3DView Graph: Learning Global Features for 3D Shapes from A Graph of Unordered Views with Attention

UM > Faculty of Science and Technology > DEPARTMENT OF COMPUTER AND INFORMATION SCIENCE

Status	已發表Published
	3DView Graph: Learning Global Features for 3D Shapes from A Graph of Unordered Views with Attention
	Han, Z. Z.; Wang, X.Y.; Vong, C. M.; Liu, Y.S.; Zwicker, M.; Chen, C. L. P.
	2019-08-01
Source Publication	Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI-19)
Abstract	Learning global features by aggregating information over multiple views has been shown to be effective for 3D shape analysis. For view aggregation in deep learning models, pooling has been applied extensively. However, pooling leads to a loss of the content within views, and the spatial relationship among views, which limits the discriminability of learned features. We propose 3DViewGraph to resolve this issue, which learns 3D global features by more effectively aggregating unordered views with attention. Specifically, unordered views taken around a shape are regarded as view nodes on a view graph. 3DViewGraph first learns a novel latent semantic mapping to project low-level view features into meaningful latent semantic embeddings in a lower dimensional space, which is spanned by latent semantic patterns. Then, the content and spatial information of each pair of view nodes are encoded by a novel spatial pattern correlation, where the correlation is computed among latent semantic patterns. Finally, all spatial pattern correlations are integrated with attention weights learned by a novel attention mechanism. This further increases the discriminability of learned features by highlighting the unordered view nodes with distinctive characteristics and depressing the ones with appearance ambiguity. We show that 3DViewGraph outperforms state-of-the-art methods under three large-scale benchmarks.
Keyword	3D View Computer Visision
URL	View the original
Language	英語English
The Source to Article	PB_Publication
PUB ID	52989
Document Type	Conference paper
Collection	DEPARTMENT OF COMPUTER AND INFORMATION SCIENCE
Corresponding Author	Han, Z. Z.
Recommended Citation GB/T 7714	Han, Z. Z.,Wang, X.Y.,Vong, C. M.,et al. 3DView Graph: Learning Global Features for 3D Shapes from A Graph of Unordered Views with Attention[C], 2019.
APA	Han, Z. Z.., Wang, X.Y.., Vong, C. M.., Liu, Y.S.., Zwicker, M.., & Chen, C. L. P. (2019). 3DView Graph: Learning Global Features for 3D Shapes from A Graph of Unordered Views with Attention. Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI-19).

Files in This Item:
There are no files associated with this item.

If you have any objections to this item, please fill out the form below and the administrator will contact you as soon as possible.
Content:
Email：	*
Affiliation No.
Verification Code:	Refresh

Any comments and suggestions are welcomed.
Title:	*
Content:
Email：	*
Verification Code:	Refresh