Shape representation and classification using the Poisson equation

By Lena Gorelick, Meirav Galun, Eitan Sharon, Ronen Basri, Achi Brandt. Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004., 2004

312 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/7df998fefc9ceaa085f329ecb29bdf71e4794765

How researchers see this paper

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

Citations in the corpus

Geometrical Structure of Laplacian Eigenfunctions (2012, background): “for a reliable extraction of various shape properties of a silhouette, including part structure and rough skeleton, local orientation and aspect ratio of different parts, and convex and concave sections of the boundaries [209].”
Actions as space-time shapes (2005, unknown): “The isosurfaces of the solution U represent smoother versions of the Dirichlet bounding surface and are perpendicular to the Neumann bounding surfaces (first and last frames) [14].”
Event Detection in Crowded Videos (2007, background): “Similarly, the extensive research on generalizing shape matching [11, 17] requires reliable figure/ground separation, which is infeasible in crowded scenes using current segmentation techniques.”
Actions as Space-Time Shapes (2007, unknown): “The isosurfaces of the solution U represent smoother versions of the Dirichlet bounding surface and are perpendicular to the Neumann bounding surfaces (first and last frames) [14].”
Shape Classification Using the Inner-Distance (2007, background): “In contrast, the other two categories (e.g. [23], [4], [39], [41], [17], [30], etc.) capture part structures from only one image.”
On the Embeddability of Random Walk Distances (2013, background): “For example, work in computer vision [15] reliably extracts shape properties in Silhouettes using hitting time.”
Random Walks for Image Segmentation (2006, background): “More recently, the average hitting time of a random walk from an object boundary has been studied as a measure to characterize object shape [39].”
The wave kernel signature: A quantum mechanical approach to shape analysis (2011, methodology): “Precursors using the (Euclidean) Laplace operator in the interior of the shape were developed by Tari et al. [27] [26] and by Gorelick et al. [10].”