape-context” edge-based histograms from the human body [29, 30] or just silhouette features [31].”
Multiple Tree Models for Occlusion and Spatial Constraints in Human Pose Estimation (2008, background): “Mori & Malik [11] and Sullivan& Carlsson [19] address the pose estimation problems as 2D template matchin g us g pre-stored exemplars upon which joint locations have been marked.”
Learning to parse images of articulated bodies (2006, background): “Topdown approaches match an image to a set of templates spanning a range of body poses [17, 9, 19].”
Multi-source Deep Learning for Human Pose Estimation (2014, background): “Pose estimation is considered as holistic recognition in [14, 32, 33].”
Real-time human pose recognition in parts from single depth images (2011, methodology): “For training data, we generate realistic synthetic depth images of humans of many shapes and sizes in highly varied poses sampled from a large motion capture database.”
Synthesizing Training Images for Boosting Human 3D Pose Estimation (2016, background): “Most of the existing work in human pose estimation produces a set of 2D locations corresponding to the joints of an articulated human skeleton [33].”
Robust Optimization for Deep Regression (2015, background): “Unlike part-based models, holistic pose estimation approaches directly map image features to body poses [12, 28, 33].”
Shape context and chamfer matching in cluttered scenes (2003, background): “Shape context matching has been applied to a variety of object recognition problems [3] [15].”
Finding and tracking people from the bottom up (2003, background): “An attractive alternative is to ignore dynamics and find people in each frame independently, using such cues as local motion [15] or appearance [11].”
Efficient Human Pose Estimation from Single Depth Images (2013, methodology): “The shape context descriptor was used by Mori and Malik [33] to retrieve exemplars.”
Guiding model search using segmentation (2005, background): “Mori and Malik [6], and Sullivan and Carlsson [17] directly address the problem of pose estimation.”
Articulated Pose Estimation Using Discriminative Armlet Classifiers (2013, methodology): “Mori and Malik [16] matched whole body shapes of figures to exemplars using shape contexts and then transferred keypoint locations from exemplars to the test image.”
Recognizing action at a distance (2003, methodology): “The visual quality of our motion descriptor matching (see Figure 7) suggests that the method could be used in graphics for action synthesis, creating a novel video sequence of an actor by assembling frames of existing footage.”
Multi-task Recurrent Neural Network for Immediacy Prediction (2015, methodology): “Both holistic models [28, 11, 19, 20, 33] and local models [31, 8, 39, 6, 9, 30, 24, 10, 26, 14, 29, 35, 25, 1, 21, 4] were used for estimating the pose of a single person.”
Fast directional chamfer matching (2010, background): “As proposed in [13], we matched a gallery of human shapes with known poses to the given observation.”
SVM-KNN: Discriminative Nearest Neighbor Classification for Visual Category Recognition (2006, background): “[26]), or the SIFT descriptor([24]), or the geometric blur descriptor([4]).”
Tracking multiple humans in complex situations (2004, methodology): “Mori and Malik [27] also used recognition tohelp tracking.”