3D2SeqViews: Aggregating Sequential Views for 3D Global Feature Learning by CNN With Hierarchical Attention Aggregation

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

Status	已發表Published
	3D2SeqViews: Aggregating Sequential Views for 3D Global Feature Learning by CNN With Hierarchical Attention Aggregation
	Han, Z.Z.; Lu, H.L.; Liu, Z.B.; Vong, C. M.; Liu, Y.S.; Zwicker, M.; Han, J.W.; Chen, C. L. P.
	2019-08-01
Source Publication	IEEE Transactions on Image Processing (SCI-E)
ISSN	1057-7149
Pages	3986-3999
Abstract	Learning 3D global features by aggregating multiple views is important. Pooling is widely used to aggregate views in deep learning models. However, pooling disregards a lot of content information within views and the spatial relationship among the views, which limits the discriminability of learned features. To resolve this issue, 3D to Sequential Views (3D2SeqViews) is proposed to more effectively aggregate the sequential views using convolutional neural networks with a novel hierarchical attention aggregation. Specifically, the content information within each view is first encoded. Then, the encoded view content information and the sequential spatiality among the views are simultaneously aggregated by the hierarchical attention aggregation, where view-level attention and class-level attention are proposed to hierarchically weight sequential views and shape classes. View-level attention is learned to indicate how much attention is paid to each view by each shape class, which subsequently weights sequential views through a novel recursive view integration. Recursive view integration learns the semantic meaning of view sequence, which is robust to the first view position. Furthermore, class-level attention is introduced to describe how much attention is paid to each shape class, which innovatively employs the discriminative ability of the fine-tuned network. 3D2SeqViews learns more discriminative features than the state-of-the-art, which leads to the outperforming results in shape classification and retrieval under three large-scale benchmarks.
Keyword	3D global feature learning view aggregation sequential views hierarchical attention aggregation CNN
URL	View the original
Language	英語English
The Source to Article	PB_Publication
PUB ID	53048
Document Type	Journal article
Collection	DEPARTMENT OF COMPUTER AND INFORMATION SCIENCE
Corresponding Author	Liu, Z.B.
Recommended Citation GB/T 7714	Han, Z.Z.,Lu, H.L.,Liu, Z.B.,et al. 3D2SeqViews: Aggregating Sequential Views for 3D Global Feature Learning by CNN With Hierarchical Attention Aggregation[J]. IEEE Transactions on Image Processing (SCI-E), 2019, 3986-3999.
APA	Han, Z.Z.., Lu, H.L.., Liu, Z.B.., Vong, C. M.., Liu, Y.S.., Zwicker, M.., Han, J.W.., & Chen, C. L. P. (2019). 3D2SeqViews: Aggregating Sequential Views for 3D Global Feature Learning by CNN With Hierarchical Attention Aggregation. IEEE Transactions on Image Processing (SCI-E), 3986-3999.
MLA	Han, Z.Z.,et al."3D2SeqViews: Aggregating Sequential Views for 3D Global Feature Learning by CNN With Hierarchical Attention Aggregation".IEEE Transactions on Image Processing (SCI-E) (2019):3986-3999.

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