{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T16:15:53Z","timestamp":1781799353841,"version":"3.54.5"},"reference-count":44,"publisher":"Association for Computing Machinery (ACM)","issue":"3s","license":[{"start":{"date-parts":[[2021,10,31]],"date-time":"2021-10-31T00:00:00Z","timestamp":1635638400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"crossref","award":["MOST 110-2634-F-002-026"],"award-info":[{"award-number":["MOST 110-2634-F-002-026"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Qualcomm Technologies, Inc."}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2021,10,31]]},"abstract":"<jats:p>\n            We study the XAI (explainable AI) on the face recognition task, particularly the face verification. Face verification has become a crucial task in recent days and it has been deployed to plenty of applications, such as access control, surveillance, and automatic personal log-on for mobile devices. With the increasing amount of data, deep convolutional neural networks can achieve very high accuracy for the face verification task. Beyond exceptional performances, deep face verification models need more interpretability so that we can trust the results they generate. In this article, we propose a novel similarity metric, called explainable cosine (\n            <jats:italic>xCos<\/jats:italic>\n            ), that comes with a learnable module that can be plugged into most of the verification models to provide meaningful explanations. With the help of\n            <jats:italic>xCos<\/jats:italic>\n            , we can see which parts of the two input faces are similar, where the model pays its attention to, and how the local similarities are weighted to form the output\n            <jats:italic>xCos<\/jats:italic>\n            score. We demonstrate the effectiveness of our proposed method on LFW and various competitive benchmarks, not only resulting in providing novel and desirable model interpretability for face verification but also ensuring the accuracy as plugging into existing face recognition models.\n          <\/jats:p>","DOI":"10.1145\/3469288","type":"journal-article","created":{"date-parts":[[2021,11,15]],"date-time":"2021-11-15T17:56:12Z","timestamp":1636998972000},"page":"1-16","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":40,"title":["xCos: An Explainable Cosine Metric for Face Verification Task"],"prefix":"10.1145","volume":"17","author":[{"given":"Yu-Sheng","family":"Lin","sequence":"first","affiliation":[{"name":"National Taiwan University, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhe-Yu","family":"Liu","sequence":"additional","affiliation":[{"name":"National Taiwan University, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-An","family":"Chen","sequence":"additional","affiliation":[{"name":"National Taiwan University, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Siang","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Toronto, Toronto, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ya-Liang","family":"Chang","sequence":"additional","affiliation":[{"name":"National Taiwan University, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Winston H.","family":"Hsu","sequence":"additional","affiliation":[{"name":"National Taiwan University, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,11,15]]},"reference":[{"key":"e_1_3_2_2_2","volume-title":"Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings","author":"Bartlett Peter L.","year":"2012","unstructured":"Peter L. Bartlett, Fernando C. N. Pereira, Christopher J. C. Burges, L\u00e9on Bottou, and Kilian Q. Weinberger (Eds.). 2012. In Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings. http:\/\/papers.nips.cc\/book\/advances-in-neural-information-processing-systems-25-2012."},{"key":"e_1_3_2_3_2","article-title":"Approximating CNNs with Bag-of-Local-Features models works surprisingly well on ImageNet","author":"Brendel Wieland","year":"2019","unstructured":"Wieland Brendel and Matthias Bethge. 2019. Approximating CNNs with Bag-of-Local-Features models works surprisingly well on ImageNet. In International Conference on Learning Representations. https:\/\/openreview.net\/pdf?id=SkfMWhAqYQ.","journal-title":"International Conference on Learning Representations"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00020"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00013"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00916"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00097"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2015.2420374"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00928"},{"key":"e_1_3_2_10_2","doi-asserted-by":"crossref","unstructured":"Jiankang Deng Jia Guo Xue Niannan and Stefanos Zafeiriou. 2019. ArcFace: Additive angular margin loss for deep face recognition. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201919) .","DOI":"10.1109\/CVPR.2019.00482"},{"key":"e_1_3_2_11_2","first-page":"2006","article-title":"Marginal loss for deep face recognition","author":"Deng Jiankang","year":"2017","unstructured":"Jiankang Deng, Yuxiang Zhou, and Stefanos P. Zafeiriou. 2017. Marginal loss for deep face recognition. In IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW\u201917), 2006\u20132014.","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW\u201917)"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2971170"},{"key":"e_1_3_2_13_2","article-title":"Explainable artificial intelligence (XAI)","volume":"2","author":"Gunning David","year":"2017","unstructured":"David Gunning. 2017. Explainable artificial intelligence (XAI). Defense Advanced Research Projects Agency (DARPA), nd Web 2 (2017).","journal-title":"Defense Advanced Research Projects Agency (DARPA), nd Web"},{"key":"e_1_3_2_14_2","unstructured":"Yandong Guo Lei Zhang Yuxiao Hu Xiaodong He and Jianfeng Gao. 2016. MS-Celeb-1M: A dataset and benchmark for large-scale face recognition. In European Conference Computer Vision (ECCV\u201916) ."},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3306618.3314273"},{"key":"e_1_3_2_17_2","volume-title":"NIPS Deep Learning and Representation Learning Workshop","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeffrey Dean. 2015. Distilling the knowledge in a neural network. In NIPS Deep Learning and Representation Learning Workshop. http:\/\/arxiv.org\/abs\/1503.02531."},{"key":"e_1_3_2_18_2","volume-title":"Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments","author":"Huang Gary B.","year":"2007","unstructured":"Gary B. Huang, Manu Ramesh, Tamara Berg, and Erik Learned-Miller. 2007. Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments. Technical Report 07-49. University of Massachusetts, Amherst."},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.267"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.243"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459250"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.713"},{"key":"e_1_3_2_23_2","first-page":"905","article-title":"Improving the interpretability of deep neural networks with knowledge distillation","author":"Liu Xuan","year":"2018","unstructured":"Xuan Liu, Xiaoguang Wang, and Stan Matwin. 2018. Improving the interpretability of deep neural networks with knowledge distillation. In IEEE International Conference on Data Mining Workshops (ICDMW\u201918), 905\u2013912.","journal-title":"IEEE International Conference on Data Mining Workshops (ICDMW\u201918)"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.5555\/2888116.2888245"},{"key":"e_1_3_2_25_2","article-title":"The AR face database","author":"Martinez A. M.","year":"1998","unstructured":"A. M. Martinez and Robert Benavente. 1998. The AR face database. Tech. Rep. 24 CVC Technical Report (Jan. 1998).","journal-title":"Tech. Rep. 24 CVC Technical Report"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413499"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.250"},{"key":"e_1_3_2_28_2","doi-asserted-by":"crossref","unstructured":"Omkar M. Parkhi Andrea Vedaldi and Andrew Zisserman. 2015. Deep face recognition. In The British Machine Vision Conference (BMVC\u201915) .","DOI":"10.5244\/C.29.41"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477558"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2572683"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969049"},{"key":"e_1_3_2_35_2","doi-asserted-by":"crossref","unstructured":"H. J. Wang Yitong Wang Zheng Zhou Xing Ji Dihong Gong Jingchao Zhou Zhifeng Li and Wei Liu. 2018. CosFace: Large margin cosine loss for deep face recognition. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR\u201918) . 5265\u20135274.","DOI":"10.1109\/CVPR.2018.00552"},{"key":"e_1_3_2_36_2","unstructured":"Yandong Wen Kaipeng Zhang Zhifeng Li and Yu Qiao. 2016. A discriminative feature learning approach for deep face recognition. In European Conference Computer Vision (ECCV\u201916) ."},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_15"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995566"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00148"},{"key":"e_1_3_2_40_2","article-title":"Learning face representation from scratch","volume":"1411","author":"Yi Dong","year":"2014","unstructured":"Dong Yi, Zhen Lei, Shengcai Liao, and Stan Z. Li. 2014. Learning face representation from scratch. ArXiv abs\/1411.7923 (2014).","journal-title":"ArXiv"},{"key":"e_1_3_2_41_2","unstructured":"Bangjie Yin Luan Tran Haoxiang Li Xiaohui Shen and Xiaoming Liu. 2019. Towards interpretable face recognition. In Proceeding of International Conference on Computer Vision (ICCV\u201919) ."},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"e_1_3_2_43_2","article-title":"Cross-age LFW: A database for studying cross-age face recognition in unconstrained environments","volume":"1708","author":"Zheng Tianyue","year":"2017","unstructured":"Tianyue Zheng, Weihong Deng, and Jiani Hu. 2017. Cross-age LFW: A database for studying cross-age face recognition in unconstrained environments. CoRR abs\/1708.08197 (2017). arxiv:1708.08197http:\/\/arxiv.org\/abs\/1708.08197.","journal-title":"CoRR"},{"key":"e_1_3_2_44_2","first-page":"arXiv:1512.0415","article-title":"Learning deep features for discriminative localization","author":"Zhou Bolei","year":"2015","unstructured":"Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, and Antonio Torralba. 2015. Learning deep features for discriminative localization. arXiv e-prints, Article arXiv:1512.04150 (Dec 2015), arXiv:1512.04150 pages. arxiv:1512.04150 [cs.CV]","journal-title":"arXiv e-prints"},{"key":"e_1_3_2_45_2","doi-asserted-by":"crossref","unstructured":"Z. Zhu P. Luo X. Wang and X. Tang. 2013. Deep learning identity-preserving face space. In IEEE International Conference on Computer Vision (ICCV\u201913) . 113\u2013120.","DOI":"10.1109\/ICCV.2013.21"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3469288","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3469288","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:28:23Z","timestamp":1750195703000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3469288"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,31]]},"references-count":44,"journal-issue":{"issue":"3s","published-print":{"date-parts":[[2021,10,31]]}},"alternative-id":["10.1145\/3469288"],"URL":"https:\/\/doi.org\/10.1145\/3469288","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,31]]},"assertion":[{"value":"2020-12-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-06-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-11-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}