{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T02:31:24Z","timestamp":1777861884388,"version":"3.51.4"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031971402","type":"print"},{"value":"9783031971419","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-031-97141-9_12","type":"book-chapter","created":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T08:56:58Z","timestamp":1751273818000},"page":"173-185","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CLIP-Driven Deep Hashing for\u00a0Cross-Modal Retrieval"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-2992-5697","authenticated-orcid":false,"given":"Zhichao","family":"Han","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4118-4809","authenticated-orcid":false,"given":"Azreen","family":"Azman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5088-2871","authenticated-orcid":false,"given":"Mas Rina","family":"Mustaffa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5791-065X","authenticated-orcid":false,"given":"Fatimah","family":"Khalid","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,1]]},"reference":[{"key":"12_CR1","unstructured":"Zhu, L., Song, J., Wei, X., et al.: CAESAR: concept augmentation based semantic representation for cross-modal retrieval. Multimedia Tools Appl. 1\u201331 (2022)"},{"issue":"4","key":"12_CR2","doi-asserted-by":"publisher","first-page":"2549","DOI":"10.1007\/s11063-021-10447-4","volume":"54","author":"L Zhu","year":"2022","unstructured":"Zhu, L., Song, J., Yang, Z., et al.: DAP 2 CMH: deep adversarial privacy-preserving cross-modal hashing. Neural Process. Lett. 54(4), 2549\u20132569 (2022)","journal-title":"Neural Process. Lett."},{"issue":"1s","key":"12_CR3","first-page":"1","volume":"17","author":"C Zhang","year":"2021","unstructured":"Zhang, C., Song, J., Zhu, X., et al.: HCMSL: hybrid cross-modal similarity learning for cross-modal retrieval. ACM Trans. Multimedia Comput. Commun. Appl. (TOMM) 17(1s), 1\u201322 (2021)","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl. (TOMM)"},{"key":"12_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.106818","volume":"217","author":"Z Yang","year":"2021","unstructured":"Yang, Z., Yang, L., Raymond, O.I., et al.: NSDH: a nonlinear supervised discrete hashing framework for large-scale cross-modal retrieval. Knowl.-Based Syst. 217, 106818 (2021)","journal-title":"Knowl.-Based Syst."},{"key":"12_CR5","unstructured":"Jia, C., Yang, Y., Xia, Y., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"12_CR6","unstructured":"Radford, A., Kim, J.W., Hallacy, C., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Zhang, C., Zhong, Z., Zhu, L., et al.: M2guda: multi-metrics graph-based unsupervised domain adaptation for cross-modal hashing. In: Proceedings of the International Conference on Multimedia Retrieval, pp. 674\u2013681 (2021)","DOI":"10.1145\/3460426.3463670"},{"key":"12_CR8","unstructured":"Kumar, S., Udupa, R.: Learning hash functions for cross-view similarity search. In: IJCAI Proceedings-International Joint Conference on Artificial Intelligence, vol. 22, no. 1, p. 1360 (2011)"},{"issue":"7","key":"12_CR9","doi-asserted-by":"publisher","first-page":"3157","DOI":"10.1109\/TIP.2016.2564638","volume":"25","author":"J Tang","year":"2016","unstructured":"Tang, J., Wang, K., Shao, L.: Supervised matrix factorization hashing for cross-modal retrieval. IEEE Trans. Image Process. 25(7), 3157\u20133166 (2016)","journal-title":"IEEE Trans. Image Process."},{"issue":"8","key":"12_CR10","doi-asserted-by":"publisher","first-page":"3893","DOI":"10.1109\/TIP.2018.2821921","volume":"27","author":"C Deng","year":"2018","unstructured":"Deng, C., Chen, Z., Liu, X., et al.: Triplet-based deep hashing network for cross-modal retrieval. IEEE Trans. Image Process. 27(8), 3893\u20133903 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"12_CR11","doi-asserted-by":"publisher","first-page":"3626","DOI":"10.1109\/TIP.2020.2963957","volume":"29","author":"D Xie","year":"2020","unstructured":"Xie, D., Deng, C., Li, C., et al.: Multi-task consistency-preserving adversarial hashing for cross-modal retrieval. IEEE Trans. Image Process. 29, 3626\u20133637 (2020)","journal-title":"IEEE Trans. Image Process."},{"issue":"3","key":"12_CR12","doi-asserted-by":"publisher","first-page":"964","DOI":"10.1109\/TPAMI.2019.2940446","volume":"43","author":"X Liu","year":"2019","unstructured":"Liu, X., Hu, Z., Ling, H., et al.: MTFH: a matrix tri-factorization hashing framework for efficient cross-modal retrieval. IEEE Trans. Pattern Anal. Mach. Intell. 43(3), 964\u2013981 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Han, Z., Chen, W., Huang, C., et al.: Unsupervised method for cross-modal retrieval based on domain adaptive learning. In: Advances in Guidance, Navigation and Control, pp. 539\u2013548 (2025)","DOI":"10.1007\/978-981-96-2268-9_51"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"He, L., Xu, X., Lu, H., et al.: Unsupervised cross-modal retrieval through adversarial learning. In: 2017 IEEE International Conference on Multimedia and Expo (ICME), pp. 1153\u20131158. IEEE (2017)","DOI":"10.1109\/ICME.2017.8019549"},{"issue":"3","key":"12_CR15","doi-asserted-by":"publisher","first-page":"1047","DOI":"10.1109\/TCYB.2018.2879846","volume":"50","author":"X Huang","year":"2018","unstructured":"Huang, X., Peng, Y., Yuan, M.: MHTN: modal-adversarial hybrid transfer network for cross-modal retrieval. IEEE Trans. Cybern. 50(3), 1047\u20131059 (2018)","journal-title":"IEEE Trans. Cybern."},{"issue":"11","key":"12_CR16","doi-asserted-by":"publisher","first-page":"4368","DOI":"10.1109\/TCSVT.2019.2953692","volume":"30","author":"Y Peng","year":"2019","unstructured":"Peng, Y., Chi, J.: Unsupervised cross-media retrieval using domain adaptation with scene graph. IEEE Trans. Circuits Syst. Video Technol. 30(11), 4368\u20134379 (2019)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"9","key":"12_CR17","doi-asserted-by":"publisher","first-page":"1811","DOI":"10.1109\/TCYB.2014.2360856","volume":"45","author":"X Liu","year":"2014","unstructured":"Liu, X., Mu, Y., Zhang, D., et al.: Large-scale unsupervised hashing with shared structure learning. IEEE Trans. Cybern. 45(9), 1811\u20131822 (2014)","journal-title":"IEEE Trans. Cybern."},{"key":"12_CR18","unstructured":"Li, J., Li, D., Xiong, C., et al.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Chua, T.-S., Tang, J., Hong, R., Li, H., Luo, Z., Zheng, Y.: Nuswide: a real-world web image database from national university of Singapore. In: ACM International Conference on Image and Video Retrieval (CIVR), no. 48 (2009)","DOI":"10.1145\/1646396.1646452"},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Huiskes, M.J., Lew, M.S.: The MIR flickr retrieval evaluation. In: Proceedings of the 1st ACM International Conference on Multimedia Information Retrieval, pp. 39\u201343 (2008)","DOI":"10.1145\/1460096.1460104"},{"issue":"1","key":"12_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"AP Dempster","year":"1977","unstructured":"Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the EM algorithm. J. Roy. Stat. Soc. Ser. B (Methodol.) 39(1), 1\u201322 (1977)","journal-title":"J. Roy. Stat. Soc. Ser. B (Methodol.)"},{"issue":"12","key":"12_CR22","doi-asserted-by":"publisher","first-page":"2639","DOI":"10.1162\/0899766042321814","volume":"16","author":"DR Hardoon","year":"2004","unstructured":"Hardoon, D.R., Szedmak, S., Shawe-Taylor, J.: Canonical correlation analysis: an overview with application to learning methods. Neural Comput. 16(12), 2639\u20132664 (2004)","journal-title":"Neural Comput."},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Wang, B., Yang, Y., Xu, X., et al.: Adversarial cross-modal retrieval. In: Proceedings of the 25th ACM International Conference on Multimedia, pp. 154\u2013162 (2017)","DOI":"10.1145\/3123266.3123326"},{"issue":"3","key":"12_CR24","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1109\/MMUL.2022.3144138","volume":"29","author":"L Zhu","year":"2022","unstructured":"Zhu, L., Zhang, C., Song, J., et al.: Deep multigraph hierarchical enhanced semantic representation for cross-modal retrieval. IEEE Multimedia 29(3), 17\u201326 (2022)","journal-title":"IEEE Multimedia"},{"key":"12_CR25","doi-asserted-by":"crossref","unstructured":"Yu, J., Zhou, H., Zhan, Y., Tao, D.: Deep graph-neighbor coherence preserving network for unsupervised cross-modal hashing. In: Proceedings of AAAI Conference on Artificial Intelligence, vol. 35, no. 5, pp. 4626\u20134634 (2021)","DOI":"10.1609\/aaai.v35i5.16592"},{"key":"12_CR26","doi-asserted-by":"crossref","unstructured":"Su, S., Zhong, Z., Zhang, C.: Deep joint-semantics reconstructing hashing for large-scale unsupervised cross-modal retrieval. In: Proceedings of IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3027\u20133035 (2019)","DOI":"10.1109\/ICCV.2019.00312"},{"key":"12_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.109891","volume":"256","author":"C Hou","year":"2022","unstructured":"Hou, C., Li, Z., Tang, Z., et al.: Multiple instance relation graph reasoning for cross-modal hash retrieval. Knowl.-Based Syst. 256, 109891 (2022)","journal-title":"Knowl.-Based Syst."},{"key":"12_CR28","doi-asserted-by":"publisher","first-page":"44682","DOI":"10.1109\/ACCESS.2024.3380019","volume":"12","author":"Z Han","year":"2024","unstructured":"Han, Z., Azman, A., Khalid, F., et al.: Multi-granularity semantic information integration graph for cross-modal hash retrieval. IEEE Access 12, 44682\u201344694 (2024)","journal-title":"IEEE Access"},{"key":"12_CR29","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1016\/j.jvcir.2017.02.011","volume":"48","author":"B Jiang","year":"2017","unstructured":"Jiang, B., Yang, J., Lv, Z., Tian, K., Meng, Q., Yan, Y.: Internet cross-media retrieval based on deep learning. J. Vis. Commun. Image Represent. 48, 356\u2013366 (2017)","journal-title":"J. Vis. Commun. Image Represent."},{"key":"12_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.120731","volume":"231","author":"Q Cheng","year":"2023","unstructured":"Cheng, Q., Guo, Q., Gu, X.: Adversarial pre-optimized graph representation learning with double-order sampling for cross-modal retrieval. Expert Syst. Appl. 231, 120731 (2023)","journal-title":"Expert Syst. Appl."},{"key":"12_CR31","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.ins.2022.11.087","volume":"620","author":"Z Li","year":"2023","unstructured":"Li, Z., Lu, H., Fu, H., et al.: Parallel learned generative adversarial network with multi-path subspaces for cross-modal retrieval. Inf. Sci. 620, 84\u2013104 (2023)","journal-title":"Inf. Sci."},{"key":"12_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2023.102489","volume":"79","author":"B Li","year":"2023","unstructured":"Li, B., Yao, D., Li, Z.: RICH: a rapid method for image-text cross-modal hash retrieval. Displays 79, 102489 (2023)","journal-title":"Displays"},{"key":"12_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2023.103807","volume":"93","author":"M Yuan","year":"2023","unstructured":"Yuan, M., Zhang, H., Liu, D., et al.: Semantic-embedding guided graph network for cross-modal retrieval. J. Vis. Commun. Image Represent. 93, 103807 (2023)","journal-title":"J. Vis. Commun. Image Represent."}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-97141-9_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T05:04:42Z","timestamp":1777525482000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-97141-9_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,1]]},"ISBN":["9783031971402","9783031971419"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-97141-9_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,1]]},"assertion":[{"value":"1 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLDB","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Applications of Natural Language to Information Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kanazawa","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nldb2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/nldb2025.github.io\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}