Beyond a strong baseline: cross-modality contrastive learning for visible-infrared person re-identification
Abstract Cross-modality pedestrian image matching, which entails the matching of visible and infrared images, is a vital area in person re-identification (reID) due to its potential to facilitate person retrieval across a spectrum of lighting conditions. Despite its importance, this task presents co...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Fang, Pengfei [verfasserIn] |
|---|
| Format: |
Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2023 |
|---|
| Schlagwörter: |
|---|
| Anmerkung: |
© The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. |
|---|
| Übergeordnetes Werk: |
Enthalten in: Machine vision and applications - Springer Berlin Heidelberg, 1988, 34(2023), 6 vom: 15. Sept. |
|---|---|
| Übergeordnetes Werk: |
volume:34 ; year:2023 ; number:6 ; day:15 ; month:09 |
| Links: |
|---|
| DOI / URN: |
10.1007/s00138-023-01458-3 |
|---|
| Katalog-ID: |
OLC214556036X |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | OLC214556036X | ||
| 003 | DE-627 | ||
| 005 | 20240118105351.0 | ||
| 007 | tu | ||
| 008 | 240118s2023 xx ||||| 00| ||eng c | ||
| 024 | 7 | |a 10.1007/s00138-023-01458-3 |2 doi | |
| 035 | |a (DE-627)OLC214556036X | ||
| 035 | |a (DE-He213)s00138-023-01458-3-p | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 004 |q VZ |
| 084 | |a 11 |2 ssgn | ||
| 100 | 1 | |a Fang, Pengfei |e verfasserin |0 (orcid)0000-0001-8939-0460 |4 aut | |
| 245 | 1 | 0 | |a Beyond a strong baseline: cross-modality contrastive learning for visible-infrared person re-identification |
| 264 | 1 | |c 2023 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ohne Hilfsmittel zu benutzen |b n |2 rdamedia | ||
| 338 | |a Band |b nc |2 rdacarrier | ||
| 500 | |a © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. | ||
| 520 | |a Abstract Cross-modality pedestrian image matching, which entails the matching of visible and infrared images, is a vital area in person re-identification (reID) due to its potential to facilitate person retrieval across a spectrum of lighting conditions. Despite its importance, this task presents considerable challenges stemming from two significant areas: cross-modality discrepancies due to the different imaging principles of spectrum cameras and within-class variations caused by the diverse viewpoints of large-scale distributed surveillance cameras. Unfortunately, the existing literature provides limited insights into effectively mitigating these issues, signifying a crucial research gap. In response to this, the present paper makes two primary contributions. First, we conduct a comprehensive study of training methodologies and subsequently present a strong baseline network designed specifically to address the complexities of the visible-infrared person reID task. This strong baseline network is paramount to the advancement of the field and to ensure the fair evaluation of algorithmic effectiveness. Second, we propose the Cross-Modality Contrastive Learning (CMCL) scheme, a novel approach to address the cross-modality discrepancies and enhance the quality of image embeddings across both modalities. CMCL incorporates intra-modality and inter-modality contrastive loss components, designed to improve the matching quality across the modalities. Thorough experiments show the superior performance of the baseline network, and the proposed CMCL can further bring performance over the baselines, outperforming the state-of-the-art methods considerably. | ||
| 650 | 4 | |a Cross-modality | |
| 650 | 4 | |a Person re-identification | |
| 650 | 4 | |a Strong baseline | |
| 650 | 4 | |a Cross-modality contrastive learning | |
| 700 | 1 | |a Zhang, Yukang |4 aut | |
| 700 | 1 | |a Lan, Zhenzhong |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Machine vision and applications |d Springer Berlin Heidelberg, 1988 |g 34(2023), 6 vom: 15. Sept. |w (DE-627)129248843 |w (DE-600)59385-0 |w (DE-576)017944139 |x 0932-8092 |7 nnns |
| 773 | 1 | 8 | |g volume:34 |g year:2023 |g number:6 |g day:15 |g month:09 |
| 856 | 4 | 1 | |u https://doi.org/10.1007/s00138-023-01458-3 |z lizenzpflichtig |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a SYSFLAG_A | ||
| 912 | |a GBV_OLC | ||
| 912 | |a SSG-OLC-MAT | ||
| 912 | |a GBV_ILN_2018 | ||
| 912 | |a GBV_ILN_4277 | ||
| 951 | |a AR | ||
| 952 | |d 34 |j 2023 |e 6 |b 15 |c 09 | ||
| author_variant |
p f pf y z yz z l zl |
|---|---|
| matchkey_str |
article:09328092:2023----::eodsrnbslncosoaiyotatvlannfriilifa |
| hierarchy_sort_str |
2023 |
| publishDate |
2023 |
| allfields |
10.1007/s00138-023-01458-3 doi (DE-627)OLC214556036X (DE-He213)s00138-023-01458-3-p DE-627 ger DE-627 rakwb eng 004 VZ 11 ssgn Fang, Pengfei verfasserin (orcid)0000-0001-8939-0460 aut Beyond a strong baseline: cross-modality contrastive learning for visible-infrared person re-identification 2023 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. Abstract Cross-modality pedestrian image matching, which entails the matching of visible and infrared images, is a vital area in person re-identification (reID) due to its potential to facilitate person retrieval across a spectrum of lighting conditions. Despite its importance, this task presents considerable challenges stemming from two significant areas: cross-modality discrepancies due to the different imaging principles of spectrum cameras and within-class variations caused by the diverse viewpoints of large-scale distributed surveillance cameras. Unfortunately, the existing literature provides limited insights into effectively mitigating these issues, signifying a crucial research gap. In response to this, the present paper makes two primary contributions. First, we conduct a comprehensive study of training methodologies and subsequently present a strong baseline network designed specifically to address the complexities of the visible-infrared person reID task. This strong baseline network is paramount to the advancement of the field and to ensure the fair evaluation of algorithmic effectiveness. Second, we propose the Cross-Modality Contrastive Learning (CMCL) scheme, a novel approach to address the cross-modality discrepancies and enhance the quality of image embeddings across both modalities. CMCL incorporates intra-modality and inter-modality contrastive loss components, designed to improve the matching quality across the modalities. Thorough experiments show the superior performance of the baseline network, and the proposed CMCL can further bring performance over the baselines, outperforming the state-of-the-art methods considerably. Cross-modality Person re-identification Strong baseline Cross-modality contrastive learning Zhang, Yukang aut Lan, Zhenzhong aut Enthalten in Machine vision and applications Springer Berlin Heidelberg, 1988 34(2023), 6 vom: 15. Sept. (DE-627)129248843 (DE-600)59385-0 (DE-576)017944139 0932-8092 nnns volume:34 year:2023 number:6 day:15 month:09 https://doi.org/10.1007/s00138-023-01458-3 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2018 GBV_ILN_4277 AR 34 2023 6 15 09 |
| spelling |
10.1007/s00138-023-01458-3 doi (DE-627)OLC214556036X (DE-He213)s00138-023-01458-3-p DE-627 ger DE-627 rakwb eng 004 VZ 11 ssgn Fang, Pengfei verfasserin (orcid)0000-0001-8939-0460 aut Beyond a strong baseline: cross-modality contrastive learning for visible-infrared person re-identification 2023 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. Abstract Cross-modality pedestrian image matching, which entails the matching of visible and infrared images, is a vital area in person re-identification (reID) due to its potential to facilitate person retrieval across a spectrum of lighting conditions. Despite its importance, this task presents considerable challenges stemming from two significant areas: cross-modality discrepancies due to the different imaging principles of spectrum cameras and within-class variations caused by the diverse viewpoints of large-scale distributed surveillance cameras. Unfortunately, the existing literature provides limited insights into effectively mitigating these issues, signifying a crucial research gap. In response to this, the present paper makes two primary contributions. First, we conduct a comprehensive study of training methodologies and subsequently present a strong baseline network designed specifically to address the complexities of the visible-infrared person reID task. This strong baseline network is paramount to the advancement of the field and to ensure the fair evaluation of algorithmic effectiveness. Second, we propose the Cross-Modality Contrastive Learning (CMCL) scheme, a novel approach to address the cross-modality discrepancies and enhance the quality of image embeddings across both modalities. CMCL incorporates intra-modality and inter-modality contrastive loss components, designed to improve the matching quality across the modalities. Thorough experiments show the superior performance of the baseline network, and the proposed CMCL can further bring performance over the baselines, outperforming the state-of-the-art methods considerably. Cross-modality Person re-identification Strong baseline Cross-modality contrastive learning Zhang, Yukang aut Lan, Zhenzhong aut Enthalten in Machine vision and applications Springer Berlin Heidelberg, 1988 34(2023), 6 vom: 15. Sept. (DE-627)129248843 (DE-600)59385-0 (DE-576)017944139 0932-8092 nnns volume:34 year:2023 number:6 day:15 month:09 https://doi.org/10.1007/s00138-023-01458-3 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2018 GBV_ILN_4277 AR 34 2023 6 15 09 |
| allfields_unstemmed |
10.1007/s00138-023-01458-3 doi (DE-627)OLC214556036X (DE-He213)s00138-023-01458-3-p DE-627 ger DE-627 rakwb eng 004 VZ 11 ssgn Fang, Pengfei verfasserin (orcid)0000-0001-8939-0460 aut Beyond a strong baseline: cross-modality contrastive learning for visible-infrared person re-identification 2023 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. Abstract Cross-modality pedestrian image matching, which entails the matching of visible and infrared images, is a vital area in person re-identification (reID) due to its potential to facilitate person retrieval across a spectrum of lighting conditions. Despite its importance, this task presents considerable challenges stemming from two significant areas: cross-modality discrepancies due to the different imaging principles of spectrum cameras and within-class variations caused by the diverse viewpoints of large-scale distributed surveillance cameras. Unfortunately, the existing literature provides limited insights into effectively mitigating these issues, signifying a crucial research gap. In response to this, the present paper makes two primary contributions. First, we conduct a comprehensive study of training methodologies and subsequently present a strong baseline network designed specifically to address the complexities of the visible-infrared person reID task. This strong baseline network is paramount to the advancement of the field and to ensure the fair evaluation of algorithmic effectiveness. Second, we propose the Cross-Modality Contrastive Learning (CMCL) scheme, a novel approach to address the cross-modality discrepancies and enhance the quality of image embeddings across both modalities. CMCL incorporates intra-modality and inter-modality contrastive loss components, designed to improve the matching quality across the modalities. Thorough experiments show the superior performance of the baseline network, and the proposed CMCL can further bring performance over the baselines, outperforming the state-of-the-art methods considerably. Cross-modality Person re-identification Strong baseline Cross-modality contrastive learning Zhang, Yukang aut Lan, Zhenzhong aut Enthalten in Machine vision and applications Springer Berlin Heidelberg, 1988 34(2023), 6 vom: 15. Sept. (DE-627)129248843 (DE-600)59385-0 (DE-576)017944139 0932-8092 nnns volume:34 year:2023 number:6 day:15 month:09 https://doi.org/10.1007/s00138-023-01458-3 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2018 GBV_ILN_4277 AR 34 2023 6 15 09 |
| allfieldsGer |
10.1007/s00138-023-01458-3 doi (DE-627)OLC214556036X (DE-He213)s00138-023-01458-3-p DE-627 ger DE-627 rakwb eng 004 VZ 11 ssgn Fang, Pengfei verfasserin (orcid)0000-0001-8939-0460 aut Beyond a strong baseline: cross-modality contrastive learning for visible-infrared person re-identification 2023 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. Abstract Cross-modality pedestrian image matching, which entails the matching of visible and infrared images, is a vital area in person re-identification (reID) due to its potential to facilitate person retrieval across a spectrum of lighting conditions. Despite its importance, this task presents considerable challenges stemming from two significant areas: cross-modality discrepancies due to the different imaging principles of spectrum cameras and within-class variations caused by the diverse viewpoints of large-scale distributed surveillance cameras. Unfortunately, the existing literature provides limited insights into effectively mitigating these issues, signifying a crucial research gap. In response to this, the present paper makes two primary contributions. First, we conduct a comprehensive study of training methodologies and subsequently present a strong baseline network designed specifically to address the complexities of the visible-infrared person reID task. This strong baseline network is paramount to the advancement of the field and to ensure the fair evaluation of algorithmic effectiveness. Second, we propose the Cross-Modality Contrastive Learning (CMCL) scheme, a novel approach to address the cross-modality discrepancies and enhance the quality of image embeddings across both modalities. CMCL incorporates intra-modality and inter-modality contrastive loss components, designed to improve the matching quality across the modalities. Thorough experiments show the superior performance of the baseline network, and the proposed CMCL can further bring performance over the baselines, outperforming the state-of-the-art methods considerably. Cross-modality Person re-identification Strong baseline Cross-modality contrastive learning Zhang, Yukang aut Lan, Zhenzhong aut Enthalten in Machine vision and applications Springer Berlin Heidelberg, 1988 34(2023), 6 vom: 15. Sept. (DE-627)129248843 (DE-600)59385-0 (DE-576)017944139 0932-8092 nnns volume:34 year:2023 number:6 day:15 month:09 https://doi.org/10.1007/s00138-023-01458-3 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2018 GBV_ILN_4277 AR 34 2023 6 15 09 |
| allfieldsSound |
10.1007/s00138-023-01458-3 doi (DE-627)OLC214556036X (DE-He213)s00138-023-01458-3-p DE-627 ger DE-627 rakwb eng 004 VZ 11 ssgn Fang, Pengfei verfasserin (orcid)0000-0001-8939-0460 aut Beyond a strong baseline: cross-modality contrastive learning for visible-infrared person re-identification 2023 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. Abstract Cross-modality pedestrian image matching, which entails the matching of visible and infrared images, is a vital area in person re-identification (reID) due to its potential to facilitate person retrieval across a spectrum of lighting conditions. Despite its importance, this task presents considerable challenges stemming from two significant areas: cross-modality discrepancies due to the different imaging principles of spectrum cameras and within-class variations caused by the diverse viewpoints of large-scale distributed surveillance cameras. Unfortunately, the existing literature provides limited insights into effectively mitigating these issues, signifying a crucial research gap. In response to this, the present paper makes two primary contributions. First, we conduct a comprehensive study of training methodologies and subsequently present a strong baseline network designed specifically to address the complexities of the visible-infrared person reID task. This strong baseline network is paramount to the advancement of the field and to ensure the fair evaluation of algorithmic effectiveness. Second, we propose the Cross-Modality Contrastive Learning (CMCL) scheme, a novel approach to address the cross-modality discrepancies and enhance the quality of image embeddings across both modalities. CMCL incorporates intra-modality and inter-modality contrastive loss components, designed to improve the matching quality across the modalities. Thorough experiments show the superior performance of the baseline network, and the proposed CMCL can further bring performance over the baselines, outperforming the state-of-the-art methods considerably. Cross-modality Person re-identification Strong baseline Cross-modality contrastive learning Zhang, Yukang aut Lan, Zhenzhong aut Enthalten in Machine vision and applications Springer Berlin Heidelberg, 1988 34(2023), 6 vom: 15. Sept. (DE-627)129248843 (DE-600)59385-0 (DE-576)017944139 0932-8092 nnns volume:34 year:2023 number:6 day:15 month:09 https://doi.org/10.1007/s00138-023-01458-3 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2018 GBV_ILN_4277 AR 34 2023 6 15 09 |
| language |
English |
| source |
Enthalten in Machine vision and applications 34(2023), 6 vom: 15. Sept. volume:34 year:2023 number:6 day:15 month:09 |
| sourceStr |
Enthalten in Machine vision and applications 34(2023), 6 vom: 15. Sept. volume:34 year:2023 number:6 day:15 month:09 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
Cross-modality Person re-identification Strong baseline Cross-modality contrastive learning |
| dewey-raw |
004 |
| isfreeaccess_bool |
false |
| container_title |
Machine vision and applications |
| authorswithroles_txt_mv |
Fang, Pengfei @@aut@@ Zhang, Yukang @@aut@@ Lan, Zhenzhong @@aut@@ |
| publishDateDaySort_date |
2023-09-15T00:00:00Z |
| hierarchy_top_id |
129248843 |
| dewey-sort |
14 |
| id |
OLC214556036X |
| language_de |
englisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">OLC214556036X</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20240118105351.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">240118s2023 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s00138-023-01458-3</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC214556036X</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s00138-023-01458-3-p</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">004</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">11</subfield><subfield code="2">ssgn</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Fang, Pengfei</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0001-8939-0460</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Beyond a strong baseline: cross-modality contrastive learning for visible-infrared person re-identification</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Cross-modality pedestrian image matching, which entails the matching of visible and infrared images, is a vital area in person re-identification (reID) due to its potential to facilitate person retrieval across a spectrum of lighting conditions. Despite its importance, this task presents considerable challenges stemming from two significant areas: cross-modality discrepancies due to the different imaging principles of spectrum cameras and within-class variations caused by the diverse viewpoints of large-scale distributed surveillance cameras. Unfortunately, the existing literature provides limited insights into effectively mitigating these issues, signifying a crucial research gap. In response to this, the present paper makes two primary contributions. First, we conduct a comprehensive study of training methodologies and subsequently present a strong baseline network designed specifically to address the complexities of the visible-infrared person reID task. This strong baseline network is paramount to the advancement of the field and to ensure the fair evaluation of algorithmic effectiveness. Second, we propose the Cross-Modality Contrastive Learning (CMCL) scheme, a novel approach to address the cross-modality discrepancies and enhance the quality of image embeddings across both modalities. CMCL incorporates intra-modality and inter-modality contrastive loss components, designed to improve the matching quality across the modalities. Thorough experiments show the superior performance of the baseline network, and the proposed CMCL can further bring performance over the baselines, outperforming the state-of-the-art methods considerably.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Cross-modality</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Person re-identification</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Strong baseline</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Cross-modality contrastive learning</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zhang, Yukang</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Lan, Zhenzhong</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Machine vision and applications</subfield><subfield code="d">Springer Berlin Heidelberg, 1988</subfield><subfield code="g">34(2023), 6 vom: 15. Sept.</subfield><subfield code="w">(DE-627)129248843</subfield><subfield code="w">(DE-600)59385-0</subfield><subfield code="w">(DE-576)017944139</subfield><subfield code="x">0932-8092</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:34</subfield><subfield code="g">year:2023</subfield><subfield code="g">number:6</subfield><subfield code="g">day:15</subfield><subfield code="g">month:09</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s00138-023-01458-3</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-MAT</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2018</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4277</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">34</subfield><subfield code="j">2023</subfield><subfield code="e">6</subfield><subfield code="b">15</subfield><subfield code="c">09</subfield></datafield></record></collection>
|
| author |
Fang, Pengfei |
| spellingShingle |
Fang, Pengfei ddc 004 ssgn 11 misc Cross-modality misc Person re-identification misc Strong baseline misc Cross-modality contrastive learning Beyond a strong baseline: cross-modality contrastive learning for visible-infrared person re-identification |
| authorStr |
Fang, Pengfei |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)129248843 |
| format |
Article |
| dewey-ones |
004 - Data processing & computer science |
| delete_txt_mv |
keep |
| author_role |
aut aut aut |
| collection |
OLC |
| remote_str |
false |
| illustrated |
Not Illustrated |
| issn |
0932-8092 |
| topic_title |
004 VZ 11 ssgn Beyond a strong baseline: cross-modality contrastive learning for visible-infrared person re-identification Cross-modality Person re-identification Strong baseline Cross-modality contrastive learning |
| topic |
ddc 004 ssgn 11 misc Cross-modality misc Person re-identification misc Strong baseline misc Cross-modality contrastive learning |
| topic_unstemmed |
ddc 004 ssgn 11 misc Cross-modality misc Person re-identification misc Strong baseline misc Cross-modality contrastive learning |
| topic_browse |
ddc 004 ssgn 11 misc Cross-modality misc Person re-identification misc Strong baseline misc Cross-modality contrastive learning |
| format_facet |
Aufsätze Gedruckte Aufsätze |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
nc |
| hierarchy_parent_title |
Machine vision and applications |
| hierarchy_parent_id |
129248843 |
| dewey-tens |
000 - Computer science, knowledge & systems |
| hierarchy_top_title |
Machine vision and applications |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)129248843 (DE-600)59385-0 (DE-576)017944139 |
| title |
Beyond a strong baseline: cross-modality contrastive learning for visible-infrared person re-identification |
| ctrlnum |
(DE-627)OLC214556036X (DE-He213)s00138-023-01458-3-p |
| title_full |
Beyond a strong baseline: cross-modality contrastive learning for visible-infrared person re-identification |
| author_sort |
Fang, Pengfei |
| journal |
Machine vision and applications |
| journalStr |
Machine vision and applications |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
000 - Computer science, information & general works |
| recordtype |
marc |
| publishDateSort |
2023 |
| contenttype_str_mv |
txt |
| author_browse |
Fang, Pengfei Zhang, Yukang Lan, Zhenzhong |
| container_volume |
34 |
| class |
004 VZ 11 ssgn |
| format_se |
Aufsätze |
| author-letter |
Fang, Pengfei |
| doi_str_mv |
10.1007/s00138-023-01458-3 |
| normlink |
(ORCID)0000-0001-8939-0460 |
| normlink_prefix_str_mv |
(orcid)0000-0001-8939-0460 |
| dewey-full |
004 |
| title_sort |
beyond a strong baseline: cross-modality contrastive learning for visible-infrared person re-identification |
| title_auth |
Beyond a strong baseline: cross-modality contrastive learning for visible-infrared person re-identification |
| abstract |
Abstract Cross-modality pedestrian image matching, which entails the matching of visible and infrared images, is a vital area in person re-identification (reID) due to its potential to facilitate person retrieval across a spectrum of lighting conditions. Despite its importance, this task presents considerable challenges stemming from two significant areas: cross-modality discrepancies due to the different imaging principles of spectrum cameras and within-class variations caused by the diverse viewpoints of large-scale distributed surveillance cameras. Unfortunately, the existing literature provides limited insights into effectively mitigating these issues, signifying a crucial research gap. In response to this, the present paper makes two primary contributions. First, we conduct a comprehensive study of training methodologies and subsequently present a strong baseline network designed specifically to address the complexities of the visible-infrared person reID task. This strong baseline network is paramount to the advancement of the field and to ensure the fair evaluation of algorithmic effectiveness. Second, we propose the Cross-Modality Contrastive Learning (CMCL) scheme, a novel approach to address the cross-modality discrepancies and enhance the quality of image embeddings across both modalities. CMCL incorporates intra-modality and inter-modality contrastive loss components, designed to improve the matching quality across the modalities. Thorough experiments show the superior performance of the baseline network, and the proposed CMCL can further bring performance over the baselines, outperforming the state-of-the-art methods considerably. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. |
| abstractGer |
Abstract Cross-modality pedestrian image matching, which entails the matching of visible and infrared images, is a vital area in person re-identification (reID) due to its potential to facilitate person retrieval across a spectrum of lighting conditions. Despite its importance, this task presents considerable challenges stemming from two significant areas: cross-modality discrepancies due to the different imaging principles of spectrum cameras and within-class variations caused by the diverse viewpoints of large-scale distributed surveillance cameras. Unfortunately, the existing literature provides limited insights into effectively mitigating these issues, signifying a crucial research gap. In response to this, the present paper makes two primary contributions. First, we conduct a comprehensive study of training methodologies and subsequently present a strong baseline network designed specifically to address the complexities of the visible-infrared person reID task. This strong baseline network is paramount to the advancement of the field and to ensure the fair evaluation of algorithmic effectiveness. Second, we propose the Cross-Modality Contrastive Learning (CMCL) scheme, a novel approach to address the cross-modality discrepancies and enhance the quality of image embeddings across both modalities. CMCL incorporates intra-modality and inter-modality contrastive loss components, designed to improve the matching quality across the modalities. Thorough experiments show the superior performance of the baseline network, and the proposed CMCL can further bring performance over the baselines, outperforming the state-of-the-art methods considerably. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. |
| abstract_unstemmed |
Abstract Cross-modality pedestrian image matching, which entails the matching of visible and infrared images, is a vital area in person re-identification (reID) due to its potential to facilitate person retrieval across a spectrum of lighting conditions. Despite its importance, this task presents considerable challenges stemming from two significant areas: cross-modality discrepancies due to the different imaging principles of spectrum cameras and within-class variations caused by the diverse viewpoints of large-scale distributed surveillance cameras. Unfortunately, the existing literature provides limited insights into effectively mitigating these issues, signifying a crucial research gap. In response to this, the present paper makes two primary contributions. First, we conduct a comprehensive study of training methodologies and subsequently present a strong baseline network designed specifically to address the complexities of the visible-infrared person reID task. This strong baseline network is paramount to the advancement of the field and to ensure the fair evaluation of algorithmic effectiveness. Second, we propose the Cross-Modality Contrastive Learning (CMCL) scheme, a novel approach to address the cross-modality discrepancies and enhance the quality of image embeddings across both modalities. CMCL incorporates intra-modality and inter-modality contrastive loss components, designed to improve the matching quality across the modalities. Thorough experiments show the superior performance of the baseline network, and the proposed CMCL can further bring performance over the baselines, outperforming the state-of-the-art methods considerably. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2018 GBV_ILN_4277 |
| container_issue |
6 |
| title_short |
Beyond a strong baseline: cross-modality contrastive learning for visible-infrared person re-identification |
| url |
https://doi.org/10.1007/s00138-023-01458-3 |
| remote_bool |
false |
| author2 |
Zhang, Yukang Lan, Zhenzhong |
| author2Str |
Zhang, Yukang Lan, Zhenzhong |
| ppnlink |
129248843 |
| mediatype_str_mv |
n |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| doi_str |
10.1007/s00138-023-01458-3 |
| up_date |
2024-07-04T03:35:40.016Z |
| _version_ |
1803617975698194432 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">OLC214556036X</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20240118105351.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">240118s2023 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s00138-023-01458-3</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC214556036X</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s00138-023-01458-3-p</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">004</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">11</subfield><subfield code="2">ssgn</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Fang, Pengfei</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0001-8939-0460</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Beyond a strong baseline: cross-modality contrastive learning for visible-infrared person re-identification</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Cross-modality pedestrian image matching, which entails the matching of visible and infrared images, is a vital area in person re-identification (reID) due to its potential to facilitate person retrieval across a spectrum of lighting conditions. Despite its importance, this task presents considerable challenges stemming from two significant areas: cross-modality discrepancies due to the different imaging principles of spectrum cameras and within-class variations caused by the diverse viewpoints of large-scale distributed surveillance cameras. Unfortunately, the existing literature provides limited insights into effectively mitigating these issues, signifying a crucial research gap. In response to this, the present paper makes two primary contributions. First, we conduct a comprehensive study of training methodologies and subsequently present a strong baseline network designed specifically to address the complexities of the visible-infrared person reID task. This strong baseline network is paramount to the advancement of the field and to ensure the fair evaluation of algorithmic effectiveness. Second, we propose the Cross-Modality Contrastive Learning (CMCL) scheme, a novel approach to address the cross-modality discrepancies and enhance the quality of image embeddings across both modalities. CMCL incorporates intra-modality and inter-modality contrastive loss components, designed to improve the matching quality across the modalities. Thorough experiments show the superior performance of the baseline network, and the proposed CMCL can further bring performance over the baselines, outperforming the state-of-the-art methods considerably.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Cross-modality</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Person re-identification</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Strong baseline</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Cross-modality contrastive learning</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zhang, Yukang</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Lan, Zhenzhong</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Machine vision and applications</subfield><subfield code="d">Springer Berlin Heidelberg, 1988</subfield><subfield code="g">34(2023), 6 vom: 15. Sept.</subfield><subfield code="w">(DE-627)129248843</subfield><subfield code="w">(DE-600)59385-0</subfield><subfield code="w">(DE-576)017944139</subfield><subfield code="x">0932-8092</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:34</subfield><subfield code="g">year:2023</subfield><subfield code="g">number:6</subfield><subfield code="g">day:15</subfield><subfield code="g">month:09</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s00138-023-01458-3</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-MAT</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2018</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4277</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">34</subfield><subfield code="j">2023</subfield><subfield code="e">6</subfield><subfield code="b">15</subfield><subfield code="c">09</subfield></datafield></record></collection>
|
| score |
7.40086 |