{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:01:47Z","timestamp":1760709707661},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2018,9,13]],"date-time":"2018-09-13T00:00:00Z","timestamp":1536796800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61532018","61322212","61602437,61672497","61472229,61202152"],"award-info":[{"award-number":["61532018","61322212","61602437,61672497","61472229,61202152"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Municipal Commission of Science and Technology","award":["D161100001816001"],"award-info":[{"award-number":["D161100001816001"]}]},{"name":"Beijing Natural Science Foundation of Beijing Municipality (CN)","award":["4174106"],"award-info":[{"award-number":["4174106"]}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2016M590135","2017T100110"],"award-info":[{"award-number":["2016M590135","2017T100110"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Lenovo Outstanding Young Scientists Program"},{"name":"National Program for Special Support of Eminent Professionals"},{"name":"National Program for Support of Top-notch Young Professionals"},{"name":"Science and Technology Development Fund of Shandong Province of China","award":["2016ZDJS02A11,ZR2017MF027"],"award-info":[{"award-number":["2016ZDJS02A11,ZR2017MF027"]}]},{"name":"Taishan Scholar Climbing Program of Shandong Province"},{"name":"SDUST Research Fund","award":["2015TDJH102"],"award-info":[{"award-number":["2015TDJH102"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2019,5]]},"DOI":"10.1007\/s11042-018-6427-1","type":"journal-article","created":{"date-parts":[[2018,9,13]],"date-time":"2018-09-13T11:53:30Z","timestamp":1536839610000},"page":"13247-13261","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Instance-level object retrieval via deep region CNN"],"prefix":"10.1007","volume":"78","author":[{"given":"Shuhuan","family":"Mei","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiqing","family":"Min","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hua","family":"Duan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuqiang","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,9,13]]},"reference":[{"key":"6427_CR1","doi-asserted-by":"crossref","unstructured":"Arandjelovic R, Zisserman A (2013) All about VLAD. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1578\u20131585","DOI":"10.1109\/CVPR.2013.207"},{"key":"6427_CR2","unstructured":"Babenko A, Lempitsky V (2015) Aggregating local deep features for image retrieval. In: Proceedings of the IEEE international conference on computer vision, pp 1269\u20131277"},{"key":"6427_CR3","doi-asserted-by":"crossref","unstructured":"Babenko A, Slesarev A, Chigorin A, Lempitsky V (2014) Neural codes for image retrieval. In: European conference on computer vision, pp 584\u2013599. Springer, Berlin","DOI":"10.1007\/978-3-319-10590-1_38"},{"key":"6427_CR4","doi-asserted-by":"crossref","unstructured":"Chandrasekhar V, Lin J, Morere O, Veillard A, Goh H (2015) Compact global descriptors for visual search. In: Data compression conference (DCC), 2015, pp 333\u2013342. IEEE","DOI":"10.1109\/DCC.2015.54"},{"issue":"7","key":"6427_CR5","doi-asserted-by":"publisher","first-page":"1019","DOI":"10.1109\/TMM.2015.2427744","volume":"17","author":"DM Chen","year":"2015","unstructured":"Chen DM, Girod B (2015) A hybrid mobile visual search system with compact global signatures. IEEE Transactions on Multimedia 17(7):1019\u20131030","journal-title":"IEEE Transactions on Multimedia"},{"issue":"8","key":"6427_CR6","doi-asserted-by":"publisher","first-page":"1982","DOI":"10.1109\/TMM.2013.2270455","volume":"15","author":"L Chu","year":"2013","unstructured":"Chu L, Jiang S, Wang S, Zhang Y, Huang Q (2013) Robust spatial consistency graph model for partial duplicate image retrieval. IEEE Transactions on Multimedia 15(8):1982\u20131996","journal-title":"IEEE Transactions on Multimedia"},{"key":"6427_CR7","unstructured":"Donahue J, Jia Y, Vinyals O, Hoffman J, Zhang N, Tzeng E, Darrell T (2014) Decaf: a deep convolutional activation feature for generic visual recognition Icml, vol 32, pp 647\u2013655"},{"issue":"2","key":"6427_CR8","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1109\/TMM.2013.2293063","volume":"16","author":"LY Duan","year":"2014","unstructured":"Duan LY, Ji R, Chen Z, Huang T, Gao W (2014) Towards mobile document image retrieval for digital library. IEEE Transactions on Multimedia 16(2):346\u2013359","journal-title":"IEEE Transactions on Multimedia"},{"issue":"6","key":"6427_CR9","doi-asserted-by":"publisher","first-page":"828","DOI":"10.1109\/TMM.2015.2419973","volume":"17","author":"LY Duan","year":"2015","unstructured":"Duan LY, Lin J, Wang Z, Huang T, Gao W (2015) Weighted component hashing of binary aggregated descriptors for fast visual search. IEEE Transactions on multimedia 17(6):828\u2013842","journal-title":"IEEE Transactions on multimedia"},{"key":"6427_CR10","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"key":"6427_CR11","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 580\u2013587","DOI":"10.1109\/CVPR.2014.81"},{"key":"6427_CR12","doi-asserted-by":"crossref","unstructured":"Gong Y, Wang L, Guo R, Lazebnik S (2014) Multi-scale orderless pooling of deep convolutional activation features. In: European conference on computer vision, pp 392\u2013407. Springer, Berlin","DOI":"10.1007\/978-3-319-10584-0_26"},{"key":"6427_CR13","doi-asserted-by":"crossref","unstructured":"Gordo A, Almaz\u00e1n J, Revaud J, Larlus D (2016) Deep image retrieval: Learning global representations for image search. In: European conference on computer vision, pp 241\u2013257. Springer, Berlin","DOI":"10.1007\/978-3-319-46466-4_15"},{"key":"6427_CR14","doi-asserted-by":"crossref","unstructured":"Gordo A, Larlus D (2017) Beyond instance-level image retrieval: Leveraging captions to learn a global visual representation for semantic retrieval. In: IEEE Conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2017.560"},{"key":"6427_CR15","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2014) Spatial pyramid pooling in deep convolutional networks for visual recognition. In: European conference on computer vision, pp 346\u2013361. Springer, Berlin","DOI":"10.1007\/978-3-319-10578-9_23"},{"key":"6427_CR16","doi-asserted-by":"crossref","unstructured":"Hoang T, Do TT, Le Tan DK, Cheung NM (2017) Selective deep convolutional features for image retrieval. In: Proceedings of the 2017 ACM on Multimedia Conference, pp 1600\u20131608","DOI":"10.1145\/3123266.3123417"},{"issue":"9","key":"6427_CR17","doi-asserted-by":"publisher","first-page":"4128","DOI":"10.1109\/TIP.2017.2710635","volume":"26","author":"R Hong","year":"2017","unstructured":"Hong R, Li L, Cai J, Tao D, Wang M, Tian Q (2017) Coherent semantic-visual indexing for large-scale image retrieval in the cloud. IEEE Trans Image Process 26(9):4128\u20134138","journal-title":"IEEE Trans Image Process"},{"key":"6427_CR18","first-page":"304","volume":"2008","author":"H Jegou","year":"2008","unstructured":"Jegou H, Douze M, Schmid C (2008) Hamming embedding and weak geometric consistency for large scale image search. Computer Vision\u2013ECCV 2008:304\u2013317","journal-title":"Computer Vision\u2013ECCV"},{"issue":"1","key":"6427_CR19","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1109\/TMM.2012.2225035","volume":"15","author":"R Ji","year":"2013","unstructured":"Ji R, Duan LY, Chen J, Xie L, Yao H, Gao W (2013) Learning to distribute vocabulary indexing for scalable visual search. IEEE Transactions on Multimedia 15(1):153\u2013166","journal-title":"IEEE Transactions on Multimedia"},{"issue":"2","key":"6427_CR20","doi-asserted-by":"publisher","first-page":"442","DOI":"10.1109\/TMM.2012.2231061","volume":"15","author":"YG Jiang","year":"2013","unstructured":"Jiang YG, Wang J, Xue X, Chang SF (2013) Query-adaptive image search with hash codes. IEEE transactions on Multimedia 15(2):442\u2013453","journal-title":"IEEE transactions on Multimedia"},{"key":"6427_CR21","doi-asserted-by":"crossref","unstructured":"Kalantidis Y, Mellina C, Osindero S (2016) Cross-dimensional weighting for aggregated deep convolutional features. In: European conference on computer vision, pp 685\u2013701. Springer, Berlin","DOI":"10.1007\/978-3-319-46604-0_48"},{"key":"6427_CR22","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097\u20131105"},{"key":"6427_CR23","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2016) Ssd: Single shot multibox detector. In: European conference on computer vision, pp 21\u201337. Springer, Berlin","DOI":"10.1007\/978-3-319-46448-0_2"},{"issue":"2","key":"6427_CR24","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91\u2013110","journal-title":"Int J Comput Vis"},{"key":"6427_CR25","unstructured":"Noh H, Araujo A, Sim J, Han B (2016) Image retrieval with deep local features and attention-based keypoints. arXiv:\n                    1612.06321"},{"key":"6427_CR26","doi-asserted-by":"crossref","unstructured":"Panda J, Brown MS, Jawahar CV (2013) Offline mobile instance retrieval with a small memory footprint, pp 1257\u20131264","DOI":"10.1109\/ICCV.2013.159"},{"key":"6427_CR27","doi-asserted-by":"crossref","unstructured":"Philbin J, Chum O, Isard M, Sivic J, Zisserman A (2007) Object retrieval with large vocabularies and fast spatial matching. In: IEEE conference on computer vision and pattern recognition, 2007, pp 1\u20138","DOI":"10.1109\/CVPR.2007.383172"},{"key":"6427_CR28","doi-asserted-by":"crossref","unstructured":"Radenovi\u0107 F, Tolias G, Chum O (2016) Cnn image retrieval learns from bow: Unsupervised fine-tuning with hard examples. In: European conference on computer vision, pp 3\u201320. Springer, Berlin","DOI":"10.1007\/978-3-319-46448-0_1"},{"key":"6427_CR29","unstructured":"Razavian AS, Sullivan J, Carlsson S, Maki A (2014) Visual instance retrieval with deep convolutional networks. arXiv:\n                    1412.6574"},{"key":"6427_CR30","doi-asserted-by":"crossref","unstructured":"Redmon J, Farhadi A (2016)","DOI":"10.1515\/lincu-2016-0003"},{"key":"6427_CR31","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: Towards real-time object detection with region proposal networks. In: Advances in neural information processing systems, pp 91\u201399"},{"issue":"3","key":"6427_CR32","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M et al (2015) Imagenet large scale visual recognition challenge. Int J Comput Vis 115(3):211\u2013252","journal-title":"Int J Comput Vis"},{"issue":"3","key":"6427_CR33","doi-asserted-by":"publisher","first-page":"883","DOI":"10.1109\/TMM.2012.2188782","volume":"14","author":"J Sang","year":"2012","unstructured":"Sang J, Xu C, Liu J (2012) User-aware image tag refinement via ternary semantic analysis. IEEE Transactions on Multimedia 14(3):883\u2013895","journal-title":"IEEE Transactions on Multimedia"},{"key":"6427_CR34","unstructured":"Sharif Razavian A, Azizpour H, Sullivan J, Carlsson S (2014) Cnn features off-the-shelf: an astounding baseline for recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 806\u2013813"},{"key":"6427_CR35","unstructured":"Sharma G, Schiele B (2015)"},{"key":"6427_CR36","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:\n                    1409.1556"},{"key":"6427_CR37","doi-asserted-by":"crossref","unstructured":"Sivic J, Zisserman A, et al (2003) Video google: a text retrieval approach to object matching in videos. In: Iccv, vol 2, pp 1470\u20131477","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"6427_CR38","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"6427_CR39","unstructured":"Tolias G, Sicre R, J\u00e9gou H (2015) Particular object retrieval with integral max-pooling of cnn activations. arXiv:\n                    1511.05879"},{"issue":"3","key":"6427_CR40","first-page":"37","volume":"11","author":"S Wang","year":"2015","unstructured":"Wang S, Jiang S (2015) Instre: a new benchmark for instance-level object retrieval and recognition. ACM Transactions on Multimedia Computing Communications, and Applications (TOMM) 11(3):37","journal-title":"ACM Transactions on Multimedia Computing Communications, and Applications (TOMM)"},{"key":"6427_CR41","doi-asserted-by":"publisher","first-page":"478","DOI":"10.1016\/j.neucom.2013.03.004","volume":"119","author":"Y Xie","year":"2013","unstructured":"Xie Y, Jiang S, Huang Q (2013) Weighted visual vocabulary to balance the descriptive ability on general dataset. Neurocomputing 119:478\u2013488","journal-title":"Neurocomputing"},{"key":"6427_CR42","unstructured":"Zheng L, Yang Y, Tian Q (2016) Sift meets cnn: a decade survey of instance retrieval. arXiv:\n                    1608.01807"},{"key":"6427_CR43","doi-asserted-by":"crossref","unstructured":"Zhou W, Lu Y, Li H, Song Y, Tian Q (2010) Spatial coding for large scale partial-duplicate web image search. In: Proceedings of the 18th ACM international conference on Multimedia, pp 511\u2013520. ACM","DOI":"10.1145\/1873951.1874019"},{"issue":"1","key":"6427_CR44","first-page":"4","volume":"9","author":"W Zhou","year":"2013","unstructured":"Zhou W, Li H, Lu Y, Tian Q (2013) Sift match verification by geometric coding for large-scale partial-duplicate web image search. ACM Transactions on Multimedia Computing Communications, and Applications (TOMM) 9(1):4","journal-title":"ACM Transactions on Multimedia Computing Communications, and Applications (TOMM)"},{"key":"6427_CR45","unstructured":"Zisserman A (2014) Triangulation embedding and democratic aggregation for image search. In: Computer vision and pattern recognition, pp 3310\u20133317"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-6427-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-018-6427-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-6427-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,23]],"date-time":"2019-09-23T21:37:41Z","timestamp":1569274661000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-018-6427-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9,13]]},"references-count":45,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2019,5]]}},"alternative-id":["6427"],"URL":"https:\/\/doi.org\/10.1007\/s11042-018-6427-1","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,9,13]]},"assertion":[{"value":"31 July 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 February 2018","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 July 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 September 2018","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}