{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T14:15:54Z","timestamp":1753884954095,"version":"3.41.2"},"reference-count":26,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"vor","delay-in-days":269,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61876098","61671274","61573219"],"award-info":[{"award-number":["61876098","61671274","61573219"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018YFC0830100","2018YFC0830102"],"award-info":[{"award-number":["2018YFC0830100","2018YFC0830102"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007927","name":"Shandong Jianzhu University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007927","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computational Intelligence and Neuroscience"],"published-print":{"date-parts":[[2021,1]]},"abstract":"<jats:p>The cross\u2010modal hashing method can map heterogeneous multimodal data into a compact binary code that preserves semantic similarity, which can significantly enhance the convenience of cross\u2010modal retrieval. However, the currently available supervised cross\u2010modal hashing methods generally only factorize the label matrix and do not fully exploit the supervised information. Furthermore, these methods often only use one\u2010directional mapping, which results in an unstable hash learning process. To address these problems, we propose a new supervised cross\u2010modal hash learning method called Discrete Two\u2010step Cross\u2010modal Hashing (DTCH) through the exploitation of pairwise relations. Specifically, this method fully exploits the pairwise similarity relations contained in the supervision information: for the label matrix, the hash learning process is stabilized by combining matrix factorization and label regression; for the pairwise similarity matrix, a semirelaxed and semidiscrete strategy is adopted to potentially reduce the cumulative quantization errors while improving the retrieval efficiency and accuracy. The approach further combines an exploration of fine\u2010grained features in the objective function with a novel out\u2010of\u2010sample extension strategy to enable the implicit preservation of consistency between the different modal distributions of samples and the pairwise similarity relations. The superiority of our method was verified through extensive experiments using two widely used datasets.<\/jats:p>","DOI":"10.1155\/2021\/4846043","type":"journal-article","created":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T23:50:56Z","timestamp":1632786656000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Discrete Two\u2010Step Cross\u2010Modal Hashing through the Exploitation of Pairwise Relations"],"prefix":"10.1155","volume":"2021","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9599-3698","authenticated-orcid":false,"given":"Shaohua","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0846-1587","authenticated-orcid":false,"given":"Xiao","family":"Kang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0469-3989","authenticated-orcid":false,"given":"Fasheng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9644-9723","authenticated-orcid":false,"given":"Xiushan","family":"Nie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7236-8715","authenticated-orcid":false,"given":"Xingbo","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2021,9,27]]},"reference":[{"key":"e_1_2_9_1_2","unstructured":"WangK. YinQ. WangW. WuS. andWangL. A comprehensive survey on cross-modal retrieval 2016 https:\/\/arxiv.org\/abs\/1607.06215v1."},{"key":"e_1_2_9_2_2","doi-asserted-by":"publisher","DOI":"10.32604\/cmc.2019.05588"},{"key":"e_1_2_9_3_2","first-page":"675","article-title":"Feature fusion multi-view hashing based on random kernel canonical correlation analysis","volume":"63","author":"Qin J.","year":"2020","journal-title":"Computers, Materials & Continua"},{"key":"e_1_2_9_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2017.2676345"},{"key":"e_1_2_9_5_2","doi-asserted-by":"crossref","unstructured":"LinT. RoyChowdhuryA. andMajiS. Bilinear CNN models for fine-grained visual recognition Proceedings of the 2015 IEEE International Conference on Computer Vision ICCV 2015 December 2015 Santiago Chile IEEE Computer Society 1449\u20131457.","DOI":"10.1109\/ICCV.2015.170"},{"key":"e_1_2_9_6_2","unstructured":"WuB. YangQ. ZhengW. S. WangY. andWangJ. Quantized correlation hashing for fast cross-modal search Proceedings of the International Conference on Artificial Intelligence July 2015 Buenos Aires Argentina 3946\u20133952."},{"key":"e_1_2_9_7_2","doi-asserted-by":"crossref","unstructured":"CaoY. LongM. WangJ. andZhuH. Correlation autoencoder hashing for supervised cross-modal search Proceedings of the ACM SIGMM International Conference on Multimedia Retrieval June 2016 New York NY USA 197\u2013204 https:\/\/doi.org\/10.1145\/2911996.2912000 2-s2.0-84978765461.","DOI":"10.1145\/2911996.2912000"},{"key":"e_1_2_9_8_2","doi-asserted-by":"crossref","unstructured":"LiuX. NieX. XiX. ZhuL. andYinY. Moboost: a self-improvement framework for linear-based hashing Proceedings of the 28th ACM International Conference on Information and Knowledge Management November 2019 Beijing China ACM 871\u2013880.","DOI":"10.1145\/3357384.3357915"},{"key":"e_1_2_9_9_2","doi-asserted-by":"crossref","unstructured":"JiangQ. Y.andLiW. J. Deep cross-modal hashing Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition July 2017 Honolulu HI USA https:\/\/doi.org\/10.1109\/cvpr.2017.348 2-s2.0-85041908169.","DOI":"10.1109\/CVPR.2017.348"},{"key":"e_1_2_9_10_2","doi-asserted-by":"crossref","unstructured":"WuD. DaiQ. LiuJ. LiB. andWangW. Deep incremental hashing network for efficient image retrieval Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) June 2019 Long Beach CA USA https:\/\/doi.org\/10.1109\/cvpr.2019.00928.","DOI":"10.1109\/CVPR.2019.00928"},{"key":"e_1_2_9_11_2","doi-asserted-by":"crossref","unstructured":"ZhangW. WuD. ZhouY. LiB. WangW. andMengD. Deep unsupervised hybrid-similarity hadamard hashing Proceedings of the MM October 2020 Seattle WA USA 3274\u20133282 https:\/\/doi.org\/10.1145\/3394171.3414028.","DOI":"10.1145\/3394171.3414028"},{"key":"e_1_2_9_12_2","doi-asserted-by":"crossref","unstructured":"ZhaoS. WuD. ZhangW. ZhouY. LiB. andWangW. Asymmetric deep hashing for efficient hash code compression Proceedings of the MM October 2020 Seattle WA USA 763\u2013771 https:\/\/doi.org\/10.1145\/3394171.3414033.","DOI":"10.1145\/3394171.3414033"},{"key":"e_1_2_9_13_2","doi-asserted-by":"crossref","unstructured":"SunL. JiS. andYeJ. CohenW. W. McCallumA. andRoweisS. T. A least squares formulation for canonical correlation analysis Proceedings of the 25th International Conference on Machine Learning (ICML 2008) June 2008 Helsinki Finland ACM 1024\u20131031.","DOI":"10.1145\/1390156.1390285"},{"key":"e_1_2_9_14_2","doi-asserted-by":"crossref","unstructured":"SongJ. YangY. YangY. HuangZ. andShenH. T. Inter-media hashing for large-scale retrieval from heterogeneous data sources Proceedings of the 2013 ACM SIGMOD International Conference on Management of Data June 2013 New York NY USA ACM 785\u2013796 https:\/\/doi.org\/10.1145\/2463676.2465274 2-s2.0-84880548516.","DOI":"10.1145\/2463676.2465274"},{"key":"e_1_2_9_15_2","doi-asserted-by":"crossref","unstructured":"ZhouJ. DingG. andGuoY. Latent semantic sparse hashing for cross-modal similarity search Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval July 2014 Gold Coast Queensland Australia ACM 415\u2013424 https:\/\/doi.org\/10.1145\/2600428.2609610 2-s2.0-84904546285.","DOI":"10.1145\/2600428.2609610"},{"key":"e_1_2_9_16_2","doi-asserted-by":"crossref","unstructured":"ZhangD.andLiW. J. Large-scale supervised multimodal hashing with semantic correlation maximization Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence July 2014 Qu\u00e9bec City Canada 2177\u20132183.","DOI":"10.1609\/aaai.v28i1.8995"},{"key":"e_1_2_9_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2019.2911359"},{"key":"e_1_2_9_18_2","doi-asserted-by":"crossref","unstructured":"ChenZ. WangY. LiH. LuoX. NieL. andXuX. AmsalegL. HuetB. LarsonM. A. GravierG. HungH. NgoC. andOoiW. T. A two-step cross-modal hashing by exploiting label correlations and preserving similarity in both steps Proceedings of the 27th ACM International Conference on Multimedia MM 2019 October 2019 Nice France ACM 1694\u20131702.","DOI":"10.1145\/3343031.3350862"},{"key":"e_1_2_9_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2970577"},{"key":"e_1_2_9_20_2","doi-asserted-by":"crossref","unstructured":"ShenF. ShenC. LiuW. andTao ShenH. Supervised discrete hashing Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June2015 Boston MA USA 37\u201345 https:\/\/doi.org\/10.1109\/cvpr.2015.7298598 2-s2.0-84951869843.","DOI":"10.1109\/CVPR.2015.7298598"},{"key":"e_1_2_9_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2016.2592800"},{"key":"e_1_2_9_22_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-013-0701-9"},{"key":"e_1_2_9_23_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"e_1_2_9_24_2","doi-asserted-by":"crossref","unstructured":"ChuaT.-S. TangJ. HongR. LiH. LuoZ. andZhengY. Nus-wide: a real-world web image database from national university of Singapore Proceedings of the ACM international conference on image and video retrieval July 2009 Santorini Fira Greece ACM.","DOI":"10.1145\/1646396.1646452"},{"key":"e_1_2_9_25_2","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkg509"},{"key":"e_1_2_9_26_2","doi-asserted-by":"crossref","unstructured":"LiuX. NieX. ZengW. CuiC. ZhuL. andYinY. Fast discrete cross-modal hashing with regressing from semantic labels Proceedings of the 2018 ACM Multimedia Conference on Multimedia Conference October 2018 Seoul Republic of Korea ACM 1662\u20131669.","DOI":"10.1145\/3240508.3240683"}],"container-title":["Computational Intelligence and Neuroscience"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2021\/4846043.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2021\/4846043.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2021\/4846043","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T12:10:18Z","timestamp":1722946218000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2021\/4846043"}},"subtitle":[],"editor":[{"given":"Thippa Reddy","family":"G","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":26,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["10.1155\/2021\/4846043"],"URL":"https:\/\/doi.org\/10.1155\/2021\/4846043","archive":["Portico"],"relation":{},"ISSN":["1687-5265","1687-5273"],"issn-type":[{"type":"print","value":"1687-5265"},{"type":"electronic","value":"1687-5273"}],"subject":[],"published":{"date-parts":[[2021,1]]},"assertion":[{"value":"2021-06-04","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-09-09","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-09-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"4846043"}}