File Download
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/ICCV.2017.203
- Scopus: eid_2-s2.0-85041907470
- WOS: WOS:000425498401096
- Find via
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: SCNet: Learning Semantic Correspondence
Title | SCNet: Learning Semantic Correspondence |
---|---|
Authors | |
Issue Date | 2017 |
Publisher | Institute of Electrical and Electronics Engineers. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000149 |
Citation | Proceedings of 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 22-29 October 2017, p. 1849-1858 How to Cite? |
Abstract | This paper addresses the problem of establishing semantic correspondences between images depicting different instances of the same object or scene category. Previous approaches focus on either combining a spatial regularizer with hand-crafted features, or learning a correspondence model for appearance only. We propose instead a convolutional neural network architecture, called SCNet, for learning a geometrically plausible model for semantic correspondence. SCNet uses region proposals as matching primitives, and explicitly incorporates geometric consistency in its loss function. It is trained on image pairs obtained from the PASCAL VOC 2007 keypoint dataset, and a comparative evaluation on several standard benchmarks demonstrates that the proposed approach substantially outperforms both recent deep learning architectures and previous methods based on hand-crafted features. |
Description | Recognition: paper no. 37 |
Persistent Identifier | http://hdl.handle.net/10722/246607 |
ISSN | 2023 SCImago Journal Rankings: 12.263 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Han, K | - |
dc.contributor.author | Rezende, RS | - |
dc.contributor.author | Ham, B | - |
dc.contributor.author | Wong, KKY | - |
dc.contributor.author | Cho, M | - |
dc.contributor.author | Schmid, C | - |
dc.contributor.author | Ponce, J | - |
dc.date.accessioned | 2017-09-18T02:31:28Z | - |
dc.date.available | 2017-09-18T02:31:28Z | - |
dc.date.issued | 2017 | - |
dc.identifier.citation | Proceedings of 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 22-29 October 2017, p. 1849-1858 | - |
dc.identifier.issn | 1550-5499 | - |
dc.identifier.uri | http://hdl.handle.net/10722/246607 | - |
dc.description | Recognition: paper no. 37 | - |
dc.description.abstract | This paper addresses the problem of establishing semantic correspondences between images depicting different instances of the same object or scene category. Previous approaches focus on either combining a spatial regularizer with hand-crafted features, or learning a correspondence model for appearance only. We propose instead a convolutional neural network architecture, called SCNet, for learning a geometrically plausible model for semantic correspondence. SCNet uses region proposals as matching primitives, and explicitly incorporates geometric consistency in its loss function. It is trained on image pairs obtained from the PASCAL VOC 2007 keypoint dataset, and a comparative evaluation on several standard benchmarks demonstrates that the proposed approach substantially outperforms both recent deep learning architectures and previous methods based on hand-crafted features. | - |
dc.language | eng | - |
dc.publisher | Institute of Electrical and Electronics Engineers. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000149 | - |
dc.relation.ispartof | IEEE International Conference on Computer Vision (ICCV) Proceedings | - |
dc.rights | ©2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | - |
dc.title | SCNet: Learning Semantic Correspondence | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Wong, KKY: kykwong@cs.hku.hk | - |
dc.identifier.authority | Wong, KKY=rp01393 | - |
dc.description.nature | postprint | - |
dc.identifier.doi | 10.1109/ICCV.2017.203 | - |
dc.identifier.scopus | eid_2-s2.0-85041907470 | - |
dc.identifier.hkuros | 276764 | - |
dc.identifier.spage | 1849 | - |
dc.identifier.epage | 1858 | - |
dc.identifier.isi | WOS:000425498401096 | - |
dc.publisher.place | United States | - |
dc.identifier.issnl | 1550-5499 | - |