Imperial College London


Faculty of EngineeringDepartment of Computing

Chair in Machine Learning and Pattern Recognition



m.bronstein Website




569Huxley BuildingSouth Kensington Campus






BibTex format

author = {Bronstein, AM and Bronstein, MM and Guibas, LJ and Ovsjanikov, M},
doi = {10.1145/1899404.1899405},
journal = {ACM Transactions on Graphics},
title = {Shape google: Geometric words and expressions for invariant shape retrieval},
url = {},
volume = {30},
year = {2011}

RIS format (EndNote, RefMan)

AB - The computer vision and pattern recognition communities have recently witnessed a surge of feature-based methods in object recognition and image retrieval applications. These methods allow representing images as collections of "visual words" and treat them using text search approaches following the "bag of features" paradigm. In this article, we explore analogous approaches in the 3D world applied to the problem of nonrigid shape retrieval in large databases. Using multiscale diffusion heat kernels as "geometric words," we construct compact and informative shape descriptors by means of the "bag of features" approach. We also show that considering pairs of "geometric words" ("geometric expressions") allows creating spatially sensitive bags of features with better discriminative power. Finally, adopting metric learning approaches, we show that shapes can be efficiently represented as binary codes. Our approach achieves state-of-the-art results on the SHREC 2010 large-scale shape retrieval benchmark. © 2011 ACM.
AU - Bronstein,AM
AU - Bronstein,MM
AU - Guibas,LJ
AU - Ovsjanikov,M
DO - 10.1145/1899404.1899405
PY - 2011///
SN - 0730-0301
TI - Shape google: Geometric words and expressions for invariant shape retrieval
T2 - ACM Transactions on Graphics
UR -
VL - 30
ER -