Hierarchical Matching of Deformable Shapes
By Pedro F. Felzenszwalb, Joshua D. Schwartz. 2007 IEEE Conference on Computer Vision and Pattern Recognition, 2007
382 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/d49689f92f22c055cc8dc391818f5ca415ee2ef4
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
- Luc Van Gool
- Xiaogang Wang
- Ming-Hsuan Yang
- Dacheng Tao
- Trevor Darrell
- Jitendra Malik
- Yi Yang
- Kristen Grauman
Citations in the corpus
- Shape discovery from unlabeled image collections (2009, background): “Spectral clustering from the initial affinities provides candidate object clusters.”
- Action Recognition with Image Based CNN Features (2015, methodology): “This idea was first used by [5] to describe curves and shapes in a coarse to fine fashion.”
- Active skeleton for non-rigid object detection (2009, methodology): “This makes the algorithm simpler and more computationally efficient than other methods using dynamic programming [33], belief propagation [13], or MCMC [35].”
- Correlating fourier descriptors of local patches for road sign recognition (2011, methodology): “Nowadays, there are more robust (with respect to global occlusion and non-rigid deformations) but also computationally more expensive methods for comparing the global outlines of objects [5, 6, 7].”
- CENTRIST: A Visual Descriptor for Scene Categorization (2011, methodology): “This data set has been used to evaluate shape matching methods [31], [32], in which the contour of leaves (instead of the gray scale or color leaf picture) were used as input.”
- Learning Context-Sensitive Shape Similarity by Graph Transduction (2010, methodology): “From the retrieval rates collected in Table 1, we can clearly observe that our method made a significant progress on this database, and the second highest result is 87.70 percent obtained by Shape Tree [8].”
- Fast directional chamfer matching (2010, methodology): “In [7], a hierarchical object contour representation was proposed together with a dynamic programming approach for matching.”