{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T04:16:15Z","timestamp":1784261775494,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":60,"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":"Guangdong Natural Science Foundation","award":["2023A1515010057"],"award-info":[{"award-number":["2023A1515010057"]}]},{"name":"National Key Research and Development Program of China","award":["2018AAA0100100"],"award-info":[{"award-number":["2018AAA0100100"]}]},{"name":"Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies","award":["2022B1212010005"],"award-info":[{"award-number":["2022B1212010005"]}]},{"name":"Shenzhen Science and Technology Program","award":["RCYX20221008092852077"],"award-info":[{"award-number":["RCYX20221008092852077"]}]},{"name":"National Natural Science Foundation of China","award":["62176077"],"award-info":[{"award-number":["62176077"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612411","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"893-902","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":37,"title":["Multi-Granularity Interactive Transformer Hashing for Cross-modal Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-7924-4039","authenticated-orcid":false,"given":"Yishu","family":"Liu","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1334-2663","authenticated-orcid":false,"given":"Qingpeng","family":"Wu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1470-6998","authenticated-orcid":false,"given":"Zheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology and Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1909-6332","authenticated-orcid":false,"given":"Jingyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huawei Technologies Company Ltd, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1578-2634","authenticated-orcid":false,"given":"Guangming","family":"Lu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372278.3390711"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_13"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"e_1_3_2_2_4_1","volume-title":"International Conference on Machine Learning. 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. 1597--1607."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.267"},{"key":"e_1_3_2_2_7_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401430"},{"key":"e_1_3_2_2_9_1","first-page":"21271","article-title":"Bootstrap your own latent-A new approach to self-supervised learning","volume":"33","author":"Grill Jean-Bastien","year":"2020","unstructured":"Jean-Bastien Grill, Florian Strub, Florent Altch\u00e9, Corentin Tallec, Pierre Richemond, Elena Buchatskaya, Carl Doersch, Bernardo Avila Pires, Zhaohan Guo, Mohammad Gheshlaghi Azar, et al. 2020. Bootstrap your own latent-A new approach to self-supervised learning. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 33. 21271--21284.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3323873.3325045"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_2_13_1","volume-title":"Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00319"},{"key":"e_1_3_2_2_15_1","first-page":"3877","article-title":"Unsupervised contrastive cross-modal hashing","volume":"45","author":"Hu Peng","year":"2023","unstructured":"Peng Hu, Hongyuan Zhu, Jie Lin, Dezhong Peng, Yin-Ping Zhao, and Xi Peng. 2023. Unsupervised contrastive cross-modal hashing. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 45 (2023), 3877--3889.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1460096.1460104"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.348"},{"key":"e_1_3_2_2_18_1","unstructured":"Shaishav Kumar and Raghavendra Udupa. 2011. Learning hash functions for cross-view similarity search. In Twenty-second International joint Conference on Artificial Intelligence. 1360--1365."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00446"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463626"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_2_23_1","volume-title":"Sgdr: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983","author":"Loshchilov Ilya","year":"2016","unstructured":"Ilya Loshchilov and Frank Hutter. 2016. Sgdr: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983 (2016)."},{"key":"e_1_3_2_2_24_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_2_25_1","first-page":"4905","article-title":"Understanding the effective receptive field in deep convolutional neural networks","volume":"29","author":"Luo Wenjie","year":"2016","unstructured":"Wenjie Luo, Yujia Li, Raquel Urtasun, and Richard Zemel. 2016. Understanding the effective receptive field in deep convolutional neural networks. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 29. 4905--4913.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2969792"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3451390"},{"key":"e_1_3_2_2_28_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_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3221787"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"e_1_3_2_2_31_1","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 32. 8024--8035.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_32_1","volume-title":"Proceedings of the International Conference on Machine Learning. 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In Proceedings of the International Conference on Machine Learning. 8748--8763."},{"key":"e_1_3_2_2_33_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog Vol. 1 8 (2019) 9."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2970050"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/662"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00312"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00541"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548187"},{"key":"e_1_3_2_2_39_1","first-page":"1","article-title":"Attention is all you need","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 30. 1--15.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123326"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107479"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_21"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557265"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2878970"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2963957"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/138"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2676345"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463625"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00637"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20221"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16592"},{"key":"e_1_3_2_2_53_1","volume-title":"Proceedings of the International Conference on Machine Learning. 12310--12320","author":"Zbontar Jure","year":"2021","unstructured":"Jure Zbontar, Li Jing, Ishan Misra, Yann LeCun, and St\u00e9phane Deny. 2021. Barlow twins: Self-supervised learning via redundancy reduction. In Proceedings of the International Conference on Machine Learning. 12310--12320."},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11263"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2912290"},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3018790"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3144352"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3512527.3531417"},{"key":"e_1_3_2_2_60_1","first-page":"1","article-title":"Knowledge distillation by on-the-fly native ensemble","volume":"31","author":"Zhu Xiatian","year":"2018","unstructured":"Xiatian Zhu, Shaogang Gong, et al. 2018. Knowledge distillation by on-the-fly native ensemble. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 31. 1--11.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612411","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612411","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:03:08Z","timestamp":1755820988000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612411"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":60,"alternative-id":["10.1145\/3581783.3612411","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612411","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"}}]}}