loading
Papers

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Harald Grabner 1 ; Torsten Ullrich 1 and Dieter W. Fellner 2

Affiliations: 1 Institute of Computer Graphics and Knowledge Visualization (CGV) and Technische Universität Graz, Austria ; 2 Technische Universität Darmstadt & Fraunhofer IGD, Institute of Computer Graphics and Knowledge Visualization (CGV) and Technische Universität Graz, Germany

ISBN: 978-989-758-087-1

Keyword(s): Generative Modeling, Procedural Modeling, 3D-Retrieval, Machine Learning.

Related Ontology Subjects/Areas/Topics: Computer Vision, Visualization and Computer Graphics ; Fundamental Methods and Algorithms ; Geometric Computing ; Geometry and Modeling ; Modeling and Algorithms ; Scene and Object Modeling

Abstract: A digital library for non-textual, multimedia documents can be defined by its functionality: markup, indexing, and retrieval. For textual documents, the techniques and algorithms to perform these tasks are well studied. For non-textual documents, these tasks are open research questions: How to markup a position on a digitized statue? What is the index of a building? How to search and query for a CAD model? If no additional, textual information is available, current approaches cluster, sort and classify non-textual documents using machine learning techniques, which have a cold start problem: they either need a manually labeled, sufficiently large training set or the (automatic) clustering / classification result may not respect semantic similarity. We solve this problem using procedural modeling techniques, which can generate arbitrary training sets without the need of any “real” data. The retrieval process itself can be performed with any method. In this article we describe the histog ram of inverted distances in detail and compare it to salient local visual features method. Both techniques are evaluated using the Princeton Shape Benchmark (Shilane et al., 2004). Furthermore, we improve the retrieval results by diffusion processes. (More)

PDF ImageFull Text

Download
CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.215.182.36

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Grabner, H.; Ullrich, T. and W. Fellner, D. (2015). Generative Training for 3D-Retrieval.In Proceedings of the 10th International Conference on Computer Graphics Theory and Applications - Volume 1: GRAPP, (VISIGRAPP 2015) ISBN 978-989-758-087-1, pages 97-105. DOI: 10.5220/0005248300970105

@conference{grapp15,
author={Harald Grabner. and Torsten Ullrich. and Dieter W. Fellner.},
title={Generative Training for 3D-Retrieval},
booktitle={Proceedings of the 10th International Conference on Computer Graphics Theory and Applications - Volume 1: GRAPP, (VISIGRAPP 2015)},
year={2015},
pages={97-105},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005248300970105},
isbn={978-989-758-087-1},
}

TY - CONF

JO - Proceedings of the 10th International Conference on Computer Graphics Theory and Applications - Volume 1: GRAPP, (VISIGRAPP 2015)
TI - Generative Training for 3D-Retrieval
SN - 978-989-758-087-1
AU - Grabner, H.
AU - Ullrich, T.
AU - W. Fellner, D.
PY - 2015
SP - 97
EP - 105
DO - 10.5220/0005248300970105

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.