{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T12:10:05Z","timestamp":1771503005210,"version":"3.50.1"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"17","license":[{"start":{"date-parts":[[2018,5,5]],"date-time":"2018-05-05T00:00:00Z","timestamp":1525478400000},"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":"crossref","award":["61672361"],"award-info":[{"award-number":["61672361"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61371194"],"award-info":[{"award-number":["61371194"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100004826","name":"Natural Science Foundation of Beijing Municipality","doi-asserted-by":"crossref","award":["4152012"],"award-info":[{"award-number":["4152012"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100014380","name":"Beijing Advanced Innovation Center for Imaging Technology","doi-asserted-by":"crossref","award":["BAICIT-2016006"],"award-info":[{"award-number":["BAICIT-2016006"]}],"id":[{"id":"10.13039\/100014380","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2018,9]]},"DOI":"10.1007\/s11042-018-5955-z","type":"journal-article","created":{"date-parts":[[2018,5,4]],"date-time":"2018-05-04T22:01:48Z","timestamp":1525471308000},"page":"22319-22338","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Hierarchical BoW with segmental sparse coding for large scale image classification and retrieval"],"prefix":"10.1007","volume":"77","author":[{"given":"Jianshe","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"Narentuya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sheng","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,5,5]]},"reference":[{"key":"5955_CR1","doi-asserted-by":"crossref","unstructured":"Avrithis Y, Kalantidis Y (2012) Approximate gaussian mixtures for large scale vocabularies. In: Proc of ECCV","DOI":"10.1007\/978-3-642-33712-3_2"},{"key":"5955_CR2","doi-asserted-by":"crossref","unstructured":"Chua T-S, Tang S, Trichet R, Tan HK, Song Y (2009) Moviebase: A movie database for event detection and behavioral analysis. In: Proceedings of ACM multimedia 2009 workshop on Web-Scale multimedia corpus","DOI":"10.1145\/1631135.1631143"},{"key":"5955_CR3","doi-asserted-by":"crossref","unstructured":"Deng J, Berg AC, Li K, Fei-Fei L (2010) What does classifying more than 10,000 image categories tell us? . In: Proc of the 11th European conference on computer vision: Part V, ECCV\u201910. Springer, Berlin, pp 71\u201384","DOI":"10.1007\/978-3-642-15555-0_6"},{"key":"5955_CR4","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L-J, Li K, Fei-fei L (2009) Imagenet: A large-scale hierarchical image database. In: Proc of conference on computer vision and pattern recognition (CVPR). \n                    http:\/\/image-net.org\/","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"4","key":"5955_CR5","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1109\/MSP.2011.940881","volume":"28","author":"B Girod","year":"2011","unstructured":"Girod B, Chandrasekhar V, Chen DM, Cheung NM, Grzeszczuk R, Reznik Y, Takacs G, Tsai SS, Vedantham R. (2011) Mobile visual search. IEEE Signal Processing Magazine, Special Issue on Media Search in Mobile Devices 28 (4):61\u201376","journal-title":"IEEE Signal Processing Magazine, Special Issue on Media Search in Mobile Devices"},{"issue":"2","key":"5955_CR6","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1214\/009053604000000067","volume":"32","author":"T Hastie","year":"2004","unstructured":"Hastie T, Iain J, Efron B, Tibshirani R (2004) Least angle regression. Ann Stat 32(2):407\u2013499","journal-title":"Ann Stat"},{"issue":"3","key":"5955_CR7","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1007\/s11263-009-0285-2","volume":"87","author":"H Jegou","year":"2010","unstructured":"Jegou H, Douze M, Schmid C (2010) Improving bag-of-features for large scale image search. Int J Comput Vis 87(3):316\u2013336","journal-title":"Int J Comput Vis"},{"key":"5955_CR8","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1109\/TPAMI.2010.57","volume":"33","author":"H Jegou","year":"2011","unstructured":"Jegou H, Douze M, Schmid C (2011) Product quantization for nearest neighbor search. IEEE Trans Pattern Anal Mach Intell 33:117\u2013128","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"1","key":"5955_CR9","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1109\/TMM.2009.2036235","volume":"12","author":"Y-G Jiang","year":"2010","unstructured":"Jiang Y-G, Yang J, Ngo C-W, Hauptmann AG (2010) Representations of keypoint-based semantic concept detection A comprehensive study. IEEE Trans Multimedia 12(1):42\u201353","journal-title":"IEEE Trans Multimedia"},{"issue":"6755","key":"5955_CR10","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1038\/44565","volume":"401","author":"DD Lee","year":"1999","unstructured":"Lee DD, Seung HS (1999) Learning the parts of objects by non-negative matrix factorization. Nature 401(6755):788\u2013791","journal-title":"Nature"},{"key":"5955_CR11","doi-asserted-by":"crossref","unstructured":"Li D, Yang L, Hua XS, Zhang HJ (2010) Large-scale robust visual codebook construction. In: ACM Multimedia \u201910","DOI":"10.1145\/1873951.1874182"},{"key":"5955_CR12","unstructured":"Li P, Lu X, Wang Q (2015) From dictionary of visual words to subspaces Locality-constrained affine subspace coding. In: Proc of conference on computer vision and pattern recognition (CVPR), pp 2348\u20132357"},{"issue":"4","key":"5955_CR13","doi-asserted-by":"publisher","first-page":"1561","DOI":"10.1109\/TIP.2017.2779270","volume":"27","author":"Y Li","year":"2018","unstructured":"Li Y, Tang S, Lin M, Zhang Y, Li J, Yan S (2018) Implicit negative sub-categorization and sink diversion for object detection. IEEE Trans Image Process 27(4):1561\u20131574","journal-title":"IEEE Trans Image Process"},{"key":"5955_CR14","doi-asserted-by":"crossref","unstructured":"Liu J, Tang S, Li Y (2017) Collaborative dictionary learning and soft assignment for sparse coding of image features. In: MultiMedia Modeling - 23rd International Conference, MMM 2017, Reykjavik, Iceland, January 4-6, 2017, Proceedings, Part I, pp 443\u2013451","DOI":"10.1007\/978-3-319-51811-4_36"},{"key":"5955_CR15","first-page":"19","volume":"11","author":"J Mairal","year":"2010","unstructured":"Mairal J, Bach F, Ponce J, Sapiro G (2010) Online learning for matrix factorization and sparse coding. J Mach Learn Res 11:19\u201360","journal-title":"J Mach Learn Res"},{"key":"5955_CR16","doi-asserted-by":"crossref","unstructured":"Mantziou E, Papadopoulos S, Kompatsiaris Y (2013) Scalable training with approximate incremental laplacian eigenmaps and pca. In: Proceedings of the 21st ACM international conference on Multimedia, ACM Multimedia, pp 381\u2013384","DOI":"10.1145\/2502081.2508124"},{"issue":"1","key":"5955_CR17","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1007\/s11263-012-0600-1","volume":"103","author":"A Mikulik","year":"2013","unstructured":"Mikulik A, Perdoch M, Chum O, Matas J (2013) Learning vocabularies over a fine quantization. Int J Comput Vis 103(1):163\u2013175","journal-title":"Int J Comput Vis"},{"issue":"11","key":"5955_CR18","doi-asserted-by":"publisher","first-page":"2227","DOI":"10.1109\/TPAMI.2014.2321376","volume":"36","author":"M Muja","year":"2014","unstructured":"Muja M, Lowe DG (2014) Scalable nearest neighbor algorithms for high dimensional data. IEEE Trans Pattern Anal Mach Intell 36(11):2227\u20132240","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5955_CR19","doi-asserted-by":"crossref","unstructured":"Nie L, Yan S, Wang M, Hong R, Chua T-S (2012) Harvesting visual concepts for image search with complex queries. In: Proc of ACM multimedia 2012 conference","DOI":"10.1145\/2393347.2393363"},{"key":"5955_CR20","doi-asserted-by":"crossref","unstructured":"Nister D, Stewenius H (2006) Scalable recognition with a vocabulary tree. In: Proc of conference on computer vision and pattern recognition (CVPR), pp 2161\u20132168","DOI":"10.1109\/CVPR.2006.264"},{"issue":"5","key":"5955_CR21","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1109\/79.879339","volume":"17","author":"FAP Petitcolas","year":"2000","unstructured":"Petitcolas FAP (2000) Watermarking schemes evaluation. IEEE Signal Process 17(5):117\u2013128","journal-title":"IEEE Signal Process"},{"key":"5955_CR22","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: Proc of conference on computer vision and pattern recognition (CVPR), pp 1\u20138","DOI":"10.1109\/CVPR.2007.383172"},{"key":"5955_CR23","doi-asserted-by":"crossref","unstructured":"Philbin J , Chum O, Isard M, Sivic J, Zisserman A (2008) Lost in quantization: improving particular object retrieval in large scale image databases. In: Proc of conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2008.4587635"},{"key":"5955_CR24","doi-asserted-by":"crossref","unstructured":"Sivic J, Zisserman A (2003) Video google: a text retrieval approach to object matching in videos. In: Proc of ICCV, pp 1470\u20131477","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"5955_CR25","unstructured":"Strelow D, Bengio S, Pereira F, Singer Y (2009) Group sparse coding. In: Neural information processing systems - NIPS"},{"key":"5955_CR26","unstructured":"Stricker MA, Orengo M (1995) Similarity of color images. In: SPIE conference on storage and retrieval for image and video databases III, vol 2420, pp 381\u2013392"},{"key":"5955_CR27","doi-asserted-by":"crossref","unstructured":"Tang S, Chen H, Lv K, Zhang YD (2015) Large visual words for large scale image classification. In: 2015 IEEE international conference on image processing (ICIP), pp 1170\u20131174","DOI":"10.1109\/ICIP.2015.7350984"},{"key":"5955_CR28","unstructured":"Tang S, Li J-T, Li M, Xie C, Liu Y-Z, Tao K, Xu S-X (2008) TRECVID 2008 High-Level feature extraction By MCG-ICT-CAS. In: Proceedings of TRECVID 2008 Workshop"},{"issue":"9","key":"5955_CR29","doi-asserted-by":"publisher","first-page":"2105","DOI":"10.1109\/TMM.2017.2729786","volume":"19","author":"S Tang","year":"2017","unstructured":"Tang S, Li Y, Deng L, Zhang Y-D (2017) Object localization based on proposal fusion. IEEE Trans Multimedia 19(9):2105\u20132116","journal-title":"IEEE Trans Multimedia"},{"key":"5955_CR30","doi-asserted-by":"crossref","unstructured":"Tang S, Zhang YD, Chen H (2015) Scalable logo recognition based on compact sparse dictionary for mobile devices. In: 2015 IEEE 17th international workshop on multimedia signal processing (MMSP), pp 1\u20136","DOI":"10.1109\/MMSP.2015.7340863"},{"key":"5955_CR31","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1016\/j.neucom.2014.09.100","volume":"69","author":"S Tang","year":"2015","unstructured":"Tang S, Zhang YD, Xua Z-X, Li H, Zheng Y-T, Li J-T (2015) An efficient concept detection system via sparse ensemble learning. Neurocomputing 69:124\u2013133","journal-title":"Neurocomputing"},{"issue":"1","key":"5955_CR32","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1109\/TMM.2011.2168198","volume":"14","author":"S Tang","year":"2012","unstructured":"Tang S, Zheng Y-T, Wang Y, Chua T-S (2012) Sparse ensemble learning for concept detection. IEEE Trans Multimedia 14(1):43\u201354","journal-title":"IEEE Trans Multimedia"},{"issue":"5","key":"5955_CR33","doi-asserted-by":"publisher","first-page":"733","DOI":"10.1109\/TCSVT.2009.2017400","volume":"19","author":"M Wang","year":"2010","unstructured":"Wang M, Hua X-S, Hong R, Tang J, Qi G-J, Song Y (2010) Unified video annotation via multi-graph learning. IEEE Trans Circuits Syst Video Technol 19 (5):733\u2013746","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"5955_CR34","unstructured":"Wu C (2007) SiftGPU: a GPU implementation of scale invariant feature transform (SIFT) \n                    http:\/\/cs.unc.edu\/ccwu\/siftgpu"},{"issue":"6","key":"5955_CR35","doi-asserted-by":"publisher","first-page":"1319","DOI":"10.1109\/TMM.2011.2167224","volume":"13","author":"H Xie","year":"2011","unstructured":"Xie H, Ke G, Zhang Y, Tang S, Li J, Liu Y (2011) Efficient feature detection and effective post-verification for large scale near-duplicate image search. IEEE Trans Multimedia 13(6):1319\u20131332","journal-title":"IEEE Trans Multimedia"},{"key":"5955_CR36","unstructured":"Yang J, Yu K, Gong Y, Huang T (2009) Linear spatial pyramid matching using sparse coding for image classification. In: Proc of Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"5955_CR37","doi-asserted-by":"crossref","unstructured":"Zhang H, Berg AC, Maire M, Malik J (2006) Svm-knn: Discriminative nearest neighbor classification for visual category recognition. In: Proc of conference on computer vision and pattern recognition (CVPR), pp 2126\u20132136","DOI":"10.1109\/CVPR.2006.301"},{"key":"5955_CR38","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.cviu.2014.01.011","volume":"124","author":"YD Zhang","year":"2014","unstructured":"Zhang YD, Wang Y, Tang S, Hoi SCH, Li JT (2014) Fsph: fitted spectral hashing for efficient similarity search. Comput Vis Image Underst 124:3\u201311","journal-title":"Comput Vis Image Underst"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-018-5955-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-5955-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-5955-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,6]],"date-time":"2019-05-06T10:19:13Z","timestamp":1557137953000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-018-5955-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5,5]]},"references-count":38,"journal-issue":{"issue":"17","published-print":{"date-parts":[[2018,9]]}},"alternative-id":["5955"],"URL":"https:\/\/doi.org\/10.1007\/s11042-018-5955-z","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,5,5]]},"assertion":[{"value":"28 September 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 March 2018","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 March 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 May 2018","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}