{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T01:38:08Z","timestamp":1777599488385,"version":"3.51.4"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2016,3,9]],"date-time":"2016-03-09T00:00:00Z","timestamp":1457481600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2016,10]]},"DOI":"10.1007\/s11263-016-0889-2","type":"journal-article","created":{"date-parts":[[2016,3,9]],"date-time":"2016-03-09T06:50:36Z","timestamp":1457506236000},"page":"1-13","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":74,"title":["Accurate Image Search with Multi-Scale Contextual Evidences"],"prefix":"10.1007","volume":"120","author":[{"given":"Liang","family":"Zheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengjin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingdong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,3,9]]},"reference":[{"key":"889_CR1","doi-asserted-by":"crossref","unstructured":"Arandjelovi\u0107, R., & Zisserman, A. (2011). Smooth object retrieval using a bag of boundaries. In Computer Vision, IEEE International Conference on (pp. 375\u2013382).","DOI":"10.1109\/ICCV.2011.6126265"},{"key":"889_CR2","doi-asserted-by":"crossref","unstructured":"Arandjelovi\u0107, R., & Zisserman, A. (2012). Three things everyone should know to improve object retrieval. In IEEE Conference on Computer Vision and Pattern Recognition (pp. 2911\u20132918).","DOI":"10.1109\/CVPR.2012.6248018"},{"key":"889_CR3","unstructured":"Babenko, A., Slesarev, A., Chigorin, A., & Lempitsky, V. (2014). Neural codes for image retrieval. arXiv preprint arXiv:1404.1777 ."},{"key":"889_CR4","doi-asserted-by":"crossref","unstructured":"Carson, C., Thomas, M., Belongie, S., Hellerstein, J. M., & Malik, J. (1999). Blobworld: A system for region-based image indexing and retrieval. In Visual Information and Information Systems (pp. 509\u2013517).","DOI":"10.1007\/3-540-48762-X_63"},{"key":"889_CR5","doi-asserted-by":"crossref","unstructured":"Charikar, M. S. (2002). Similarity estimation techniques from rounding algorithms. In Proceedings of the 34th annual ACM symposium on theory of computing (pp. 380\u2013388). ACM.","DOI":"10.1145\/509907.509965"},{"issue":"9","key":"889_CR6","doi-asserted-by":"crossref","first-page":"1252","DOI":"10.1109\/TPAMI.2002.1033216","volume":"24","author":"Y Chen","year":"2002","unstructured":"Chen, Y., & Wang, J. Z. (2002). A region-based fuzzy feature matching approach to content-based image retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(9), 1252\u20131267.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"889_CR7","doi-asserted-by":"crossref","unstructured":"Chum, O., Philbin, J., Sivic, J., Isard, M., & Zisserman, A. (2007). Total recall: Automatic query expansion with a generative feature model for object retrieval. In IEEE International Conference on Computer Vision (pp. 1\u20138).","DOI":"10.1109\/ICCV.2007.4408891"},{"key":"889_CR8","doi-asserted-by":"crossref","unstructured":"Deng, C., Ji, R., Liu, W., Tao, D., & Gao, X. (2013). Visual reranking through weakly supervised multi-graph learning. In IEEE International Conference on Computer Vision (pp. 2600\u20132607).","DOI":"10.1109\/ICCV.2013.323"},{"key":"889_CR9","unstructured":"Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., & Darrell, T. (2013). Decaf: A deep convolutional activation feature for generic visual recognition. arXiv preprint arXiv:1310.1531 ."},{"key":"889_CR10","doi-asserted-by":"crossref","unstructured":"Fang, Q., Sang, J., & Xu, C. (2013). Giant: Geo-informative attributes for location recognition and exploration. In Proceedings of the 21st ACM international conference on Multimedia (pp. 13\u201322).","DOI":"10.1145\/2502081.2502088"},{"key":"889_CR11","doi-asserted-by":"crossref","unstructured":"Ge, T., Ke, Q., & Sun, J. (2013). Sparse-coded features for image retrieval. In British Machine Vision Conference, vol. 6.","DOI":"10.5244\/C.27.132"},{"key":"889_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.","DOI":"10.1007\/978-3-319-10584-0_26"},{"key":"889_CR13","doi-asserted-by":"crossref","unstructured":"Huiskes, M. J., Thomee, B., & Lew, M. S. (2010). New trends and ideas in visual concept detection: The mir flickr retrieval evaluation initiative. In Proceedings of the international conference on multimedia information retrieval (pp. 527\u2013536). ACM.","DOI":"10.1145\/1743384.1743475"},{"key":"889_CR14","doi-asserted-by":"crossref","unstructured":"Jegou, H., Douze, M., & Schmid, C. (2008). Hamming embedding and weak geometric consistency for large scale image search. In European Conference on Computer Vision (pp. 304\u2013317). Springer.","DOI":"10.1007\/978-3-540-88682-2_24"},{"key":"889_CR15","doi-asserted-by":"crossref","unstructured":"J\u00e9gou, H., Douze, M., & Schmid, C. (2009). On the burstiness of visual elements. In IEEE Conference on Computer Vision and Pattern Recognition (pp. 1169\u20131176).","DOI":"10.1109\/CVPR.2009.5206609"},{"issue":"3","key":"889_CR16","doi-asserted-by":"crossref","first-page":"316","DOI":"10.1007\/s11263-009-0285-2","volume":"87","author":"H J\u00e9gou","year":"2010","unstructured":"J\u00e9gou, H., Douze, M., & Schmid, C. (2010). Improving bag-of-features for large scale image search. International Journal of Computer Vision, 87(3), 316\u2013336.","journal-title":"International Journal of Computer Vision"},{"issue":"9","key":"889_CR17","doi-asserted-by":"crossref","first-page":"1704","DOI":"10.1109\/TPAMI.2011.235","volume":"34","author":"H J\u00e9gou","year":"2012","unstructured":"J\u00e9gou, H., Perronnin, F., Douze, M., Sanchez, J., Perez, P., & Schmid, C. (2012). Aggregating local image descriptors into compact codes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(9), 1704\u20131716.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"889_CR18","doi-asserted-by":"crossref","unstructured":"Lazebnik, S., Schmid, C., & Ponce, J. (2006). Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In IEEE Conference on Computer Vision and Pattern Recognition (vol. 2, pp. 2169\u20132178).","DOI":"10.1109\/CVPR.2006.68"},{"issue":"11","key":"889_CR19","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278\u20132324.","journal-title":"Proceedings of the IEEE"},{"key":"889_CR20","doi-asserted-by":"crossref","unstructured":"LeCun, Y., Huang, F. J., & Bottou, L. (2004). Learning methods for generic object recognition with invariance to pose and lighting. In CVPR (pp. 90\u201397).","DOI":"10.1109\/CVPR.2004.1315150"},{"key":"889_CR21","doi-asserted-by":"crossref","unstructured":"Li, X., Larson, M., & Hanjalic, A. (2015). Pairwise geometric matching for large-scale object retrieval. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","DOI":"10.1007\/978-1-4471-6741-9"},{"issue":"2","key":"889_CR22","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2), 91\u2013110.","journal-title":"International Journal of Computer Vision"},{"issue":"8","key":"889_CR23","doi-asserted-by":"crossref","first-page":"837","DOI":"10.1109\/34.531803","volume":"18","author":"BS Manjunath","year":"1996","unstructured":"Manjunath, B. S., & Ma, W. Y. (1996). Texture features for browsing and retrieval of image data. IEEE Transactions on Pattern Analysis and Machine Intelligence, 18(8), 837\u2013842.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"6","key":"889_CR24","doi-asserted-by":"crossref","first-page":"703","DOI":"10.1109\/76.927424","volume":"11","author":"BS Manjunath","year":"2001","unstructured":"Manjunath, B. S., Ohm, J. R., Vasudevan, V. V., & Yamada, A. (2001). Color and texture descriptors. IEEE Transactions on Circuits and Systems for Video Technology, 11(6), 703\u2013715.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"889_CR25","doi-asserted-by":"crossref","unstructured":"Niester, D., & Stewenius, H. (2006). Scalable recognition with a vocabulary tree. In CVPR.","DOI":"10.1109\/CVPR.2006.264"},{"issue":"3","key":"889_CR26","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1023\/A:1011139631724","volume":"42","author":"A Oliva","year":"2001","unstructured":"Oliva, A., & Torralba, A. (2001). Modeling the shape of the scene: A holistic representation of the spatial envelope. International Journal of Computer Vision, 42(3), 145\u2013175.","journal-title":"International Journal of Computer Vision"},{"key":"889_CR27","doi-asserted-by":"crossref","unstructured":"Perd\u2019och, M., Chum, O., & Matas, J. (2009). Efficient representation of local geometry for large scale object retrieval. In IEEE Conference on Computer Vision and Pattern Recognition (pp. 9\u201316).","DOI":"10.1109\/CVPR.2009.5206529"},{"key":"889_CR28","doi-asserted-by":"crossref","unstructured":"Perronnin, F., Liu, Y., S\u00e1nchez, J., & Poirier, H. (2010). Large-scale image retrieval with compressed fisher vectors. In IEEE Conference on Computer Vision and Pattern Recognition (pp. 3384\u20133391).","DOI":"10.1109\/CVPR.2010.5540009"},{"key":"889_CR29","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 (pp. 1\u20138).","DOI":"10.1109\/CVPR.2007.383172"},{"key":"889_CR30","doi-asserted-by":"crossref","unstructured":"Qin, D., Wengert, C., & Van Gool, L. (2013). Query adaptive similarity for large scale object retrieval. In IEEE Conference on Computer Vision and Pattern Recognition (pp. 1610\u20131617).","DOI":"10.1109\/CVPR.2013.211"},{"key":"889_CR31","doi-asserted-by":"crossref","unstructured":"Razavian, A. S., Azizpour, H., Sullivan, J., & Carlsson, S. (2014) Cnn features off-the-shelf: An astounding baseline for recognition. In IEEE Conference on Computer Vision and Pattern Recognition Workshops (pp. 512\u2013519).","DOI":"10.1109\/CVPRW.2014.131"},{"key":"889_CR32","unstructured":"Shen, X., Lin, Z., Brandt, J., Avidan, S., & Wu, Y. (2012). Object retrieval and localization with spatially-constrained similarity measure and k-nn re-ranking. In CVPR."},{"key":"889_CR33","unstructured":"Shi, M., Avrithis, Y., & J\u00e9gou, H. (2015). Early burst detection for memory-efficient image retrieval. In Computer Vision and Pattern Recognition."},{"key":"889_CR34","unstructured":"Souvannavong, F., Merialdo, B., & Huet, B. (2005). Region-based video content indexing and retrieval. In International Workshop on Content-Based Multimedia Indexing. Citeseer."},{"key":"889_CR35","doi-asserted-by":"crossref","unstructured":"Tao, R., Gavves, E., Snoek, C. G., & Smeulders, A. W. (2014). Locality in generic instance search from one example. In IEEE Conference onComputer Vision and Pattern Recognition (CVPR), 2014 (pp. 2099\u20132106). IEEE.","DOI":"10.1109\/CVPR.2014.269"},{"key":"889_CR36","doi-asserted-by":"crossref","unstructured":"Tolias, G., Avrithis, Y., J\u00e9gou, H. (2013). To aggregate or not to aggregate: Selective match kernels for image search. In IEEE International Conference on Computer Vision (pp. 1401\u20131408).","DOI":"10.1109\/ICCV.2013.177"},{"key":"889_CR37","doi-asserted-by":"crossref","unstructured":"Van Gemert, J. C., Veenman, C. J., Smeulders, A. W., & Geusebroek, J. M. (2010). Visual word ambiguity. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(7), 1271\u20131283.","DOI":"10.1109\/TPAMI.2009.132"},{"key":"889_CR38","unstructured":"Wang, J., Shen, H. T., Song, J., & Ji, J. (2014). Hashing for similarity search: A survey. arXiv preprint arXiv:1408.2927 ."},{"key":"889_CR39","doi-asserted-by":"crossref","unstructured":"Wengert, C., Douze, M., & J\u00e9gou, H. (2011). Bag-of-colors for improved image search. In ACM international conference on Multimedia (pp. 1437\u20131440).","DOI":"10.1145\/2072298.2072034"},{"key":"889_CR40","volume-title":"Hadoop: The definitive guide","author":"T White","year":"2012","unstructured":"White, T. (2012). Hadoop: The definitive guide. Sebastopol, CA: O\u2019Reilly Media, Inc."},{"issue":"8","key":"889_CR41","doi-asserted-by":"crossref","first-page":"1489","DOI":"10.1109\/TPAMI.2010.224","volume":"33","author":"J Wu","year":"2011","unstructured":"Wu, J., & Rehg, J. M. (2011). Centrist: A visual descriptor for scene categorization. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(8), 1489\u20131501.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"889_CR42","doi-asserted-by":"crossref","unstructured":"Xie, L., Tian, Q., Hong, R., & Zhang, B. (2015). Image classification and retrieval are one. In International Conference on Multimedia Retrieval.","DOI":"10.1145\/2671188.2749289"},{"key":"889_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, H., Zha, Z. J., Yang, Y., Yan, S., Gao, Y., & Chua, T. S. (2013). Attribute-augmented semantic hierarchy: Towards bridging semantic gap and intention gap in image retrieval. In ACM international conference on Multimedia (pp. 33\u201342).","DOI":"10.1145\/2502081.2502093"},{"key":"889_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, S., Yang, M., Cour, T., Yu, K., & Metaxas, D. N. (2012). Query specific fusion for image retrieval. In European Conference on Computer Vision (pp. 660\u2013673). Springer.","DOI":"10.1007\/978-3-642-33709-3_47"},{"key":"889_CR45","unstructured":"Zhang, S., Yang, M., Wang, X., Lin, Y., & Tian, Q. (2013). Semantic-aware co-indexing for near-duplicate image retrieval. In IEEE International Conference on Computer Vision (pp. 1673\u20131680)."},{"key":"889_CR46","doi-asserted-by":"crossref","unstructured":"Zheng, L., Wang, S., Liu, Z., & Tian, Q. (2014). Packing and padding: Coupled multi-index for accurate image retrieval. In CVPR 2014.","DOI":"10.1109\/CVPR.2014.250"},{"key":"889_CR47","doi-asserted-by":"crossref","unstructured":"Zheng, L., Wang, S., Tian, L., He, F., Liu, Z., & Tian, Q. (2015). Query-adaptive late fusion for image search and person re-identification. In IEEE Conference on Computer Vision and Pattern Recognition (pp. 1741\u20131750).","DOI":"10.1109\/CVPR.2015.7298783"},{"key":"889_CR48","doi-asserted-by":"crossref","unstructured":"Zheng, L., Wang, S., Zhou, W., & Tian, Q. (2014). Bayes merging of multiple vocabularies for scalable image retrieval. In CVPR.","DOI":"10.1109\/CVPR.2014.252"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-016-0889-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-016-0889-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-016-0889-2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,5]],"date-time":"2019-09-05T10:25:46Z","timestamp":1567679146000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-016-0889-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3,9]]},"references-count":48,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2016,10]]}},"alternative-id":["889"],"URL":"https:\/\/doi.org\/10.1007\/s11263-016-0889-2","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,3,9]]}}}