A Bayesian, Exemplar-Based Approach to Hierarchical Shape Matching

By Dariu M. Gavrila. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007

309 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Ocean Engineering

View Paper: https://www.semanticscholar.org/paper/c1d6d01b2b392d99b1903334023784b60067f840

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 Ocean Engineering

Citations in the corpus

3D Traffic Scene Understanding From Movable Platforms (2014, unknown): “Conclusions are drawn in Section 6.”
Monocular Pedestrian Detection: Survey and Experiments (2009, background): “Discrete approaches represent the shape manifold by a set of exemplar shapes [22], [23], [67], [70].”
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].”
The Shape Boltzmann Machine: A Strong Model of Object Shape (2012, methodology): “Non-parametric approaches employ what is effectively a large database of template shapes [12] or shape fragments [3, 15].”
Access to Unlabeled Data can Speed up Prediction Time (2011, background): “The second hypothesis class, denoted H , is a kernelbased linear predictor with the kernel function being a Chamfer distance between images (Barrow et al., 1977; Felzenszwalb & Huttenlocher, 2004; Gavrila, 2007).”
Pedestrian Detection: An Evaluation of the State of the Art (2012, methodology): “Gavrila and Philomin [49], [50] employed the Hausdorff distance transform and a template hierarchy to rapidly match image edges to a set of shape templates.”
D Traffic Scene Understanding from Movable Platforms (2013, background): “For a long time, dynamic objects have been considered either in isolation [5], [26], [27], [52] or using simple motion [9], [23], [42], [47], [63] or social interaction [15], [62] models.”
Virtual and Real World Adaptation for Pedestrian Detection (2014, methodology): “using dense descriptors [1], [2], [4], or the pedestrian silhouette [19].”
Multi-cue onboard pedestrian detection (2009, background): “Gavrila [15] proposes a tree-structured Bayesian approach that builds on ofﬂine clustering of pedestrian shapes.”
Exemplar-based Action Recognition in Video (2009, methodology): “Figure 1: An illustration of the detection pipeline for the ‘drinking’ action: (1) a frame from the input video, (2) spatio-temporal features are computed throughout the video, (3) exemplar-based hypotheses are generated and scored, (4) a grouping algorithm yields two distinct detections.”
Multi-view 3D Human Pose Estimation in Complex Environment (2011, methodology): “For the root l = 1 up to level L∗, we will construct the tree by appearance-based grouping using the chamfer distance (Gavrila 2007).”
Voting-based pose estimation for robotic assembly using a 3D sensor (2012, methodology): “Following the seminal paper on chamfer distance [5], there were several useful variants that incorporate edge orientation [6], [7] or employ hierarchical representation [8].”