DC Field | Value | Language |
---|---|---|
dc.contributor.author | Choi, SeokEon | ko |
dc.contributor.author | Lee, SuMin | ko |
dc.contributor.author | Kim, YoungEun | ko |
dc.contributor.author | Kim, Taekyung | ko |
dc.contributor.author | Kim, Changick | ko |
dc.date.accessioned | 2020-12-18T02:50:21Z | - |
dc.date.available | 2020-12-18T02:50:21Z | - |
dc.date.created | 2020-12-01 | - |
dc.date.issued | 2020-06-18 | - |
dc.identifier.citation | IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, pp.10254 - 10263 | - |
dc.identifier.issn | 1063-6919 | - |
dc.identifier.uri | http://hdl.handle.net/10203/278678 | - |
dc.description.abstract | Visible-infrared person re-identification (VI-ReID) is an important task in night-time surveillance applications, since visible cameras are difficult to capture valid appearance information under poor illumination conditions. Compared to traditional person re-identification that handles only the intra-modality discrepancy, VI-ReID suffers from additional cross-modality discrepancy caused by different types of imaging systems. To reduce both intra- and cross-modality discrepancies, we propose a Hierarchical Cross-Modality Disentanglement (Hi-CMD) method, which automatically disentangles ID-discriminative factors and ID-excluded factors from visible-thermal images. We only use ID-discriminative factors for robust cross-modality matching without ID-excluded factors such as pose or illumination. To implement our approach, we introduce an ID-preserving person image generation network and a hierarchical feature learning module. Our generation network learns the disentangled representation by generating a new cross-modality image with different poses and illuminations while preserving a person's identity. At the same time, the feature learning module enables our model to explicitly extract the common ID-discriminative characteristic between visible-infrared images. Extensive experimental results demonstrate that our method outperforms the state-of-the-art methods on two VI-ReID datasets. The source code is available at: https://github.com/bismex/HiCMD. | - |
dc.language | English | - |
dc.publisher | IEEE Conference on Computer Vision and Pattern Recognition | - |
dc.title | Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification | - |
dc.type | Conference | - |
dc.identifier.scopusid | 2-s2.0-85092726425 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 10254 | - |
dc.citation.endingpage | 10263 | - |
dc.citation.publicationname | IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020 | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | Virtual | - |
dc.identifier.doi | 10.1109/CVPR42600.2020.01027 | - |
dc.contributor.localauthor | Kim, Changick | - |
dc.contributor.nonIdAuthor | Kim, YoungEun | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.