{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T06:20:18Z","timestamp":1742970018042,"version":"3.40.3"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030260743"},{"type":"electronic","value":"9783030260750"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-26075-0_4","type":"book-chapter","created":{"date-parts":[[2019,7,24]],"date-time":"2019-07-24T23:05:48Z","timestamp":1564009548000},"page":"42-56","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Supervised Hashing with Recurrent Scaling"],"prefix":"10.1007","author":[{"given":"Xiyao","family":"Fu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Bin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qin","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Si","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,7,17]]},"reference":[{"key":"4_CR1","doi-asserted-by":"crossref","unstructured":"Yao, L., et al.: Describing videos by exploiting temporal structure. In: ICCV, pp. 4507\u20134515 (2015)","DOI":"10.1109\/ICCV.2015.512"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Bergstra, J., et al.: Theano: a CPU and GPU math compiler in Python. In: Proceedings of 9th Python in Science Conference, vol. 1, pp. 3\u201310, June 2010","DOI":"10.25080\/Majora-92bf1922-003"},{"key":"4_CR3","doi-asserted-by":"crossref","unstructured":"Zhang, H., Wang, M., Hong, R., Chua, T.S.: Play and rewind: optimizing binary representations of videos by self-supervised temporal hashing. In: ACM Multimedia, pp. 781\u2013790, October 2016","DOI":"10.1145\/2964284.2964308"},{"issue":"12","key":"4_CR4","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.: Iterative quantization: a procrustean approach to learning binary codes for large-scale image retrieval. TPAMI 35(12), 2916\u20132929 (2013)","journal-title":"TPAMI"},{"key":"4_CR5","unstructured":"Liu, W., Wang, J., Ji, R., Jiang, Y.G., Chang, S.F.: Supervised hashing with kernels. In: CVPR, pp. 2074\u20132081, June 2012"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Fang, H., et al.: From captions to visual concepts and back. In: CVPR, pp. 1473\u20131482 (2015)","DOI":"10.1109\/CVPR.2015.7298754"},{"issue":"7","key":"4_CR7","first-page":"3210","volume":"27","author":"J Song","year":"2018","unstructured":"Song, J., Zhang, H., Li, X., Gao, L., Wang, M., Hong, R.: Self-supervised video hashing with hierarchical binary auto-encoder. TIP 27(7), 3210\u20133221 (2018)","journal-title":"TIP"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Shen, F., Shen, C., Liu, W., Tao Shen, H.: Supervised discrete hashing. In: CVPR, pp. 37\u201345 (2015)","DOI":"10.1109\/CVPR.2015.7298598"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Xia, R., Pan, Y., Lai, H., Liu, C., Yan, S.: Supervised hashing for image retrieval via image representation learning. In: AAAI, June 2014","DOI":"10.1609\/aaai.v28i1.8952"},{"key":"4_CR10","unstructured":"Weiss, Y., Torralba, A., Fergus, R.: Spectral hashing. In: NIPS, pp. 1753\u20131760 (2009)"},{"key":"4_CR11","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: ICML, pp. 2048\u20132057, June 2015"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Bin, Y., Yang, Y., Zhou, J., Huang, Z., Shen, H.T.: Adaptively attending to visual attributes and linguistic knowledge for captioning. In: ACM Multimedia, pp. 1345\u20131353, October 2017","DOI":"10.1145\/3123266.3123391"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Jia, Y.: Caffe: convolutional architecture for fast feature embedding. In: ACM Multimedia, pp. 675\u2013678, November 2014","DOI":"10.1145\/2647868.2654889"},{"key":"4_CR14","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)"},{"key":"4_CR15","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICLR (2015)"},{"key":"4_CR16","unstructured":"Tang, Y., Srivastava, N., Salakhutdinov, R.R.: Learning generative models with visual attention. In: NIPS, pp. 1808\u20131816 (2014)"},{"key":"4_CR17","doi-asserted-by":"crossref","unstructured":"Zhu, H., Long, M., Wang, J., Cao, Y.: Deep hashing network for efficient similarity retrieval. In: AAAI, March 2016","DOI":"10.1609\/aaai.v30i1.10235"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Chua, T.S., Tang, J., Hong, R., Li, H., Luo, Z., Zheng, Y.: NUS-WIDE: a real-world web image database from National University of Singapore. In: ACM CIVR, p. 48, July 2009","DOI":"10.1145\/1646396.1646452"},{"key":"4_CR19","unstructured":"Gionis, A., Indyk, P., Motwani, R.: Similarity search in high dimensions via hashing. In: VLDB, vol. 99, no. 6, pp. 518\u2013529, September 1999"},{"key":"4_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"4_CR21","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS, pp. 1097\u20131105 (2012)"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Yao, T., Pan, Y., Li, Y., Qiu, Z., Mei, T.: Boosting image captioning with attributes. In: ICCV, pp. 4894\u20134902 (2017)","DOI":"10.1109\/ICCV.2017.524"},{"issue":"6","key":"4_CR23","doi-asserted-by":"publisher","first-page":"1367","DOI":"10.1109\/TPAMI.2017.2708709","volume":"40","author":"Q Wu","year":"2018","unstructured":"Wu, Q., Shen, C., Wang, P., Dick, A., van den Hengel, A.: Image captioning and visual question answering based on attributes and external knowledge. TPAMI 40(6), 1367\u20131381 (2018)","journal-title":"TPAMI"},{"key":"4_CR24","doi-asserted-by":"crossref","unstructured":"Liu, H., Wang, R., Shan, S., Chen, X.: Deep supervised hashing for fast image retrieval. In: CVPR, pp. 2064\u20132072 (2016)","DOI":"10.1109\/CVPR.2016.227"},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"Cao, Z., Long, M., Wang, J., Yu, P.S.: Hashnet: deep learning to hash by continuation. In: ICCV, pp. 5608\u20135617 (2017)","DOI":"10.1109\/ICCV.2017.598"},{"key":"4_CR26","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: ICLR (2014)"},{"key":"4_CR27","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.: Glove: global vectors for word representation. In: EMNLP, pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"4_CR28","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: a unified embedding for face recognition and clustering. In: CVPR, pp. 815\u2013823 (2015)","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"4_CR29","doi-asserted-by":"crossref","unstructured":"Cheng, D., Gong, Y., Zhou, S., Wang, J., Zheng, N.: Person re-identification by multi-channel parts-based CNN with improved triplet loss function. In: CVPR, pp. 1335\u20131344 (2016)","DOI":"10.1109\/CVPR.2016.149"},{"key":"4_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"472","DOI":"10.1007\/978-3-030-01261-8_28","volume-title":"Computer Vision \u2013 ECCV 2018","author":"X Dong","year":"2018","unstructured":"Dong, X., Shen, J.: Triplet loss in siamese network for object tracking. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 472\u2013488. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_28"},{"key":"4_CR31","doi-asserted-by":"crossref","unstructured":"Zhu, X., Zhou, W., Li, H.: Improving deep neural network sparsity through decorrelation regularization. In: IJCAI, pp. 3264\u20133270 July (2018)","DOI":"10.24963\/ijcai.2018\/453"},{"key":"4_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"792","DOI":"10.1007\/978-3-030-01228-1_47","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Z Dang","year":"2018","unstructured":"Dang, Z., Yi, K.M., Hu, Y., Wang, F., Fua, P., Salzmann, M.: Eigendecomposition-free training of deep networks with zero eigenvalue-based losses. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 792\u2013807. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_47"},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"Indyk, P., Motwani, R., Raghavan, P., Vempala, S.: Locality-preserving hashing in multidimensional spaces. In: STOC, vol. 97, pp. 618\u2013625, May 1997","DOI":"10.1145\/258533.258656"},{"key":"4_CR34","unstructured":"Maaten, L.V.D., Hinton, G.: Visualizing data using t-SNE. JMLR 9(Nov), 2579\u20132605 (2008)"},{"key":"4_CR35","doi-asserted-by":"crossref","unstructured":"Li, C., et al.: SCRATCH: a scalable discrete matrix factorization hashing for cross-modal retrieval. In: ACM Multimedia (2018)","DOI":"10.1145\/3240508.3240547"},{"issue":"6","key":"4_CR36","doi-asserted-by":"publisher","first-page":"2962","DOI":"10.1109\/TIP.2019.2892703","volume":"28","author":"Xin Luo","year":"2019","unstructured":"Luo, X., Zhang, P., Huang, Z., Nie, L., Xu, X.: Discrete hashing with multiple supervision. In: TIP, vol. 28, no. 6, pp. 2962\u20132975, June 2019","journal-title":"IEEE Transactions on Image Processing"},{"key":"4_CR37","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"4_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T Lin","year":"2014","unstructured":"Lin, T., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"4_CR39","doi-asserted-by":"crossref","unstructured":"Hu, M., Yang, Y., Shen, F., Xie, N., Hong, R., Shen, H.T.: Collective reconstructive embeddings for cross-modal hashing. TIP (2019)","DOI":"10.1109\/TIP.2018.2890144"},{"key":"4_CR40","doi-asserted-by":"crossref","unstructured":"Yang, Y., et al.: Video captioning with adversarial LSTM. TIP 27, 5600\u20135611 (2018)","DOI":"10.1109\/TIP.2018.2855422"},{"key":"4_CR41","doi-asserted-by":"crossref","unstructured":"Bin, Y., Yang, Y., Shen, F., Xie, N., Shen, HT., Li, X.: Describing video with attention based bidirectional LSTM. TCYB (2018)","DOI":"10.1109\/TCYB.2018.2831447"},{"issue":"9","key":"4_CR42","doi-asserted-by":"publisher","first-page":"1834","DOI":"10.1109\/TKDE.2017.2701825","volume":"29","author":"Yang Yang","year":"2017","unstructured":"Yang, Y., Shen, F., Huang, Z., Shen, HT., Li, X.: Discrete nonnegative spectral clustering. TKDE 29, 1834\u20131845 (2017)","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"issue":"4","key":"4_CR43","doi-asserted-by":"publisher","first-page":"757","DOI":"10.1109\/TKDE.2018.2842190","volume":"31","author":"Yang Yang","year":"2019","unstructured":"Yang, Y., Duan, Y., Wang, X., Huang, Z., Xie, N., Shen, H.T.: Hierarchical multi-clue modelling for POI popularity prediction with heterogeneous tourist information. TKDE 31, 757\u2013768 (2018)","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"4_CR44","doi-asserted-by":"crossref","unstructured":"Luo, Y., Yang, Y., Shen, F., Huang, Z., Zhou, P., Shen, H.T.: Robust discrete code modeling for supervised hashing. In: PR (2018)","DOI":"10.1016\/j.patcog.2017.02.034"},{"key":"4_CR45","doi-asserted-by":"publisher","first-page":"3843","DOI":"10.1007\/s11042-018-6389-3","volume":"78","author":"L Peng","year":"2018","unstructured":"Peng, L., et al.: Word-to-region attention network for visual question answering. Multimedia Tools Appl. 78, 3843\u20133858 (2018)","journal-title":"Multimedia Tools Appl."},{"key":"4_CR46","unstructured":"Zhang, Y., Hare, J., Pr\u00fcgel-Bennett, A.: Learning to count objects in natural images for visual question answering. In: ICLR (2018)"}],"container-title":["Lecture Notes in Computer Science","Web and Big Data"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-26075-0_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,24]],"date-time":"2022-09-24T14:28:39Z","timestamp":1664029719000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-26075-0_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030260743","9783030260750"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-26075-0_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"17 July 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"APWeb-WAIM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asia-Pacific Web (APWeb) and Web-Age Information Management (WAIM) Joint International Conference on Web and Big Data","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chengdu","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 August 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 August 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"apwebwaim2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/cfm.uestc.edu.cn\/apwebwaim2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Research Microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"180","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"42","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"17","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"23% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}