{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T16:17:20Z","timestamp":1761581840426,"version":"3.41.0"},"reference-count":72,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2019,5,31]],"date-time":"2019-05-31T00:00:00Z","timestamp":1559260800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2019,5,31]]},"abstract":"<jats:p>\n            In the large-scale image retrieval task, the two most important requirements are the discriminability of image representations and the efficiency in computation and storage of representations. Regarding the former requirement, Convolutional Neural Network is proven to be a very powerful tool to extract highly discriminative local descriptors for effective image search. Additionally, to further improve the discriminative power of the descriptors, recent works adopt fine-tuned strategies. In this article, taking a different approach, we propose a novel, computationally efficient, and competitive framework. Specifically, we first propose various strategies to compute masks, namely,\n            <jats:bold>\n              <jats:italic>SIFT-masks<\/jats:italic>\n            <\/jats:bold>\n            ,\n            <jats:bold>\n              <jats:italic>SUM-mask<\/jats:italic>\n            <\/jats:bold>\n            , and\n            <jats:bold>\n              <jats:italic>MAX-mask<\/jats:italic>\n            <\/jats:bold>\n            , to select a representative subset of local convolutional features and eliminate redundant features. Our in-depth analyses demonstrate that proposed masking schemes are effective to address the burstiness drawback and improve retrieval accuracy. Second, we propose to employ recent embedding and aggregating methods that can significantly boost the feature discriminability. Regarding the computation and storage efficiency, we include a hashing module to produce very compact binary image representations. Extensive experiments on six image retrieval benchmarks demonstrate that our proposed framework achieves the state-of-the-art retrieval performances.\n          <\/jats:p>","DOI":"10.1145\/3314051","type":"journal-article","created":{"date-parts":[[2019,6,6]],"date-time":"2019-06-06T12:28:42Z","timestamp":1559824122000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":23,"title":["From Selective Deep Convolutional Features to Compact Binary Representations for Image Retrieval"],"prefix":"10.1145","volume":"15","author":[{"given":"Thanh-Toan","family":"Do","sequence":"first","affiliation":[{"name":"University of Liverpool, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1076-8043","authenticated-orcid":false,"given":"Tuan","family":"Hoang","sequence":"additional","affiliation":[{"name":"Singapore University of Technology and Design, Singapore"}]},{"given":"Dang-Khoa Le","family":"Tan","sequence":"additional","affiliation":[{"name":"Singapore University of Technology and Design, Singapore"}]},{"given":"Huu","family":"Le","sequence":"additional","affiliation":[{"name":"Queensland University of Technology, Brisbane, Australia"}]},{"given":"Tam V.","family":"Nguyen","sequence":"additional","affiliation":[{"name":"University of Dayton, Dayton, OH, United States"}]},{"given":"Ngai-Man","family":"Cheung","sequence":"additional","affiliation":[{"name":"Singapore University of Technology and Design, Singapore"}]}],"member":"320","published-online":{"date-parts":[[2019,6,5]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.572"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/2354409.2355123"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301270"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.150"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_38"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967262"},{"volume-title":"Carreira-Perpinan and Ramin Raziperchikolaei","year":"2015","author":"Miguel","key":"e_1_2_1_7_1"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502171"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00079"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2686861"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_14"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.449"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_48"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.193"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_26"},{"volume-title":"Proceedings of the NIPS.","year":"2014","author":"Goodfellow Ian","key":"e_1_2_1_17_1"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_15"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1016-8"},{"volume-title":"Roberto Cipolla","author":"Grauman Kristen","key":"e_1_2_1_20_1"},{"volume-title":"Proceedings of the CVPR.","year":"2014","author":"Hariharan Bharath","key":"e_1_2_1_21_1"},{"volume-title":"Girshick","year":"2017","author":"He Kaiming","key":"e_1_2_1_22_1"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.378"},{"key":"e_1_2_1_24_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2015. Deep residual learning for image recognition. arXiv preprint arXiv:1512.03385.  Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2015. Deep residual learning for image recognition. arXiv preprint arXiv:1512.03385."},{"volume-title":"Dang-Khoa Le Tan, and Ngai-Man Cheung","year":"2018","author":"Hoang Tuan","key":"e_1_2_1_25_1"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123417"},{"volume-title":"Proceedings of the ICCV.","year":"2017","author":"Hyeonwoo Noh","key":"e_1_2_1_27_1"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33709-3_55"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88682-2_24"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206609"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0285-2"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.235"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.417"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46604-0_48"},{"volume-title":"Hinton","year":"2012","author":"Krizhevsky Alex","key":"e_1_2_1_37_1"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967197"},{"volume-title":"Proceedings of the CVPR.","author":"Lin Guosheng","key":"e_1_2_1_39_1"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2660244"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.5555\/850924.851523"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.317"},{"volume-title":"Proceedings of the ECCV.","year":"2016","author":"Noroozi Mehdi","key":"e_1_2_1_43_1"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011139631724"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383266"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.5555\/1888089.1888101"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383172"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587635"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_1"},{"key":"e_1_2_1_50_1","unstructured":"Filip Radenovi\u0107 Giorgos Tolias and Ond\u0159ej Chum. 2017. Fine-tuning CNN image retrieval with no human annotation. arXiv:1711.02512.  Filip Radenovi\u0107 Giorgos Tolias and Ond\u0159ej Chum. 2017. Fine-tuning CNN image retrieval with no human annotation. arXiv:1711.02512."},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.131"},{"volume-title":"Proceedings of the NIPS.","year":"2015","author":"Ren Shaoqing","key":"e_1_2_1_52_1"},{"key":"e_1_2_1_53_1","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.  Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556."},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.5555\/946247.946751"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.03.021"},{"volume-title":"Proceedings of the AAAI.","year":"2018","author":"Song Jingkuan","key":"e_1_2_1_56_1"},{"volume-title":"Proceedings of the AAAI.","year":"2018","author":"Song Jingkuan","key":"e_1_2_1_57_1"},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2814344"},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/2812802"},{"key":"e_1_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.177"},{"volume-title":"Proceedings of the ICLR.","year":"2016","author":"Tolias Giorgos","key":"e_1_2_1_62_1"},{"key":"e_1_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874249"},{"key":"e_1_2_1_64_1","doi-asserted-by":"crossref","unstructured":"Andrea Vedaldi and Karel Lenc. 2014. MatConvNet\u2014Convolutional neural networks for MATLAB. Retrieved from http:\/\/arxiv.org\/abs\/1412.4564.  Andrea Vedaldi and Karel Lenc. 2014. MatConvNet\u2014Convolutional neural networks for MATLAB. Retrieved from http:\/\/arxiv.org\/abs\/1412.4564.","DOI":"10.1145\/2733373.2807412"},{"key":"e_1_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699960"},{"key":"e_1_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2688133"},{"volume-title":"Proceedings of the NIPS.","year":"2008","author":"Weiss Yair","key":"e_1_2_1_67_1"},{"volume-title":"Proceedings of the AAAI.","year":"2018","author":"Xu Jian","key":"e_1_2_1_68_1"},{"key":"e_1_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967252"},{"volume-title":"Zeiler and Rob Fergus","year":"2013","author":"Matthew","key":"e_1_2_1_70_1"},{"key":"e_1_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2549360"},{"key":"e_1_2_1_72_1","article-title":"SIFT meets CNN: A decade survey of instance retrieval","author":"Zheng Liang","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3314051","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3314051","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:23:48Z","timestamp":1750202628000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3314051"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5,31]]},"references-count":72,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2019,5,31]]}},"alternative-id":["10.1145\/3314051"],"URL":"https:\/\/doi.org\/10.1145\/3314051","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"type":"print","value":"1551-6857"},{"type":"electronic","value":"1551-6865"}],"subject":[],"published":{"date-parts":[[2019,5,31]]},"assertion":[{"value":"2018-07-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-02-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-06-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}