{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T12:05:38Z","timestamp":1780056338260,"version":"3.54.0"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T00:00:00Z","timestamp":1665360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Strategic Priority Research Program of Chinese Academy of Sciences","award":["XDB28000000"],"award-info":[{"award-number":["XDB28000000"]}]},{"name":"Youth Innovation Promotion Association CAS"},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key R&D Program of China","award":["2018AAA0102000"],"award-info":[{"award-number":["2018AAA0102000"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2038, 61931008,6212200758, 61976202"],"award-info":[{"award-number":["U21B2038, 61931008,6212200758, 61976202"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,10]]},"DOI":"10.1145\/3503161.3548256","type":"proceedings-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T15:42:35Z","timestamp":1665416555000},"page":"5862-5870","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Pay Attention to Your Positive Pairs: Positive Pair Aware Contrastive Knowledge Distillation"],"prefix":"10.1145","author":[{"given":"Zhipeng","family":"Yu","sequence":"first","affiliation":[{"name":"SEECE, UCAS, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qianqian","family":"Xu","sequence":"additional","affiliation":[{"name":"IIP, ICT, CAS, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yangbangyan","family":"Jiang","sequence":"additional","affiliation":[{"name":"SKLOIS, IIE, CAS & SCS, UCAS, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoyu","family":"Qin","sequence":"additional","affiliation":[{"name":"SenseTime Group Limited, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingming","family":"Huang","sequence":"additional","affiliation":[{"name":"SCST, UCAS; IIP, ICT, CAS; BDKM, CAS; & Peng Cheng Laboratory, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,10,10]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00938"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01603"},{"key":"e_1_3_2_2_3_1","volume-title":"International conference on machine learning. PMLR, 1597--1607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen , Simon Kornblith , Mohammad Norouzi , and Geoffrey Hinton . 2020 . A simple framework for contrastive learning of visual representations . In International conference on machine learning. PMLR, 1597--1607 . Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597--1607."},{"key":"e_1_3_2_2_4_1","volume-title":"Proceedings of the fourteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 215--223","author":"Coates Adam","year":"2011","unstructured":"Adam Coates , Andrew Ng , and Honglak Lee . 2011 . An analysis of single-layer networks in unsupervised feature learning . In Proceedings of the fourteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 215--223 . Adam Coates, Andrew Ng, and Honglak Lee. 2011. An analysis of single-layer networks in unsupervised feature learning. In Proceedings of the fourteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 215--223."},{"key":"e_1_3_2_2_5_1","volume-title":"Sinkhorn distances: Lightspeed computation of optimal transport. Advances in neural information processing systems","author":"Cuturi Marco","year":"2013","unstructured":"Marco Cuturi . 2013. Sinkhorn distances: Lightspeed computation of optimal transport. Advances in neural information processing systems , Vol. 26 ( 2013 ), 2292--2300. Marco Cuturi. 2013. Sinkhorn distances: Lightspeed computation of optimal transport. Advances in neural information processing systems, Vol. 26 (2013), 2292--2300."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_2_7_1","volume-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149","author":"Han Song","year":"2015","unstructured":"Song Han , Huizi Mao , and William J Dally . 2015a. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149 ( 2015 ). Song Han, Huizi Mao, and William J Dally. 2015a. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149 (2015)."},{"key":"e_1_3_2_2_8_1","volume-title":"Learning both weights and connections for efficient neural networks. arXiv preprint arXiv:1506.02626","author":"Han Song","year":"2015","unstructured":"Song Han , Jeff Pool , John Tran , and William J Dally . 2015b. Learning both weights and connections for efficient neural networks. arXiv preprint arXiv:1506.02626 ( 2015 ). Song Han, Jeff Pool, John Tran, and William J Dally. 2015b. Learning both weights and connections for efficient neural networks. arXiv preprint arXiv:1506.02626 (2015)."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475329"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013779"},{"key":"e_1_3_2_2_12_1","first-page":"38","article-title":"Distilling the Knowledge in a Neural Network","volume":"14","author":"Hinton G.","year":"2015","unstructured":"G. Hinton , O. Vinyals , and J. Dean . 2015 . Distilling the Knowledge in a Neural Network . Computer Science , Vol. 14 , 7 (2015), 38 -- 39 . G. Hinton, O. Vinyals, and J. Dean. 2015. Distilling the Knowledge in a Neural Network. Computer Science, Vol. 14, 7 (2015), 38--39.","journal-title":"Computer Science"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475327"},{"key":"e_1_3_2_2_14_1","unstructured":"Alex Krizhevsky Geoffrey Hinton etal 2009. Learning multiple layers of features from tiny images. (2009).  Alex Krizhevsky Geoffrey Hinton et al. 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475492"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414069"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240567"},{"key":"e_1_3_2_2_18_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"34","author":"Mirzadeh S. I.","year":"2020","unstructured":"S. I. Mirzadeh , M. Farajtabar , A. Li , N. Levine , and H. Ghasemzadeh . 2020. Improved Knowledge Distillation via Teacher Assistant . Proceedings of the AAAI Conference on Artificial Intelligence , Vol. 34 , 4 ( 2020 ), 5191--5198. S. I. Mirzadeh, M. Farajtabar, A. Li, N. Levine, and H. Ghasemzadeh. 2020. Improved Knowledge Distillation via Teacher Assistant. Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34, 4 (2020), 5191--5198."},{"key":"e_1_3_2_2_19_1","volume-title":"Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748","author":"van den Oord Aaron","year":"2018","unstructured":"Aaron van den Oord , Yazhe Li , and Oriol Vinyals . 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 ( 2018 ). Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_17"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00511"},{"key":"e_1_3_2_2_23_1","unstructured":"M. Phuong and C. H. Lampert. 2021. Towards Understanding Knowledge Distillation. (2021).  M. Phuong and C. H. Lampert. 2021. Towards Understanding Knowledge Distillation. (2021)."},{"key":"e_1_3_2_2_24_1","volume-title":"Antoine Chassang, Carlo Gatta, and Yoshua Bengio.","author":"Romero Adriana","year":"2014","unstructured":"Adriana Romero , Nicolas Ballas , Samira Ebrahimi Kahou , Antoine Chassang, Carlo Gatta, and Yoshua Bengio. 2014 . Fitnets : Hints for thin deep nets. arXiv preprint arXiv:1412.6550 (2014). Adriana Romero, Nicolas Ballas, Samira Ebrahimi Kahou, Antoine Chassang, Carlo Gatta, and Yoshua Bengio. 2014. Fitnets: Hints for thin deep nets. arXiv preprint arXiv:1412.6550 (2014)."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_2_2_26_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman . 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 ( 2014 ). Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_2_27_1","volume-title":"Garnett (Eds.)","volume":"29","author":"Sohn Kihyuk","year":"2016","unstructured":"Kihyuk Sohn . 2016 . Improved Deep Metric Learning with Multi-class N-pair Loss Objective. In Advances in Neural Information Processing Systems, D. Lee, M. Sugiyama, U. Luxburg, I. Guyon, and R . Garnett (Eds.) , Vol. 29 . Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper\/ 2016\/file\/6b180037abbebea991d8b1232f8a8ca9-Paper.pdf Kihyuk Sohn. 2016. Improved Deep Metric Learning with Multi-class N-pair Loss Objective. In Advances in Neural Information Processing Systems, D. Lee, M. Sugiyama, U. Luxburg, I. Guyon, and R. Garnett (Eds.), Vol. 29. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper\/2016\/file\/6b180037abbebea991d8b1232f8a8ca9-Paper.pdf"},{"key":"e_1_3_2_2_28_1","volume-title":"Wortman Vaughan (Eds.)","volume":"34","author":"Stanton Samuel","year":"2021","unstructured":"Samuel Stanton , Pavel Izmailov , Polina Kirichenko , Alexander A Alemi , and Andrew G Wilson . 2021 . Does Knowledge Distillation Really Work?. In Advances in Neural Information Processing Systems, M. Ranzato, A. Beygelzimer, Y. Dauphin, P.S. Liang, and J . Wortman Vaughan (Eds.) , Vol. 34 . Curran Associates, Inc., 6906--6919. Samuel Stanton, Pavel Izmailov, Polina Kirichenko, Alexander A Alemi, and Andrew G Wilson. 2021. Does Knowledge Distillation Really Work?. In Advances in Neural Information Processing Systems, M. Ranzato, A. Beygelzimer, Y. Dauphin, P.S. Liang, and J. Wortman Vaughan (Eds.), Vol. 34. Curran Associates, Inc., 6906--6919."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475676"},{"key":"e_1_3_2_2_30_1","volume-title":"Contrastive representation distillation. arXiv preprint arXiv:1910.10699","author":"Tian Yonglong","year":"2019","unstructured":"Yonglong Tian , Dilip Krishnan , and Phillip Isola . 2019. Contrastive representation distillation. arXiv preprint arXiv:1910.10699 ( 2019 ). Yonglong Tian, Dilip Krishnan, and Phillip Isola. 2019. Contrastive representation distillation. arXiv preprint arXiv:1910.10699 (2019)."},{"key":"e_1_3_2_2_31_1","volume-title":"Proceedings, Part XI 16","author":"Tian Yonglong","year":"2020","unstructured":"Yonglong Tian , Dilip Krishnan , and Phillip Isola . 2020 . Contrastive multiview coding. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020 , Proceedings, Part XI 16 . Springer, 776--794. Yonglong Tian, Dilip Krishnan, and Phillip Isola. 2020. Contrastive multiview coding. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XI 16. Springer, 776--794."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_34"},{"key":"e_1_3_2_2_34_1","volume-title":"Hierarchical Self-supervised Augmented Knowledge Distillation. arXiv preprint arXiv:2107.13715","author":"Yang Chuanguang","year":"2021","unstructured":"Chuanguang Yang , Zhulin An , Linhang Cai , and Yongjun Xu. 2021. Hierarchical Self-supervised Augmented Knowledge Distillation. arXiv preprint arXiv:2107.13715 ( 2021 ). Chuanguang Yang, Zhulin An, Linhang Cai, and Yongjun Xu. 2021. Hierarchical Self-supervised Augmented Knowledge Distillation. arXiv preprint arXiv:2107.13715 (2021)."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20211"},{"key":"e_1_3_2_2_36_1","volume-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. arXiv preprint arXiv:1612.03928","author":"Zagoruyko Sergey","year":"2016","unstructured":"Sergey Zagoruyko and Nikos Komodakis . 2016a. Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. arXiv preprint arXiv:1612.03928 ( 2016 ). Sergey Zagoruyko and Nikos Komodakis. 2016a. Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. arXiv preprint arXiv:1612.03928 (2016)."},{"key":"e_1_3_2_2_37_1","volume-title":"Wide residual networks. arXiv preprint arXiv:1605.07146","author":"Zagoruyko Sergey","year":"2016","unstructured":"Sergey Zagoruyko and Nikos Komodakis . 2016b. Wide residual networks. arXiv preprint arXiv:1605.07146 ( 2016 ). Sergey Zagoruyko and Nikos Komodakis. 2016b. Wide residual networks. arXiv preprint arXiv:1605.07146 (2016)."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"crossref","unstructured":"Y. Zhang T. Xiang T. M. Hospedales and H. Lu. 2017. Deep Mutual Learning. (2017).  Y. Zhang T. Xiang T. M. Hospedales and H. Lu. 2017. Deep Mutual Learning. (2017).","DOI":"10.1109\/CVPR.2018.00454"},{"key":"e_1_3_2_2_40_1","volume-title":"Deep Supervised Cross-Modal Retrieval. In 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Zhen L.","unstructured":"L. Zhen , P. Hu , X. Wang , and D. Peng . 2020 . Deep Supervised Cross-Modal Retrieval. In 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). L. Zhen, P. Hu, X. Wang, and D. Peng. 2020. Deep Supervised Cross-Modal Retrieval. In 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00914"}],"event":{"name":"MM '22: The 30th ACM International Conference on Multimedia","location":"Lisboa Portugal","acronym":"MM '22","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 30th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548256","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503161.3548256","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:00:42Z","timestamp":1750186842000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548256"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":41,"alternative-id":["10.1145\/3503161.3548256","10.1145\/3503161"],"URL":"https:\/\/doi.org\/10.1145\/3503161.3548256","relation":{},"subject":[],"published":{"date-parts":[[2022,10,10]]},"assertion":[{"value":"2022-10-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}