R
Roee Litman
Researcher at Tel Aviv University
Publications - 34
Citations - 1602
Roee Litman is an academic researcher from Tel Aviv University. The author has contributed to research in topics: Shape analysis (digital geometry) & Benchmark (computing). The author has an hindex of 17, co-authored 34 publications receiving 1334 citations. Previous affiliations of Roee Litman include Technion – Israel Institute of Technology & Amazon.com.
Papers
More filters
Journal ArticleDOI
Learning Spectral Descriptors for Deformable Shape Correspondence
TL;DR: A learning scheme for the construction of optimized spectral descriptors is shown and related to Mahalanobis metric learning, which shows the superiority of the proposed approach in generating correspondences is demonstrated on synthetic and scanned human figures.
Proceedings ArticleDOI
Intrinsic shape context descriptors for deformable shapes
TL;DR: This work generalizes to surfaces the polar sampling of the image domain used in shape contexts and can leverage recent developments in intrinsic shape analysis and construct ISC based on state-of-the-art dense shape descriptors such as heat kernel signatures.
Proceedings ArticleDOI
SHREC 2011: robust feature detection and description benchmark
Edmond Boyer,Alexander M. Bronstein,Michael M. Bronstein,Benjamin Bustos,T. Darom,Radu Horaud,Ingrid Hotz,Yosi Keller,Johannes Keustermans,Artiom Kovnatsky,Roee Litman,Jan Reininghaus,Ivan Sipiran,Dirk Smeets,Paul Suetens,Dirk Vandermeulen,Andrei Zaharescu,Valentin Zobel +17 more
TL;DR: A benchmark that simulates the feature detection and description stages of feature-based shape retrieval algorithms under a wide variety of transformations is presented.
Proceedings ArticleDOI
Product Manifold Filter: Non-rigid Shape Correspondence via Kernel Density Estimation in the Product Space
TL;DR: This work derives the proposed recovery technique capable of guaranteeing a bijective correspondence and producing significantly higher accuracy and smoothness from the statistical framework of kernel density estimation and demonstrates its performance on several challenging deformable 3D shape matching datasets.
Proceedings ArticleDOI
SCATTER: Selective Context Attentional Scene Text Recognizer
TL;DR: A novel architecture for STR is introduced, named Selective Context ATtentional Text Recognizer (SCATTER), that utilizes a stacked block architecture with intermediate supervision during training, that paves the way to successfully train a deep BiLSTM encoder, thus improving the encoding of contextual dependencies.