Progressive shape-distribution-encoder for 3D shape retrieval

Jin Xie, Fan Zhu, Guoxian Dai, Yi Fang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we propose a deep shape descriptor by learning the shape distributions at different diffusion time via a progressive deep shape-distribution-encoder. First, we develop a shape distribution representation with the kernel density estimator to characterize the intrinsic geometrical structure of the shape. Then, we propose to learn discriminative shape features through a progressive shapedistribution-encoder. Specially, the progressive shape-distributionencoder aims at modeling the complex non-linear transform of the estimated shape distributions between consecutive diffusion time. Furthermore, in order to characterize the intrinsic structure of the shape more efficiently, we stack multiple proposed progressive shapedistribution-encoders to form a neural network structure. Finally, we concatenated all neurons in the hidden layers of the progressive shape-distribution-encoder network to form a discriminative shape descriptor for retrieval. The proposed method is evaluated on three benchmark 3D shape datasets and the experimental results demonstrate the superiority of our method to the existing approaches.

Original languageEnglish (US)
Title of host publicationMM 2015 - Proceedings of the 2015 ACM Multimedia Conference
PublisherAssociation for Computing Machinery, Inc
Pages1167-1170
Number of pages4
ISBN (Electronic)9781450334594
DOIs
StatePublished - Oct 13 2015
Event23rd ACM International Conference on Multimedia, MM 2015 - Brisbane, Australia
Duration: Oct 26 2015Oct 30 2015

Other

Other23rd ACM International Conference on Multimedia, MM 2015
CountryAustralia
CityBrisbane
Period10/26/1510/30/15

Fingerprint

Electric power distribution
Neurons
Neural networks

Keywords

  • 3D shape retrieval
  • Denoising Auto-Encoder
  • Heat Diffusion
  • Heat Kernel Signature

ASJC Scopus subject areas

  • Media Technology
  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Software

Cite this

Xie, J., Zhu, F., Dai, G., & Fang, Y. (2015). Progressive shape-distribution-encoder for 3D shape retrieval. In MM 2015 - Proceedings of the 2015 ACM Multimedia Conference (pp. 1167-1170). Association for Computing Machinery, Inc. https://doi.org/10.1145/2733373.2806308

Progressive shape-distribution-encoder for 3D shape retrieval. / Xie, Jin; Zhu, Fan; Dai, Guoxian; Fang, Yi.

MM 2015 - Proceedings of the 2015 ACM Multimedia Conference. Association for Computing Machinery, Inc, 2015. p. 1167-1170.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Xie, J, Zhu, F, Dai, G & Fang, Y 2015, Progressive shape-distribution-encoder for 3D shape retrieval. in MM 2015 - Proceedings of the 2015 ACM Multimedia Conference. Association for Computing Machinery, Inc, pp. 1167-1170, 23rd ACM International Conference on Multimedia, MM 2015, Brisbane, Australia, 10/26/15. https://doi.org/10.1145/2733373.2806308
Xie J, Zhu F, Dai G, Fang Y. Progressive shape-distribution-encoder for 3D shape retrieval. In MM 2015 - Proceedings of the 2015 ACM Multimedia Conference. Association for Computing Machinery, Inc. 2015. p. 1167-1170 https://doi.org/10.1145/2733373.2806308
Xie, Jin ; Zhu, Fan ; Dai, Guoxian ; Fang, Yi. / Progressive shape-distribution-encoder for 3D shape retrieval. MM 2015 - Proceedings of the 2015 ACM Multimedia Conference. Association for Computing Machinery, Inc, 2015. pp. 1167-1170
@inproceedings{d9f51ea344ff4dd78d5a1bb1de6ab6b4,
title = "Progressive shape-distribution-encoder for 3D shape retrieval",
abstract = "In this paper, we propose a deep shape descriptor by learning the shape distributions at different diffusion time via a progressive deep shape-distribution-encoder. First, we develop a shape distribution representation with the kernel density estimator to characterize the intrinsic geometrical structure of the shape. Then, we propose to learn discriminative shape features through a progressive shapedistribution-encoder. Specially, the progressive shape-distributionencoder aims at modeling the complex non-linear transform of the estimated shape distributions between consecutive diffusion time. Furthermore, in order to characterize the intrinsic structure of the shape more efficiently, we stack multiple proposed progressive shapedistribution-encoders to form a neural network structure. Finally, we concatenated all neurons in the hidden layers of the progressive shape-distribution-encoder network to form a discriminative shape descriptor for retrieval. The proposed method is evaluated on three benchmark 3D shape datasets and the experimental results demonstrate the superiority of our method to the existing approaches.",
keywords = "3D shape retrieval, Denoising Auto-Encoder, Heat Diffusion, Heat Kernel Signature",
author = "Jin Xie and Fan Zhu and Guoxian Dai and Yi Fang",
year = "2015",
month = "10",
day = "13",
doi = "10.1145/2733373.2806308",
language = "English (US)",
pages = "1167--1170",
booktitle = "MM 2015 - Proceedings of the 2015 ACM Multimedia Conference",
publisher = "Association for Computing Machinery, Inc",

}

TY - GEN

T1 - Progressive shape-distribution-encoder for 3D shape retrieval

AU - Xie, Jin

AU - Zhu, Fan

AU - Dai, Guoxian

AU - Fang, Yi

PY - 2015/10/13

Y1 - 2015/10/13

N2 - In this paper, we propose a deep shape descriptor by learning the shape distributions at different diffusion time via a progressive deep shape-distribution-encoder. First, we develop a shape distribution representation with the kernel density estimator to characterize the intrinsic geometrical structure of the shape. Then, we propose to learn discriminative shape features through a progressive shapedistribution-encoder. Specially, the progressive shape-distributionencoder aims at modeling the complex non-linear transform of the estimated shape distributions between consecutive diffusion time. Furthermore, in order to characterize the intrinsic structure of the shape more efficiently, we stack multiple proposed progressive shapedistribution-encoders to form a neural network structure. Finally, we concatenated all neurons in the hidden layers of the progressive shape-distribution-encoder network to form a discriminative shape descriptor for retrieval. The proposed method is evaluated on three benchmark 3D shape datasets and the experimental results demonstrate the superiority of our method to the existing approaches.

AB - In this paper, we propose a deep shape descriptor by learning the shape distributions at different diffusion time via a progressive deep shape-distribution-encoder. First, we develop a shape distribution representation with the kernel density estimator to characterize the intrinsic geometrical structure of the shape. Then, we propose to learn discriminative shape features through a progressive shapedistribution-encoder. Specially, the progressive shape-distributionencoder aims at modeling the complex non-linear transform of the estimated shape distributions between consecutive diffusion time. Furthermore, in order to characterize the intrinsic structure of the shape more efficiently, we stack multiple proposed progressive shapedistribution-encoders to form a neural network structure. Finally, we concatenated all neurons in the hidden layers of the progressive shape-distribution-encoder network to form a discriminative shape descriptor for retrieval. The proposed method is evaluated on three benchmark 3D shape datasets and the experimental results demonstrate the superiority of our method to the existing approaches.

KW - 3D shape retrieval

KW - Denoising Auto-Encoder

KW - Heat Diffusion

KW - Heat Kernel Signature

UR - http://www.scopus.com/inward/record.url?scp=84962916582&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84962916582&partnerID=8YFLogxK

U2 - 10.1145/2733373.2806308

DO - 10.1145/2733373.2806308

M3 - Conference contribution

AN - SCOPUS:84962916582

SP - 1167

EP - 1170

BT - MM 2015 - Proceedings of the 2015 ACM Multimedia Conference

PB - Association for Computing Machinery, Inc

ER -