{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,5]],"date-time":"2026-04-05T05:28:28Z","timestamp":1775366908872,"version":"3.50.1"},"reference-count":69,"publisher":"Springer Science and Business Media LLC","issue":"8-9","license":[{"start":{"date-parts":[[2020,4,23]],"date-time":"2020-04-23T00:00:00Z","timestamp":1587600000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,4,23]],"date-time":"2020-04-23T00:00:00Z","timestamp":1587600000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2020,9]]},"DOI":"10.1007\/s11263-020-01326-x","type":"journal-article","created":{"date-parts":[[2020,4,23]],"date-time":"2020-04-23T03:53:16Z","timestamp":1587613996000},"page":"2325-2343","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Product Quantization Network for Fast Visual Search"],"prefix":"10.1007","volume":"128","author":[{"given":"Tan","family":"Yu","sequence":"first","affiliation":[]},{"given":"Jingjing","family":"Meng","sequence":"additional","affiliation":[]},{"given":"Chen","family":"Fang","sequence":"additional","affiliation":[]},{"given":"Hailin","family":"Jin","sequence":"additional","affiliation":[]},{"given":"Junsong","family":"Yuan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,4,23]]},"reference":[{"key":"1326_CR1","doi-asserted-by":"crossref","unstructured":"Babenko, A., & Lempitsky, V. (2014). Additive quantization for extreme vector compression. In CVPR (pp. 931\u2013938).","DOI":"10.1109\/CVPR.2014.124"},{"key":"1326_CR2","unstructured":"Babenko, A., & Lempitsky, V. (2015). Aggregating local deep features for image retrieval. In ICCV (pp. 1269\u20131277)."},{"key":"1326_CR3","unstructured":"Babenko, A., Slesarev, A., Chigorin, A., & Lempitsky, V. (2014). Neural codes for image retrieval. In ECCV (pp. 584\u2013599). Berlin: Springer."},{"key":"1326_CR4","unstructured":"Bai, S., Bai, X., Tian, Q., & Latecki, L. J. (2018). Regularized diffusion process on bidirectional context for object retrieval. TPAMI."},{"key":"1326_CR5","doi-asserted-by":"crossref","unstructured":"Bai, S., Zhou, Z., Wang, J., Bai, X., Latecki, L. J., & Tian, Q. (2017). Ensemble diffusion for retrieval.","DOI":"10.1109\/ICCV.2017.90"},{"key":"1326_CR6","doi-asserted-by":"crossref","unstructured":"Cakir, F., He, K., Bargal, S. A., & Sclaroff, S. (2017). Mihash: Online hashing with mutual information. In ICCV.","DOI":"10.1109\/ICCV.2017.55"},{"key":"1326_CR7","doi-asserted-by":"crossref","unstructured":"Cao, L., Li, Z., Mu, Y., & Chang, S. F. (2012). Submodular video hashing: a unified framework towards video pooling and indexing. In Proceedings of the 20th ACM international conference on Multimedia (pp. 299\u2013308). ACM.","DOI":"10.1145\/2393347.2393393"},{"key":"1326_CR8","doi-asserted-by":"crossref","unstructured":"Cao, Y., Long, M., Wang, J., Zhu, H., & Wen, Q. (2016). Deep quantization network for efficient image retrieval. In AAAI.","DOI":"10.1609\/aaai.v30i1.10455"},{"key":"1326_CR9","doi-asserted-by":"crossref","unstructured":"Cao, Z., Long, M., Wang, J., & Yu, P. S. (2017). Hashnet: Deep learning to hash by continuation. In ICCV.","DOI":"10.1109\/ICCV.2017.598"},{"key":"1326_CR10","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).","DOI":"10.1145\/509907.509965"},{"issue":"12","key":"1326_CR11","doi-asserted-by":"publisher","first-page":"11259","DOI":"10.3390\/s101211259","volume":"10","author":"Y Chen","year":"2010","unstructured":"Chen, Y., Guan, T., & Wang, C. (2010). Approximate nearest neighbor search by residual vector quantization. Sensors, 10(12), 11259\u201311273.","journal-title":"Sensors"},{"key":"1326_CR12","doi-asserted-by":"crossref","unstructured":"Chua, T. S., Tang, J., Hong, R., Li, H., Luo, Z., & Zheng, Y. (2009). Nus-wide: a real-world web image database from national university of singapore. In Proceedings of the ACM international conference on image and video retrieval (p \u00a048).","DOI":"10.1145\/1646396.1646452"},{"key":"1326_CR13","doi-asserted-by":"crossref","unstructured":"Datar, M., Immorlica, N., Indyk, P., Mirrokni, V. S. (2004). Locality-sensitive hashing scheme based on p-stable distributions. In Proceedings of the twentieth annual symposium on Computational geometry (pp. 253\u2013262).","DOI":"10.1145\/997817.997857"},{"key":"1326_CR14","doi-asserted-by":"crossref","unstructured":"Ge, T., He, K., Ke, Q., & Sun, J. (2013). Optimized product quantization for approximate nearest neighbor search. In CVPR (pp. 2946\u20132953). IEEE.","DOI":"10.1109\/CVPR.2013.379"},{"issue":"12","key":"1326_CR15","doi-asserted-by":"publisher","first-page":"2916","DOI":"10.1109\/TPAMI.2012.193","volume":"35","author":"Y Gong","year":"2013","unstructured":"Gong, Y., Lazebnik, S., Gordo, A., & Perronnin, F. (2013). Iterative quantization: A procrustean approach to learning binary codes for large-scale image retrieval. IEEE T-PAMI, 35(12), 2916\u20132929.","journal-title":"IEEE T-PAMI"},{"key":"1326_CR16","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 ECCV (pp. 241\u2013257). Springer.","DOI":"10.1007\/978-3-319-46466-4_15"},{"key":"1326_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Cakir, F., Bargal, S. A., & Sclaroff, S. (2018). Hashing as tie-aware learning to rank. In CVPR.","DOI":"10.1109\/CVPR.2018.00423"},{"key":"1326_CR18","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770\u2013778)."},{"key":"1326_CR19","doi-asserted-by":"crossref","unstructured":"Hong, W., Meng, J., & Yuan, J. (2018). Distributed composite quantization. In AAAI.","DOI":"10.1609\/aaai.v32i1.11294"},{"key":"1326_CR20","doi-asserted-by":"crossref","unstructured":"Hong, W., Meng, J., & Yuan, J. (2018). Tensorized projection for high-dimensional binary embedding. In AAAI.","DOI":"10.1609\/aaai.v32i1.11292"},{"issue":"10","key":"1326_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIP.2018.2846670","volume":"27","author":"W Hong","year":"2018","unstructured":"Hong, W., & Yuan, J. (2018). Fried binary embedding: From high-dimensional visual features to high-dimensional binary codes. IEEE Transactions on Image Processing, 27(10), 1.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1326_CR22","first-page":"18","volume":"11","author":"W Hong","year":"2017","unstructured":"Hong, W., Yuan, J., & Bhattacharjee, S. D. (2017). Fried binary embedding for high-dimensional visual features. CVPR, 11, 18.","journal-title":"CVPR"},{"key":"1326_CR23","unstructured":"Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International conference on machine learning (pp. 448\u2013456)."},{"key":"1326_CR24","doi-asserted-by":"crossref","unstructured":"Jain, H., Zepeda, J., Perez, P., & Gribonval, R. (2017). Subic: A supervised, structured binary code for image search. In ICCV (pp. 833\u2013842).","DOI":"10.1109\/ICCV.2017.96"},{"issue":"1","key":"1326_CR25","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 T-PAMI, 33(1), 117\u2013128.","journal-title":"IEEE T-PAMI"},{"key":"1326_CR26","unstructured":"J\u00e9gou, H., Douze, M., Schmid, C., & P\u00e9rez, P. (2010). Aggregating local descriptors into a compact image representation. In: CVPR (pp. 3304\u20133311)."},{"key":"1326_CR27","doi-asserted-by":"crossref","unstructured":"Jiang, Q. Y., & Li, W. J. (2018). Asymmetric deep supervised hashing. AAAI.","DOI":"10.1609\/aaai.v32i1.11814"},{"key":"1326_CR28","unstructured":"Klein, B., & Wolf, L. (2017). In defense of product quantization. arXiv preprint arXiv:1711.08589."},{"key":"1326_CR29","unstructured":"Krizhevsky, A. (2009). Learning multiple layers of features from tiny images."},{"key":"1326_CR30","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., & Serre, T. (2011). Hmdb: a large video database for human motion recognition. In IEEE International Conference on Computer Vision (ICCV), 2011 (pp. 2556\u20132563). IEEE.","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"1326_CR31","unstructured":"Lai, H., Pan, Y., Liu, Y., & Yan, S. (2015). Simultaneous feature learning and hash coding with deep neural networks. arXiv preprint arXiv:1504.03410."},{"key":"1326_CR32","unstructured":"Li, Q., Sun, Z., He, R., & Tan, T. (2017). Deep supervised discrete hashing. In NIPS (pp. 2479\u20132488)."},{"key":"1326_CR33","unstructured":"Li, W. J., Wang, S., & Kang, W. C. (2015). Feature learning based deep supervised hashing with pairwise labels. arXiv preprint arXiv:1511.03855"},{"issue":"6","key":"1326_CR34","doi-asserted-by":"publisher","first-page":"1209","DOI":"10.1109\/TMM.2016.2645404","volume":"19","author":"VE Liong","year":"2017","unstructured":"Liong, V. E., Lu, J., Tan, Y. P., & Zhou, J. (2017). Deep video hashing. IEEE Transactions on Multimedia, 19(6), 1209\u20131219.","journal-title":"IEEE Transactions on Multimedia"},{"key":"1326_CR35","doi-asserted-by":"crossref","unstructured":"Liu, H., Wang, R., Shan, S., & Chen, X. (2016). Deep supervised hashing for fast image retrieval. In CVPR (pp. 2064\u20132072).","DOI":"10.1109\/CVPR.2016.227"},{"key":"1326_CR36","doi-asserted-by":"crossref","unstructured":"Liu, W., Wang, J., Ji, R., Jiang, Y. G., & Chang, S. F. (2012). Supervised hashing with kernels. In 2012 IEEE Conference on Computer Vision and Pattern Recognition (pp. 2074\u20132081). IEEE.","DOI":"10.1109\/CVPR.2012.6247912"},{"key":"1326_CR37","unstructured":"Liu, X., Zhao, L., Ding, D., & Dong, Y. (2017). Deep hashing with category mask for fast video retrieval. CoRR arXiv:1712.08315."},{"key":"1326_CR38","doi-asserted-by":"crossref","unstructured":"Martinez, J., Clement, J., Hoos, H. H., & Little, J. J. (2016). Revisiting additive quantization. In European Conference on Computer Vision (pp. 137\u2013153). Springer.","DOI":"10.1007\/978-3-319-46475-6_9"},{"key":"1326_CR39","unstructured":"Ng, J.Y.H., Yang, F., Davis, L. S. (2015). Exploiting local features from deep networks for image retrieval. arXiv preprint arXiv:1504.05133."},{"key":"1326_CR40","doi-asserted-by":"crossref","unstructured":"Norouzi, M., & Fleet, D. J. (2013). Cartesian k-means. In CVPR (pp. 3017\u20133024).","DOI":"10.1109\/CVPR.2013.388"},{"key":"1326_CR41","unstructured":"Norouzi, M., Fleet, D. J., & Salakhutdinov, R. R. (2012). Hamming distance metric learning. In Advances in neural information processing systems (pp. 1061\u20131069)."},{"key":"1326_CR42","doi-asserted-by":"crossref","unstructured":"Perronnin, F., Liu, Y., S\u00e1nchez, J., & Poirier, H. (2010). Large-scale image retrieval with compressed fisher vectors. In CVPR (pp. 3384\u20133391).","DOI":"10.1109\/CVPR.2010.5540009"},{"key":"1326_CR43","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 CVPR (pp. 1\u20138).","DOI":"10.1109\/CVPR.2007.383172"},{"key":"1326_CR44","doi-asserted-by":"crossref","unstructured":"Sablayrolles, A., Douze, M., J\u00e9gou, H., & Usunier, N. (2017). How should we evaluate supervised hashing? In ICASSP.","DOI":"10.1109\/ICASSP.2017.7952453"},{"issue":"3","key":"1326_CR45","first-page":"500","volume":"500","author":"R Salakhutdinov","year":"2007","unstructured":"Salakhutdinov, R., & Hinton, G. (2007). Semantic hashing. RBM, 500(3), 500.","journal-title":"RBM"},{"issue":"12","key":"1326_CR46","doi-asserted-by":"publisher","first-page":"2916","DOI":"10.1109\/TPAMI.2013.136","volume":"35","author":"F Shen","year":"2013","unstructured":"Shen, F., Shen, C., Liu, W., & Shen, H. T. (2013). Supervised discrete hashing. IEEE T-PAMI, 35(12), 2916\u20132929.","journal-title":"IEEE T-PAMI"},{"key":"1326_CR47","unstructured":"Shen, F., Shen, C., Liu, W., & Shen, H. T. (2015). Supervised discrete hashing. In: CVPR (Vol.\u00a02, p.\u00a05)."},{"key":"1326_CR48","unstructured":"Soomro, K., Zamir, A. R., & Shah, M. (2012). Ucf101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402."},{"key":"1326_CR49","doi-asserted-by":"crossref","unstructured":"Tu, Z., Li, H., Zhang, D., Dauwels, J., Li, B., & Yuan, J. (2019). Action-stage emphasized spatio-temporal VLAD for video action recognition. IEEE Transactions on Image Processing.","DOI":"10.1109\/TIP.2018.2890749"},{"key":"1326_CR50","unstructured":"Tu, Z., Xie, W., Qin, Q., Veltkamp, R. C., Li, B., & Yuan, J. Multi-stream cnn: Learning representations based on human-related regions for action recognition. Pattern Recognition."},{"key":"1326_CR51","doi-asserted-by":"crossref","unstructured":"Wang, L., Xiong, Y., Wang, Z., Qiao, Y., Lin, D., Tang, X., & Van\u00a0Gool, L. (2016a). Temporal segment networks: Towards good practices for deep action recognition. In European Conference on Computer Vision (pp. 20\u201336). Springer.","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"1326_CR52","doi-asserted-by":"crossref","unstructured":"Wang, X., Shi, Y., & Kitani, K. M. (2016b). Deep supervised hashing with triplet labels. In ACCV (pp. 70\u201384). Springer.","DOI":"10.1007\/978-3-319-54181-5_5"},{"key":"1326_CR53","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhang, T., Qi, G.J., Tang, J., & Wang, J. (2016c). Supervised quantization for similarity search. In CVPR (pp. 2018\u20132026).","DOI":"10.1109\/CVPR.2016.222"},{"key":"1326_CR54","unstructured":"Weiss, Y., Torralba, A., & Fergus, R. (2009). Spectral hashing. In NIPS (pp. 1753\u20131760)."},{"key":"1326_CR55","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., Manmatha, R., Smola, A. J., & Kr\u00e4henb\u00fchl, P. (2017a). Sampling matters in deep embedding learning. In ICCV.","DOI":"10.1109\/ICCV.2017.309"},{"key":"1326_CR56","doi-asserted-by":"crossref","unstructured":"Wu, G., Liu, L., Guo, Y., Ding, G., Han, J., Shen, J., & Shao, L. (2017b). Unsupervised deep video hashing with balanced rotation. In IJCAI.","DOI":"10.24963\/ijcai.2017\/429"},{"key":"1326_CR57","doi-asserted-by":"crossref","unstructured":"Xia, R., Pan, Y., Lai, H., Liu, C., & Yan, S. (2014). Supervised hashing for image retrieval via image representation learning. In AAAI (pp. 2156\u20132162). AAAI Press.","DOI":"10.1609\/aaai.v28i1.8952"},{"key":"1326_CR58","unstructured":"Xia, Y., He, K., Kohli, P., & Sun, J. (2015). Sparse projections for high-dimensional binary codes. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3332\u20133339)."},{"key":"1326_CR59","doi-asserted-by":"crossref","unstructured":"Ye, G., Liu, D., Wang, J., & Chang, S. F. (2013). Large-scale video hashing via structure learning. In Proceedings of the IEEE International Conference on Computer Vision (pp. 2272\u20132279).","DOI":"10.1109\/ICCV.2013.282"},{"key":"1326_CR60","doi-asserted-by":"crossref","unstructured":"Yu, T., Meng, J., & Yuan, J. (2017a). Is my object in this video? reconstruction-based object search in videos. In Proceedings of the 26th International Joint Conference on Artificial Intelligence (pp. 4551\u20134557). AAAI Press.","DOI":"10.24963\/ijcai.2017\/635"},{"key":"1326_CR61","doi-asserted-by":"crossref","unstructured":"Yu, T., Wang, Z., & Yuan, J. (2017b). Compressive quantization for fast object instance search in videos. In ICCV (pp. 833\u2013842).","DOI":"10.1109\/ICCV.2017.85"},{"key":"1326_CR62","doi-asserted-by":"crossref","unstructured":"Yu, T., Wu, Y., Bhattacharjee, S. D., & Yuan, J. (2017c). Efficient object instance search using fuzzy objects matching. In AAAI.","DOI":"10.1609\/aaai.v31i1.11192"},{"key":"1326_CR63","doi-asserted-by":"crossref","unstructured":"Yu, T., Wu, Y., & Yuan, J. (2017d). Hope: Hierarchical object prototype encoding for efficient object instance search in videos. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2424\u20132433).","DOI":"10.1109\/CVPR.2017.340"},{"key":"1326_CR64","doi-asserted-by":"crossref","unstructured":"Yu, T., Yuan, J., Fang, C., Jin, H. (2018). Product quantization network for fast image retrieval. In Proceedings of the European Conference on Computer Vision (ECCV) (pp. 186\u2013201).","DOI":"10.1007\/978-3-030-01246-5_12"},{"issue":"12","key":"1326_CR65","first-page":"4766","volume":"24","author":"R Zhang","year":"2015","unstructured":"Zhang, R., Lin, L., Zhang, R., Zuo, W., & Zhang, L. (2015). Bit-scalable deep hashing with regularized similarity learning for image retrieval and person re-identification. IEEE TIP, 24(12), 4766\u20134779.","journal-title":"IEEE TIP"},{"key":"1326_CR66","unstructured":"Zhang, T., Du, C., & Wang, J. (2014). Composite quantization for approximate nearest neighbor search. In ICML, 2 (pp. 838\u2013846)."},{"key":"1326_CR67","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Chen, Y., & Saligrama, V. (2016). Efficient training of very deep neural networks for supervised hashing. In CVPR (pp. 1487\u20131495).","DOI":"10.1109\/CVPR.2016.165"},{"key":"1326_CR68","unstructured":"Zhao, F., Huang, Y., Wang, L., & Tan, T. (2015). Deep semantic ranking based hashing for multi-label image retrieval. In CVPR (pp. 1556\u20131564)."},{"key":"1326_CR69","doi-asserted-by":"crossref","unstructured":"Zhu, H., Long, M., Wang, J., & Cao, Y. (2016). Deep hashing network for efficient similarity retrieval. In AAAI.","DOI":"10.1609\/aaai.v30i1.10235"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-020-01326-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-020-01326-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-020-01326-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T02:49:17Z","timestamp":1666406957000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-020-01326-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4,23]]},"references-count":69,"journal-issue":{"issue":"8-9","published-print":{"date-parts":[[2020,9]]}},"alternative-id":["1326"],"URL":"https:\/\/doi.org\/10.1007\/s11263-020-01326-x","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,4,23]]},"assertion":[{"value":"8 March 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 March 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 April 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}