{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:12:36Z","timestamp":1775578356716,"version":"3.50.1"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012458","type":"print"},{"value":"9783030012465","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-01246-5_45","type":"book-chapter","created":{"date-parts":[[2018,10,5]],"date-time":"2018-10-05T16:14:56Z","timestamp":1538756096000},"page":"760-777","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":131,"title":["Attention-Based Ensemble for Deep Metric Learning"],"prefix":"10.1007","author":[{"given":"Wonsik","family":"Kim","sequence":"first","affiliation":[]},{"given":"Bhavya","family":"Goyal","sequence":"additional","affiliation":[]},{"given":"Kunal","family":"Chawla","sequence":"additional","affiliation":[]},{"given":"Jungmin","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Keunjoo","family":"Kwon","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"45_CR1","unstructured":"Ba, J., Mnih, V., Kavukcuoglu, K.: Multiple object recognition with visual attention. In: International Conference on Learning Representations (2015)"},{"key":"45_CR2","unstructured":"Bachman, P., Alsharif, O., Precup, D.: Learning with pseudo-ensembles. In: Advances in Neural Information Processing Systems (2014)"},{"issue":"4","key":"45_CR3","first-page":"98","volume":"34","author":"S Bell","year":"2015","unstructured":"Bell, S., Bala, K.: Learning visual similarity for product design with convolutional neural networks. Graphics 34(4), 98 (2015)","journal-title":"Graphics"},{"key":"45_CR4","unstructured":"Chopra, S., Hadsell, R., LeCun, Y.: Learning a similarity metric discriminatively, with application to face verification. In: Computer Vision and Pattern Recognition (2005)"},{"key":"45_CR5","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: International Conference on Artificial Intelligence and Statistics (2010)"},{"key":"45_CR6","unstructured":"Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: Computer Vision and Pattern Recognition (2006)"},{"key":"45_CR7","doi-asserted-by":"crossref","unstructured":"Harwood, B., VijayKumarB., G., Carneiro, G., Reid, I.D., Drummond, T.: Smart mining for deep metric learning. In: International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCV.2017.307"},{"key":"45_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"45_CR9","unstructured":"Huang, C., Loy, C.C., Tang, X.: Local similarity-aware deep feature embedding. In: Advances in Neural Information Processing Systems (2016)"},{"key":"45_CR10","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning (2015)"},{"key":"45_CR11","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., Kavukcuoglu, K.: Spatial transformer networks. In: Advances in Neural Information Processing Systems (2015)"},{"key":"45_CR12","doi-asserted-by":"crossref","unstructured":"Jia, Y., et al.: Caffe: convolutional architecture for fast feature embedding. In: International Conference on Multimedia (2014)","DOI":"10.1145\/2647868.2654889"},{"key":"45_CR13","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3D object representations for fine-grained categorization. In: Workshop on 3D Representation and Recognition (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"key":"45_CR14","unstructured":"Law, M.T., Urtasun, R., Zemel, R.S.: Deep spectral clustering learning. In: International Conference on Machine Learning (2017)"},{"key":"45_CR15","unstructured":"Lee, C.Y., Xie, S., Gallagher, P., Zhang, Z., Tu, Z.: Deeply-supervised nets. In: Artificial Intelligence and Statistics (2015)"},{"key":"45_CR16","unstructured":"Lee, S., Purushwalkam, S., Cogswell, M., Crandall, D., Batra, D.: Why M heads are better than one: training a diverse ensemble of deep networks. arXiv preprint arXiv:1511.06314 (2015)"},{"key":"45_CR17","doi-asserted-by":"crossref","unstructured":"Liu, X., Xia, T., Wang, J., Lin, Y.: Fully convolutional attention localization networks: efficient attention localization for fine-grained recognition. arXiv preprint arXiv:1603.06765 (2016)","DOI":"10.1609\/aaai.v31i1.11202"},{"key":"45_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Qiu, S., Wang, X., Tang, X.: DeepFashion: powering robust clothes recognition and retrieval with rich annotations. In: Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.124"},{"key":"45_CR19","unstructured":"Mnih, V., Heess, N., Graves, A., et al.: Recurrent models of visual attention. In: Advances in Neural Information Processing Systems (2014)"},{"key":"45_CR20","doi-asserted-by":"crossref","unstructured":"Movshovitz-Attias, Y., Toshev, A., Leung, T.K., Ioffe, S., Singh, S.: No fuss distance metric learning using proxies. In: International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCV.2017.47"},{"key":"45_CR21","doi-asserted-by":"crossref","unstructured":"Opitz, M., Possegger, H., Bischof, H.: Efficient model averaging for deep neural networks. In: Asian Conference on Computer Vision (2016)","DOI":"10.1007\/978-3-319-54184-6_13"},{"key":"45_CR22","doi-asserted-by":"crossref","unstructured":"Opitz, M., Waltner, G., Possegger, H., Bischof, H.: BIER-boosting independent embeddings robustly. In: International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCV.2017.555"},{"key":"45_CR23","doi-asserted-by":"crossref","unstructured":"Opitz, M., Waltner, G., Possegger, H., Bischof, H.: Deep metric learning with BIER: boosting independent embeddings robustly. arXiv preprint arXiv:1801.04815 (2018)","DOI":"10.1109\/ICCV.2017.555"},{"issue":"3","key":"45_CR24","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.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"45_CR25","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: A unified embedding for face recognition and clustering. In: Computer Vision and Pattern Recognition (2015)","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"45_CR26","unstructured":"Sermanet, P., Frome, A., Real, E.: Attention for fine-grained categorization. In: International Conference on Learning Representations Workshop (2015)"},{"key":"45_CR27","unstructured":"Sohn, K.: Improved deep metric learning with multi-class N-pair loss objective. In: Advances in Neural Information Processing Systems (2016)"},{"key":"45_CR28","doi-asserted-by":"crossref","unstructured":"Song, H.O., Jegelka, S., Rathod, V., Murphy, K.: Deep metric learning via facility location. In: Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.237"},{"key":"45_CR29","doi-asserted-by":"crossref","unstructured":"Song, H.O., Xiang, Y., Jegelka, S., Savarese, S.: Deep metric learning via lifted structured feature embedding. In: Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.434"},{"issue":"1","key":"45_CR30","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"45_CR31","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems (2014)"},{"key":"45_CR32","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: Computer Vision and Pattern Recognition (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"45_CR33","unstructured":"Ustinova, E., Lempitsky, V.: Learning deep embeddings with histogram loss. In: Advances in Neural Information Processing Systems (2016)"},{"key":"45_CR34","unstructured":"Veit, A., Wilber, M.J., Belongie, S.: Residual networks behave like ensembles of relatively shallow networks. In: Advances in Neural Information Processing Systems (2016)"},{"key":"45_CR35","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD Birds-200-2011 dataset. Technical report CNS-TR-2011-001, California Institute of Technology (2011)"},{"key":"45_CR36","doi-asserted-by":"crossref","unstructured":"Wang, J., Zhou, F., Wen, S., Liu, X., Lin, Y.: Deep metric learning with angular loss. In: International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCV.2017.283"},{"issue":"2","key":"45_CR37","first-page":"207","volume":"10","author":"KQ Weinberger","year":"2009","unstructured":"Weinberger, K.Q., Saul, L.K.: Distance metric learning for large margin nearest neighbor classification. J. Mach. Learn. Res. 10(2), 207\u2013244 (2009)","journal-title":"J. Mach. Learn. Res."},{"key":"45_CR38","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., Manmatha, R., Smola, A.J., Kr\u00e4henb\u00fchl, P.: Sampling matters in deep embedding learning. In: International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCV.2017.309"},{"key":"45_CR39","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Yang, K., Zhang, C.: Hard-aware deeply cascaded embedding. In: International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCV.2017.94"},{"issue":"6","key":"45_CR40","first-page":"1245","volume":"19","author":"B Zhao","year":"2017","unstructured":"Zhao, B., Wu, X., Feng, J., Peng, Q., Yan, S.: Diversified visual attention networks for fine-grained object classification. Multimedia 19(6), 1245\u20131256 (2017)","journal-title":"Multimedia"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01246-5_45","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T18:38:04Z","timestamp":1775241484000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01246-5_45"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012458","9783030012465"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01246-5_45","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"6 October 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}