VFMVAC: View-filtering-based multi-view aggregating convolution for 3D shape recognition and retrieval
Authors:
- Zehua LiuZLZehua Liu
- Yuhe ZhangYZYuhe Zhang
- Jian GaoJGJian Gao
- Shurui WangSWShurui Wang
- 3 May 2022
- journal article
- research article
- Published by Elsevier in Pattern Recognition
- Vol. 129
Abstract
No abstract availableKeywords
Funding Information
- Fundamental Research Funds for the Central Universities
- Key Research and Development Projects of Shaanxi Province (2019SF-272)
- National Natural Science Foundation of China (61602380, 61731015, 61772421, 61802244, 61802311)
- Fundamental Research Funds for the Central Universities (GK201903114)
- Natural Science Foundation of Shaanxi Province (2019JQ-668)
This publication has 16 references indexed in Scilit:
- 3D2SeqViews: Aggregating Sequential Views for 3D Global Feature Learning by CNN With Hierarchical Attention AggregationIEEE Transactions on Image Processing, 2019
- Learning Multi-View Representation With LSTM for 3-D Shape Recognition and RetrievalIEEE Transactions on Multimedia, 2018
- SeqViews2SeqLabels: Learning 3D Global Features via Aggregating Sequential Views by RNN With AttentionIEEE Transactions on Image Processing, 2018
- A Multi-Modal, Discriminative and Spatially Invariant CNN for RGB-D Object LabelingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- ImageNet classification with deep convolutional neural networksCommunications of the ACM, 2017
- View-Based 3-D Model Retrieval: A BenchmarkIEEE Transactions on Cybernetics, 2017
- GIFT: Towards Scalable 3D Shape RetrievalIEEE Transactions on Multimedia, 2017
- Multi-Modal Clique-Graph Matching for View-Based 3D Model RetrievalIEEE Transactions on Image Processing, 2016
- Rotational Projection Statistics for 3D Local Surface Description and Object RecognitionInternational Journal of Computer Vision, 2013
- Illumination direction estimation for augmented reality using a surface input real valued output regression networkPattern Recognition, 2010