{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:41:20Z","timestamp":1755823280581,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612329","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:26:54Z","timestamp":1698391614000},"page":"271-279","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Cross-Modal and Multi-Attribute Face Recognition: A Benchmark"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5240-5200","authenticated-orcid":false,"given":"Feng","family":"Lin","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6573-7236","authenticated-orcid":false,"given":"Kaiqiang","family":"fu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1399-2515","authenticated-orcid":false,"given":"Hao","family":"Luo","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3142-5971","authenticated-orcid":false,"given":"Ziyue","family":"Zhan","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5804-3279","authenticated-orcid":false,"given":"Zhibo","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7981-9873","authenticated-orcid":false,"given":"Zhenguang","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3878-2680","authenticated-orcid":false,"given":"Lorenzo","family":"Cavallaro","sequence":"additional","affiliation":[{"name":"Zhejiang University & University College London, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3441-6277","authenticated-orcid":false,"given":"Kui","family":"Ren","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447648"},{"key":"e_1_3_2_1_2_1","unstructured":"Apple. 2022. Website. https:\/\/support.apple.com\/en-sg\/HT208108#: text=Security%20safeguards&text=Face%20ID%20uses%20the%20TrueDepth only%20to%20the%20Secure%20Enclave.."},{"key":"e_1_3_2_1_3_1","unstructured":"J. Sun D. Huang and Y. Wang. 2012. The buaa-visnir face database instructions. (2012)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Jiankang Deng Jia Guo Evangelos Ververas Irene Kotsia and Stefanos Zafeiriou. 2020. RetinaFace: Single-Shot Multi-Level Face Localisation in the Wild. In CVPR.","DOI":"10.1109\/CVPR42600.2020.00525"},{"key":"e_1_3_2_1_5_1","volume-title":"ArcFace: Additive Angular Margin Loss for Deep Face Recognition. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019","author":"Deng Jiankang","year":"2019","unstructured":"Jiankang Deng, Jia Guo, Niannan Xue, and Stefanos Zafeiriou. 2019. ArcFace: Additive Angular Margin Loss for Deep Face Recognition. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019. Computer Vision Foundation \/ IEEE, 4690--4699. https:\/\/doi.org\/10. 1109\/CVPR.2019.00482"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018239"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00795"},{"key":"e_1_3_2_1_9_1","unstructured":"Face. 2022. Website. https:\/\/www.faceplusplus.com\/sdk\/face-comparing\/."},{"key":"e_1_3_2_1_10_1","volume-title":"Learning robust representations via multi-view information bottleneck. arXiv preprint arXiv:2002.07017","author":"Federici Marco","year":"2020","unstructured":"Marco Federici, Anjan Dutta, Patrick Forr\u00e9, Nate Kushman, and Zeynep Akata. 2020. Learning robust representations via multi-view information bottleneck. arXiv preprint arXiv:2002.07017 (2020)."},{"key":"e_1_3_2_1_11_1","volume-title":"Dvg-face: Dual variational generation for heterogeneous face recognition","author":"Fu Chaoyou","year":"2021","unstructured":"Chaoyou Fu, Xiang Wu, Yibo Hu, Huaibo Huang, and Ran He. 2021. Dvg-face: Dual variational generation for heterogeneous face recognition. IEEE transactions on pattern analysis and machine intelligence (2021)."},{"volume-title":"Deep learning","author":"Goodfellow Ian","key":"e_1_3_2_1_12_1","unstructured":"Ian Goodfellow, Yoshua Bengio, Aaron Courville, and Yoshua Bengio. 2016. Deep learning. Vol. 1. MIT press Cambridge."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_6"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107618"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.5555\/3298483.3298529"},{"key":"e_1_3_2_1_16_1","volume-title":"Wasserstein cnn: Learning invariant features for nir-vis face recognition","author":"He Ran","year":"2018","unstructured":"Ran He, XiangWu, Zhenan Sun, and Tieniu Tan. 2018. Wasserstein cnn: Learning invariant features for nir-vis face recognition. IEEE transactions on pattern analysis and machine intelligence 41, 7 (2018), 1761--1773."},{"key":"e_1_3_2_1_17_1","unstructured":"Honorsmartscreen. 2022. Website. https:\/\/www.honor.cn\/products\/wisdomscreen\/ honorsmartscreen\/."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3160612"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3081514"},{"key":"e_1_3_2_1_20_1","unstructured":"Huawei. 2022. Website. https:\/\/consumer.huawei.com\/cn\/phones\/mate30e-pro\/."},{"key":"e_1_3_2_1_21_1","unstructured":"Huawei. 2022. Website. https:\/\/consumer.huawei.com\/cn\/phones\/mate40e-pro\/."},{"key":"e_1_3_2_1_22_1","volume-title":"International conference in communications, signal processing, and systems. Springer, 59--66","author":"Jiang Bin","year":"2018","unstructured":"Bin Jiang, Qiang Ren, Fei Dai, Jian Xiong, Jie Yang, and Guan Gui. 2018. Multi-task cascaded convolutional neural networks for real-time dynamic face recognition method. In International conference in communications, signal processing, and systems. Springer, 59--66."},{"key":"e_1_3_2_1_23_1","unstructured":"Jiayn. 2022. Website. http:\/\/www.jiayn.cn\/."},{"key":"e_1_3_2_1_24_1","volume-title":"Deep learning. nature 521, 7553","author":"LeCun Yann","year":"2015","unstructured":"Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep learning. nature 521, 7553 (2015), 436--444."},{"key":"e_1_3_2_1_25_1","volume-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 1123--1128","author":"Lei Zhen","year":"2009","unstructured":"Zhen Lei and Stan Z Li. 2009. Coupled spectral regression for matching heterogeneous faces. In 2009 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 1123--1128."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2013.59"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1014"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2009.5204149"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01449"},{"key":"e_1_3_2_1_30_1","volume-title":"2016 International Conference on Biometrics (ICB). IEEE, 1--8.","author":"Liu Xiaoxiang","year":"2016","unstructured":"Xiaoxiang Liu, Lingxiao Song, XiangWu, and Tieniu Tan. 2016. Transferring deep representation for nir-vis heterogeneous face recognition. In 2016 International Conference on Biometrics (ICB). IEEE, 1--8."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","unstructured":"Zhenguang Liu Haoming Chen Runyang Feng Shuang Wu Shouling Ji Bailin Yang and Xun Wang. 2021. Deep Dual Consecutive Network for Human Pose Estimation. In CVPR. 525--534. https:\/\/doi.org\/10.1109\/CVPR46437.2021.00059","DOI":"10.1109\/CVPR46437.2021.00059"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/SIBGRAPI.2018.00067"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01070"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2016.47"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2016.47"},{"key":"e_1_3_2_1_37_1","volume-title":"Deep Perceptual Mapping for Thermal to Visible Face Recognition. arXiv e-prints","author":"Saquib Sarfraz M","year":"2015","unstructured":"M Saquib Sarfraz and Rainer Stiefelhagen. 2015. Deep Perceptual Mapping for Thermal to Visible Face Recognition. arXiv e-prints (2015), arXiv--1507."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_3_2_1_39_1","volume-title":"A Tutorial on Principal Component Analysis. CoRR abs\/1404.1100","author":"Shlens Jonathon","year":"2014","unstructured":"Jonathon Shlens. 2014. A Tutorial on Principal Component Analysis. CoRR abs\/1404.1100 (2014). arXiv:1404.1100 http:\/\/arxiv.org\/abs\/1404.1100"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12291"},{"key":"e_1_3_2_1_41_1","volume-title":"Self-Augmented Heterogeneous Face Recognition. In 2021 IEEE International Joint Conference on Biometrics (IJCB). IEEE, 1--8.","author":"Sun Zongcai","year":"2021","unstructured":"Zongcai Sun, Chaoyou Fu, Mandi Luo, and Ran He. 2021. Self-Augmented Heterogeneous Face Recognition. In 2021 IEEE International Joint Conference on Biometrics (IJCB). IEEE, 1--8."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00157"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054007"},{"key":"e_1_3_2_1_44_1","volume-title":"Face photo-sketch synthesis and recognition","author":"Wang Xiaogang","year":"2008","unstructured":"Xiaogang Wang and Xiaoou Tang. 2008. Face photo-sketch synthesis and recognition. IEEE transactions on pattern analysis and machine intelligence 31, 11 (2008), 1955--1967."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2018.2833032"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019005"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11500"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-7683-4"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3038906"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3160595"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01432-4"},{"key":"e_1_3_2_1_52_1","volume-title":"Face recognition: A literature survey. ACM computing surveys (CSUR) 35, 4","author":"Zhao Wenyi","year":"2003","unstructured":"Wenyi Zhao, Rama Chellappa, P Jonathon Phillips, and Azriel Rosenfeld. 2003. Face recognition: A literature survey. ACM computing surveys (CSUR) 35, 4 (2003), 399--458."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Ottawa ON Canada","acronym":"MM '23"},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612329","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612329","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:59:18Z","timestamp":1755820758000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612329"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":53,"alternative-id":["10.1145\/3581783.3612329","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612329","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}