{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T06:52:38Z","timestamp":1757314358684,"version":"3.41.0"},"reference-count":55,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2019,8,20]],"date-time":"2019-08-20T00:00:00Z","timestamp":1566259200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Young Elite Scientists Sponsorship Program By CAST","award":["2016QNRC001"],"award-info":[{"award-number":["2016QNRC001"]}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["61822208, 61632019 and 61836011"],"award-info":[{"award-number":["61822208, 61632019 and 61836011"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2019,8,31]]},"abstract":"<jats:p>Approximate Nearest Neighbor (ANN) search is an important research topic in multimedia and computer vision fields. In this article, we propose a new deep supervised quantization method by Self-Organizing Map to address this problem. Our method integrates the Convolutional Neural Networks and Self-Organizing Map into a unified deep architecture. The overall training objective optimizes supervised quantization loss as well as classification loss. With the supervised quantization objective, we minimize the differences on the maps between similar image pairs and maximize the differences on the maps between dissimilar image pairs. By optimization, the deep architecture can simultaneously extract deep features and quantize the features into suitable nodes in self-organizing map. To make the proposed deep supervised quantization method scalable for large datasets, instead of constructing a larger self-organizing map, we propose to divide the input space into several subspaces and construct self-organizing map in each subspace. The self-organizing maps in all the subspaces implicitly construct a large self-organizing map, which costs less memory and training time than directly constructing a self-organizing map with equal size. The experiments on several public standard datasets prove the superiority of our approaches over the existing ANN search methods. Besides, as a by-product, our deep architecture can be directly applied to visualization with little modification, and promising performance is demonstrated in the experiments.<\/jats:p>","DOI":"10.1145\/3328995","type":"journal-article","created":{"date-parts":[[2019,8,20]],"date-time":"2019-08-20T19:51:56Z","timestamp":1566330716000},"page":"1-18","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Deep Scalable Supervised Quantization by Self-Organizing Map"],"prefix":"10.1145","volume":"15","author":[{"given":"Min","family":"Wang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"given":"Wengang","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"given":"Qi","family":"Tian","sequence":"additional","affiliation":[{"name":"Huawei Noah\u2019s Ark Lab; University of Texas at San Antonio, San Antonio, Texas"}]},{"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]}],"member":"320","published-online":{"date-parts":[[2019,8,20]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00140"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00134"},{"volume-title":"Deep quantization network for efficient image retrieval","author":"Cao Yue","key":"e_1_2_1_3_1","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10455"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.6"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.449"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.516"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00386"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.193"},{"volume-title":"Neural network-based clustering using pairwise constraints. arXiv preprint arXiv:1511.06321","year":"2015","author":"Hsu Yen-Chang","key":"e_1_2_1_10_1"},{"volume-title":"Deep image category discovery using a transferred similarity function. arXiv preprint arXiv:1612.01253","year":"2016","author":"Hsu Yen-Chang","key":"e_1_2_1_11_1"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2890144"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2749147"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.96"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"volume-title":"Proceedings of the Association for the Advancement of Artificial Intelligence","year":"2018","author":"Jiang Qing-Yuan","key":"e_1_2_1_16_1"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2231061"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00337288"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.4249\/scholarpedia.1568"},{"volume-title":"Hinton","year":"2012","author":"Krizhevsky Alex","key":"e_1_2_1_21_1"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298947"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_2_1_24_1","unstructured":"Qi Li Zhenan Sun Ran He and Tieniu Tan. 2017. Deep supervised discrete hashing. In Advances in Neural Information Processing Systems. 2482--2491.   Qi Li Zhenan Sun Ran He and Tieniu Tan. 2017. Deep supervised discrete hashing. In Advances in Neural Information Processing Systems. 2482--2491."},{"volume-title":"Proceedings of the International Joint Conference on Artificial Intelligence.","year":"2016","author":"Li Wu-Jun","key":"e_1_2_1_25_1"},{"key":"e_1_2_1_26_1","unstructured":"Renjie Liao Alex Schwing Richard Zemel and Raquel Urtasun. 2016. Learning deep parsimonious representations. In Advances in Neural Information Processing Systems. 5076--5084.   Renjie Liao Alex Schwing Richard Zemel and Raquel Urtasun. 2016. Learning deep parsimonious representations. In Advances in Neural Information Processing Systems. 5076--5084."},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.227"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2305072"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2678163"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.02.034"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.388"},{"volume-title":"Overfeat: Integrated recognition, localization and detection using convolutional networks. arXiv preprint arXiv:1312.6229","year":"2013","author":"Sermanet Pierre","key":"e_1_2_1_32_1"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123345"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2789887"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2807412"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2455415"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502100"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2751150"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123415"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964334"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.222"},{"key":"e_1_2_1_42_1","unstructured":"Yair Weiss Antonio Torralba and Rob Fergus. 2009. Spectral hashing. In Advances in Neural Information Processing Systems. 1753--1760.   Yair Weiss Antonio Torralba and Rob Fergus. 2009. Spectral hashing. In Advances in Neural Information Processing Systems. 1753--1760."},{"key":"e_1_2_1_43_1","first-page":"2","article-title":"Supervised hashing for image retrieval via image representation learning","volume":"1","author":"Xia Rongkai","year":"2014","journal-title":"Association for the Advancement of Artificial Intelligence"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240590"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_12"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2781422"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502091"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2467315"},{"volume-title":"Proceedings of the International Conference on Machine Learning. 838--846","year":"2014","author":"Zhang Ting","key":"e_1_2_1_49_1"},{"volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1556--1564","year":"2015","author":"Zhao Fang","key":"e_1_2_1_50_1"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2389624"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2393377"},{"key":"e_1_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2301979"},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2430329"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.5555\/3172077.3172388"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2428171"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3328995","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3328995","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:54:41Z","timestamp":1750204481000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3328995"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8,20]]},"references-count":55,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2019,8,31]]}},"alternative-id":["10.1145\/3328995"],"URL":"https:\/\/doi.org\/10.1145\/3328995","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"type":"print","value":"1551-6857"},{"type":"electronic","value":"1551-6865"}],"subject":[],"published":{"date-parts":[[2019,8,20]]},"assertion":[{"value":"2018-10-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-04-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-08-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}