期刊
IEEE SENSORS JOURNAL
卷 21, 期 20, 页码 22985-22994出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSEN.2021.3094122
关键词
Shape; Three-dimensional displays; Manifolds; Kernel; Sensors; Strain; Eigenvalues and eigenfunctions; 3D shape retrieval; multi-modality learning; non-rigid shapes
资金
- Science and Technology Development Fund, Macau [0018/2019/AKP, 0008/2019/AGJ, SKL-IOTSC-2021-2023]
- Ministry of Science and Technology of China [2019YFB1600700]
- Guangdong Basic and Applied Basic Research Foundation [2020B1515130001]
A novel feature learning approach was proposed for non-rigid 3D shape retrieval, which captured deformation-invariant characteristics and mapped them using structured sparsity regularization, showing effectiveness and advantages over existing methods in experiments on public benchmarks.
Big challenges are usually occurring in non-rigid 3D shape retrieval, for the shapes undergoing arbitrarily non-affine transformations. In this work, a novel design of feature learning approach is proposed for non-rigid 3D shape retrieval, dubbed Structured Sparsity Regularized Multi-Modality Method (SSR-MM). The shape signatures which capture the deformation-invariant characteristics are averaged and stacked for a multi-modality machine learning approach, and a transform matrix based on the structure sparsity regularization is utilized to map those signatures obtaining the discriminative features for retrieval. The proposed framework is evaluated on the publicly available non-rigid 3D human benchmarks, and the experimental results show the efficacy of our contributions and the advantages of our method over existing ones.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据