{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:41:28Z","timestamp":1755823288458,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":44,"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"}],"funder":[{"name":"Key R&D Program of Zhejiang Province","award":["2023C01217"],"award-info":[{"award-number":["2023C01217"]}]},{"name":"R&D Program of DCI Technology and Application Joint Laboratory"},{"name":"CCF-AFSG Research Fund"},{"name":"Zhejiang Gongshang University Digital+ Disciplinary Construction Management Project","award":["SZJ2022C005"],"award-info":[{"award-number":["SZJ2022C005"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612002","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:30Z","timestamp":1698391650000},"page":"144-152","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Video Infringement Detection via Feature Disentanglement and Mutual Information Maximization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7981-9873","authenticated-orcid":false,"given":"Zhenguang","family":"Liu","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9191-2854","authenticated-orcid":false,"given":"Xinyang","family":"Yu","sequence":"additional","affiliation":[{"name":"Zhejiang Gongshang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2899-9816","authenticated-orcid":false,"given":"Ruili","family":"Wang","sequence":"additional","affiliation":[{"name":"Massey University, Auckland, New Zealand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7098-7261","authenticated-orcid":false,"given":"Shuai","family":"Ye","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0202-3863","authenticated-orcid":false,"given":"Zhe","family":"Ma","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5244-3274","authenticated-orcid":false,"given":"Jianfeng","family":"Dong","sequence":"additional","affiliation":[{"name":"Zhejiang Gongshang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4972-2640","authenticated-orcid":false,"given":"Sifeng","family":"He","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2922-9346","authenticated-orcid":false,"given":"Feng","family":"Qian","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2766-3109","authenticated-orcid":false,"given":"Xiaobo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7410-2590","authenticated-orcid":false,"given":"Roger","family":"Zimmermann","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0369-4020","authenticated-orcid":false,"given":"Lei","family":"Yang","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00814"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2072298.2072484"},{"key":"e_1_3_2_1_3_1","volume-title":"Julien Mairal, Piotr Bojanowski, and Armand Joulin.","author":"Caron Mathilde","year":"2021","unstructured":"Mathilde Caron, Hugo Touvron, Ishan Misra, Herv\u00e9 J\u00e9 gou, Julien Mairal, Piotr Bojanowski, and Armand Joulin. 2021. Emerging Properties in Self-Supervised Vision Transformers. CoRR, Vol. abs\/2104.14294 (2021). showeprint[arXiv]2104.14294 https:\/\/arxiv.org\/abs\/2104.14294"},{"key":"e_1_3_2_1_4_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."},{"key":"e_1_3_2_1_5_1","volume-title":"An Empirical Study of Training Self-Supervised Vision Transformers. arXiv preprint arXiv:2104.02057","author":"Xinlei","year":"2021","unstructured":"Xinlei Chen*, Saining Xie*, and Kaiming He. 2021. An Empirical Study of Training Self-Supervised Vision Transformers. arXiv preprint arXiv:2104.02057 (2021)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.636"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2832602"},{"key":"e_1_3_2_1_8_1","volume-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. CoRR","author":"Dosovitskiy Alexey","year":"1929","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. CoRR, Vol. abs\/2010.11929 (2020). [arXiv]2010.11929 https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"e_1_3_2_1_9_1","volume-title":"Iterative quantization: A procrustean approach to learning binary codes for large-scale image retrieval","author":"Gong Yunchao","year":"2012","unstructured":"Yunchao Gong, Svetlana Lazebnik, Albert Gordo, and Florent Perronnin. 2012. Iterative quantization: A procrustean approach to learning binary codes for large-scale image retrieval. IEEE transactions on pattern analysis and machine intelligence, Vol. 35, 12 (2012), 2916--2929."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3169842"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_1_12_1","volume-title":"Deep Residual Learning for Image Recognition. CoRR","author":"He Kaiming","year":"2015","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2015. Deep Residual Learning for Image Recognition. CoRR, Vol. abs\/1512.03385 (2015). showeprint[arXiv]1512.03385 http:\/\/arxiv.org\/abs\/112.03385"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02041"},{"key":"e_1_3_2_1_14_1","volume-title":"Self-supervised Video Retrieval Transformer Network. CoRR","author":"He Xiangteng","year":"2021","unstructured":"Xiangteng He, Yulin Pan, Mingqian Tang, and Yiliang Lv. 2021. Self-supervised Video Retrieval Transformer Network. CoRR, Vol. abs\/2104.07993 (2021). [arXiv]2104.07993 https:\/\/arxiv.org\/abs\/2104.07993"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2018.05.013"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00538"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008108327226"},{"key":"e_1_3_2_1_18_1","unstructured":"W. Kong and W. J. Li. 2012. Isotropic Hashing. Advances in neural information processing systems Vol. 2 (2012) 1646--1654."},{"key":"e_1_3_2_1_19_1","volume-title":"ViSiL: Fine-grained Spatio-Temporal Video Similarity Learning. CoRR","author":"Kordopatis-Zilos Giorgos","year":"2019","unstructured":"Giorgos Kordopatis-Zilos, Symeon Papadopoulos, Ioannis Patras, and Ioannis Kompatsiaris. 2019. ViSiL: Fine-grained Spatio-Temporal Video Similarity Learning. CoRR, Vol. abs\/1908.07410 (2019). [arXiv]1908.07410 http:\/\/arxiv.org\/abs\/1908.07410"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-51811-4_21"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.49"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2884941"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-016-4176-6"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2501654.2501658"},{"key":"e_1_3_2_1_25_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_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01073"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","unstructured":"Zhenguang Liu Shuang Wu Shuyuan Jin Qi Liu Shijian Lu Roger Zimmermann and Li Cheng. 2019. Towards Natural and Accurate Future Motion Prediction of Humans and Animals. In CVPR. 10004--10012. https:\/\/doi.org\/10.1109\/CVPR.2019.01024","DOI":"10.1109\/CVPR.2019.01024"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","unstructured":"Zhenguang Liu Sifan Wu Chejian Xu Xiang Wang Lei Zhu Shuang Wu and Fuli Feng. 2022b. Copy Motion From One to Another: Fake Motion Video Generation. In IJCAI. 1223--1231. https:\/\/doi.org\/10.24963\/ijcai.2022\/171","DOI":"10.24963\/ijcai.2022\/171"},{"key":"e_1_3_2_1_29_1","volume-title":"Hamming distance metric learning. Advances in neural information processing systems","author":"Norouzi Mohammad","year":"2012","unstructured":"Mohammad Norouzi, David J Fleet, and Russ R Salakhutdinov. 2012. Hamming distance metric learning. Advances in neural information processing systems, Vol. 25 (2012)."},{"key":"e_1_3_2_1_30_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)."},{"key":"e_1_3_2_1_31_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)."},{"volume-title":"International Conference on Multimedea. 423","author":"Song J.","key":"e_1_3_2_1_32_1","unstructured":"J. Song, Y. Yang, Z. Huang, H. T. Shen, and R. Hong. 2011. Multiple feature hashing for real-time large scale near-duplicate video retrieval. In International Conference on Multimedea. 423."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2271746"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/1631272.1631295"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00157"},{"key":"e_1_3_2_1_36_1","volume-title":"The information bottleneck method. arXiv preprint physics\/0004057","author":"Tishby Naftali","year":"2000","unstructured":"Naftali Tishby, Fernando C Pereira, and William Bialek. 2000. The information bottleneck method. arXiv preprint physics\/0004057 (2000)."},{"volume-title":"Deep learning and the information bottleneck principle. In 2015 ieee information theory workshop (itw)","author":"Tishby Naftali","key":"e_1_3_2_1_37_1","unstructured":"Naftali Tishby and Noga Zaslavsky. 2015. Deep learning and the information bottleneck principle. In 2015 ieee information theory workshop (itw). IEEE, 1--5."},{"key":"e_1_3_2_1_38_1","volume-title":"4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1511","author":"Tolias Giorgos","year":"2016","unstructured":"Giorgos Tolias, Ronan Sicre, and Herv\u00e9 J\u00e9gou. 2016. Particular object retrieval with integral max-pooling of CNN activations. In 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1511.05879"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401151"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3140611"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2306.07576"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17280"},{"key":"e_1_3_2_1_43_1","volume-title":"Contrastive Learning with Large Memory Bank and Negative Embedding Subtraction for Accurate Copy Detection. CoRR","author":"Yokoo Shuhei","year":"2021","unstructured":"Shuhei Yokoo. 2021. Contrastive Learning with Large Memory Bank and Negative Embedding Subtraction for Accurate Copy Detection. CoRR, Vol. abs\/2112.04323 (2021). showeprint[arXiv]2112.04323 https:\/\/arxiv.org\/abs\/2112.04323"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00430"}],"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\/3581783.3612002","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612002","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:58:08Z","timestamp":1755820688000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612002"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":44,"alternative-id":["10.1145\/3581783.3612002","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612002","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"}}]}}