JIPS (한국정보처리학회)
Current Result Document :
| 한글제목(Korean Title) |
Convolutional Neural Network Based Multi-feature Fusion for Non-rigid 3D Model Retrieval |
| 영문제목(English Title) |
Convolutional Neural Network Based Multi-feature Fusion for Non-rigid 3D Model Retrieval |
| 저자(Author) |
Hui Zeng
Yanrong Liu
Siqi Li
JianYong Che
Xiuqing Wang
|
| 원문수록처(Citation) |
VOL 14 NO. 01 PP. 0176 ~ 0190 (2018. 02) |
한글내용
(Korean Abstract) |
|
영문내용
(English Abstract) |
This paper presents a novel convolutional neural network based multi-feature fusion learning method for nonrigid 3D model retrieval, which can investigate the useful discriminative information of the heat kernel signature (HKS) descriptor and the wave kernel signature (WKS) descriptor. At first, we compute the 2D shape distributions of the two kinds of descriptors to represent the 3D model and use them as the input to the networks. Then we construct two convolutional neural networks for the HKS distribution and the WKS distribution separately, and use the multi-feature fusion layer to connect them. The fusion layer not only can exploit more discriminative characteristics of the two descriptors, but also can complement the correlated information between the two kinds of descriptors. Furthermore, to further improve the performance of the description ability, the cross-connected layer is built to combine the low-level features with high-level features. Extensive experiments have validated the effectiveness of the designed multi-feature fusion learning method.
|
| 키워드(Keyword) |
Convolutional Neural Network
HKS
Multi-Feature Fusion
Non-rigid 3D Model
WKS
|
| 파일첨부 |
PDF 다운로드
|
