File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.24963/ijcai.2019/109
- Scopus: eid_2-s2.0-85074924854
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: MAT-Net: Medial Axis Transform Network for 3D Object Recognition
Title | MAT-Net: Medial Axis Transform Network for 3D Object Recognition |
---|---|
Authors | |
Keywords | Computer Vision: 2D and 3D Computer Vision Computer Vision: Recognition: Detection, Categorization, Indexing, Matching, Retrieval, Semantic Interpretation |
Issue Date | 2019 |
Publisher | International Joint Conference on Artificial Intelligence. The Journal's web site is located at https://www.ijcai.org/past_proceedings |
Citation | Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI 2019), Macao, China, 10-16 August 2019, p. 774-781 How to Cite? |
Abstract | 3D deep learning performance depends on object representation and local feature extraction. In this work, we present MAT-Net, a neural network which captures local and global features from the Medial Axis Transform (MAT). Different from K-Nearest-Neighbor method which extracts local features by a fixed number of neighbors, our MAT-Net exploits effective modules Group-MAT and Edge-Net to process topological structure. Experimental results illustrate that MAT-Net demonstrates competitive or better performance on 3D shape recognition than state-of-the-art methods, and prove that MAT representation has excellent capacity in 3D deep learning, even in the case of low resolution. |
Persistent Identifier | http://hdl.handle.net/10722/294205 |
ISBN |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Hu, J | - |
dc.contributor.author | Wang, B | - |
dc.contributor.author | Qian, L | - |
dc.contributor.author | Pan, Y | - |
dc.contributor.author | Guo, X | - |
dc.contributor.author | Liu, L | - |
dc.contributor.author | Wang, WP | - |
dc.date.accessioned | 2020-11-23T08:27:55Z | - |
dc.date.available | 2020-11-23T08:27:55Z | - |
dc.date.issued | 2019 | - |
dc.identifier.citation | Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI 2019), Macao, China, 10-16 August 2019, p. 774-781 | - |
dc.identifier.isbn | 9780999241141 | - |
dc.identifier.uri | http://hdl.handle.net/10722/294205 | - |
dc.description.abstract | 3D deep learning performance depends on object representation and local feature extraction. In this work, we present MAT-Net, a neural network which captures local and global features from the Medial Axis Transform (MAT). Different from K-Nearest-Neighbor method which extracts local features by a fixed number of neighbors, our MAT-Net exploits effective modules Group-MAT and Edge-Net to process topological structure. Experimental results illustrate that MAT-Net demonstrates competitive or better performance on 3D shape recognition than state-of-the-art methods, and prove that MAT representation has excellent capacity in 3D deep learning, even in the case of low resolution. | - |
dc.language | eng | - |
dc.publisher | International Joint Conference on Artificial Intelligence. The Journal's web site is located at https://www.ijcai.org/past_proceedings | - |
dc.relation.ispartof | Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI 2019) | - |
dc.subject | Computer Vision: 2D and 3D Computer Vision | - |
dc.subject | Computer Vision: Recognition: Detection, Categorization, Indexing, Matching, Retrieval, Semantic Interpretation | - |
dc.title | MAT-Net: Medial Axis Transform Network for 3D Object Recognition | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Wang, WP: wenping@cs.hku.hk | - |
dc.identifier.authority | Wang, WP=rp00186 | - |
dc.description.nature | link_to_OA_fulltext | - |
dc.identifier.doi | 10.24963/ijcai.2019/109 | - |
dc.identifier.scopus | eid_2-s2.0-85074924854 | - |
dc.identifier.hkuros | 319285 | - |
dc.identifier.spage | 774 | - |
dc.identifier.epage | 781 | - |
dc.publisher.place | United States | - |