UM  > 科技學院  > 電腦及資訊科學系
Deep Spatiality: Unsupervised Learning of Spatially-Enhanced Global and Local 3D Features by Deep Neural Network with Coupled Softmax
Han Z.3; Liu Z.1; Vong C.-M.2; Liu Y.-S.3; Bu S.1; Han J.1; Chen C.L.P.2
2018-06-01
Source PublicationIEEE Transactions on Image Processing
ISSN10577149
Volume27Issue:6Pages:3049-3063
Abstract

The discriminability of the bag-of-words representations can be increased via encoding the spatial relationship among virtual words on 3D shapes. However, this encoding task involves several issues, including arbitrary mesh resolutions, irregular vertex topology, orientation ambiguity on 3D surface, invariance to rigid, and non-rigid shape transformations. To address these issues, a novel unsupervised spatial learning framework based on deep neural network, deep spatiality (DS), is proposed. Specifically, DS employs two novel components: spatial context extractor and deep context learner. Spatial context extractor extracts the spatial relationship among virtual words in a local region into a raw spatial representation. Along a consistent circular direction, a directed circular graph is constructed to encode relative positions between pairwise virtual words in each face ring into a relative spatial matrix. By decomposing each relative spatial matrix using singular value decomposition, the raw spatial representation is formed, from which deep context learner conducts unsupervised learning of the global and local features. Deep context learner is a deep neural network with a novel model structure to adapt the proposed coupled softmax layer, which encodes not only the discriminative information among local regions but also the one among global shapes. Experimental results show that DS outperforms state-of-the-art methods.

KeywordCoupled Softmax Deep Spatial Directed Circular Graph Spatially-enhanced 3d Features
DOI10.1109/TIP.2018.2816821
URLView the original
Indexed BySCI
Language英语
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS IDWOS:000428930600012
Fulltext Access
Citation statistics
Cited Times [WOS]:5   [WOS Record]     [Related Records in WOS]
Document TypeJournal article
CollectionDEPARTMENT OF COMPUTER AND INFORMATION SCIENCE
Affiliation1.Northwestern Polytechnical University
2.Universidade de Macau
3.Tsinghua University
Recommended Citation
GB/T 7714
Han Z.,Liu Z.,Vong C.-M.,et al. Deep Spatiality: Unsupervised Learning of Spatially-Enhanced Global and Local 3D Features by Deep Neural Network with Coupled Softmax[J]. IEEE Transactions on Image Processing,2018,27(6):3049-3063.
APA Han Z..,Liu Z..,Vong C.-M..,Liu Y.-S..,Bu S..,...&Chen C.L.P..(2018).Deep Spatiality: Unsupervised Learning of Spatially-Enhanced Global and Local 3D Features by Deep Neural Network with Coupled Softmax.IEEE Transactions on Image Processing,27(6),3049-3063.
MLA Han Z.,et al."Deep Spatiality: Unsupervised Learning of Spatially-Enhanced Global and Local 3D Features by Deep Neural Network with Coupled Softmax".IEEE Transactions on Image Processing 27.6(2018):3049-3063.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Han Z.]'s Articles
[Liu Z.]'s Articles
[Vong C.-M.]'s Articles
Baidu academic
Similar articles in Baidu academic
[Han Z.]'s Articles
[Liu Z.]'s Articles
[Vong C.-M.]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Han Z.]'s Articles
[Liu Z.]'s Articles
[Vong C.-M.]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.