{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T13:22:40Z","timestamp":1778592160877,"version":"3.51.4"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012366","type":"print"},{"value":"9783030012373","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\/978-3-030-01237-3_22","type":"book-chapter","created":{"date-parts":[[2018,10,6]],"date-time":"2018-10-06T14:42:18Z","timestamp":1538836938000},"page":"357-372","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":32,"title":["Attend and Rectify: A Gated Attention Mechanism for Fine-Grained Recovery"],"prefix":"10.1007","author":[{"given":"Pau","family":"Rodr\u00edguez","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Josep M.","family":"Gonfaus","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guillem","family":"Cucurull","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"F. Xavier","family":"Roca","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jordi","family":"Gonz\u00e0lez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,10,7]]},"reference":[{"key":"22_CR1","volume-title":"Cognitive Psychology and Its Implications","author":"JR Anderson","year":"1985","unstructured":"Anderson, J.R.: Cognitive Psychology and Its Implications. WH Freeman\/Times Books\/Henry Holt and Co, New York (1985)"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Chen, J., Ngo, C.W.: Deep-based ingredient recognition for cooking recipe retrieval. In: ACM MM, pp. 32\u201341. ACM (2016)","DOI":"10.1145\/2964284.2964315"},{"issue":"1","key":"22_CR3","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1146\/annurev.ne.18.030195.001205","volume":"18","author":"R Desimone","year":"1995","unstructured":"Desimone, R., Duncan, J.: Neural mechanisms of selective visual attention. Ann. Rev. Neurosci. 18(1), 193\u2013222 (1995)","journal-title":"Ann. Rev. Neurosci."},{"issue":"12","key":"22_CR4","first-page":"2170","volume":"9","author":"E Eidinger","year":"2014","unstructured":"Eidinger, E., Enbar, R., Hassner, T.: Age and gender estimation of unfiltered faces. TIFS 9(12), 2170\u20132179 (2014)","journal-title":"TIFS"},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Fu, J., Zheng, H., Mei, T.: Look closer to see better: recurrent attention convolutional neural network for fine-grained image recognition. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.476"},{"key":"22_CR6","doi-asserted-by":"crossref","unstructured":"Hassannejad, H., Matrella, G., Ciampolini, P., De Munari, I., Mordonini, M., Cagnoni, S.: Food image recognition using very deep convolutional networks. In: MADIMA Workshop, pp. 41\u201349. ACM (2016)","DOI":"10.1145\/2986035.2986042"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: CVPR, pp. 1026\u20131034 (2015)","DOI":"10.1109\/ICCV.2015.123"},{"key":"22_CR8","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"},{"issue":"8","key":"22_CR9","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Weinberger, K.Q., van der Maaten, L.: Densely connected convolutional networks. In: CVPR, vol. 1, p. 3 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"22_CR11","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., et al.: Spatial transformer networks. In: NIPS, pp. 2017\u20132025 (2015)"},{"key":"22_CR12","unstructured":"Jetley, S., Lord, N.A., Lee, N., Torr, P.: Learn to pay attention. In: ICLR (2018)"},{"key":"22_CR13","unstructured":"Khosla, A., Jayadevaprakash, N., Yao, B., Li, F.F.: Novel dataset for fine-grained image categorization: stanford dogs. In: FGVC, vol. 2, p. 1 (2011)"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3D object representations for fine-grained categorization. In: CVPR, pp. 554\u2013561 (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"key":"22_CR15","unstructured":"Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images (2009)"},{"key":"22_CR16","unstructured":"LeCun, Y.: The MNIST database of handwritten digits (1998). http:\/\/yann.lecun.com\/exdb\/mnist\/"},{"issue":"11","key":"22_CR17","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"22_CR18","unstructured":"Lee, C.Y., Xie, S., Gallagher, P., Zhang, Z., Tu, Z.: Deeply-supervised nets. In: AISTATS, pp. 562\u2013570 (2015)"},{"key":"22_CR19","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":"22_CR20","doi-asserted-by":"crossref","unstructured":"Matsuda, Y., Hoashi, H., Yanai, K.: Recognition of multiple-food images by detecting candidate regions. In: ICME (2012)","DOI":"10.1109\/ICME.2012.157"},{"key":"22_CR21","unstructured":"Mnih, V., Heess, N., Graves, A., et al.: Recurrent models of visual attention. In: NIPS, pp. 2204\u20132212 (2014)"},{"key":"22_CR22","unstructured":"Paszke, A., Gross, S., Chintala, S., Chanan, G.: Pytorch (2017)"},{"key":"22_CR23","first-page":"563","volume":"72","author":"P Rodriguez","year":"2017","unstructured":"Rodriguez, P., Cucurull, G., Gonfaus, J.M., Roca, F.X., Gonzalez, J.: Age and gender recognition in the wild with deep attention. PR 72, 563\u2013571 (2017)","journal-title":"PR"},{"key":"22_CR24","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1007\/s11263-016-0940-3","volume":"126","author":"R Rothe","year":"2016","unstructured":"Rothe, R., Timofte, R., Gool, L.V.: Deep expectation of real and apparent age from a single image without facial landmarks. IJCV 126, 144\u2013157 (2016)","journal-title":"IJCV"},{"key":"22_CR25","unstructured":"Russakovsky, O., Deng, J., Krause, J., Berg, A., Fei-Fei, L.: The ImageNet large scale visual recognition challenge 2012 (ILSVRC2012) (2012)"},{"key":"22_CR26","unstructured":"Sermanet, P., Frome, A., Real, E.: Attention for fine-grained categorization. In: ICLR (2015)"},{"key":"22_CR27","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"issue":"2","key":"22_CR28","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"R Uijlings","year":"2013","unstructured":"Uijlings, R., van de Sande, A., Gevers, T., Smeulders, M., et al.: Selective search for object recognition. IJCV 104(2), 154\u2013171 (2013)","journal-title":"IJCV"},{"issue":"1","key":"22_CR29","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1146\/annurev.neuro.23.1.315","volume":"23","author":"SK Ungerleider","year":"2000","unstructured":"Ungerleider, S.K.: Mechanisms of visual attention in the human cortex. Annu. Rev. Neurosci. 23(1), 315\u2013341 (2000)","journal-title":"Annu. Rev. Neurosci."},{"key":"22_CR30","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS, pp. 5998\u20136008 (2017)"},{"key":"22_CR31","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD Birds-200-2011 Dataset. Technical report (2011)"},{"key":"22_CR32","doi-asserted-by":"crossref","unstructured":"Wang, F., et al.: Residual attention network for image classification. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.683"},{"key":"22_CR33","doi-asserted-by":"crossref","unstructured":"Xiao, T., Xu, Y., Yang, K., Zhang, J., Peng, Y., Zhang, Z.: The application of two-level attention models in deep convolutional neural network for fine-grained image classification. In: CVPR, pp. 842\u2013850 (2015)","DOI":"10.1109\/CVPR.2015.7298685"},{"key":"22_CR34","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: CVPR, pp. 5987\u20135995. IEEE (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"22_CR35","doi-asserted-by":"crossref","unstructured":"Zagoruyko, S., Komodakis, N.: Wide residual networks. In: BMVC (2016)","DOI":"10.5244\/C.30.87"},{"key":"22_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1007\/978-3-319-10590-1_54","volume-title":"Computer Vision \u2013 ECCV 2014","author":"N Zhang","year":"2014","unstructured":"Zhang, N., Donahue, J., Girshick, R., Darrell, T.: Part-based R-CNNs for fine-grained category detection. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 834\u2013849. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_54"},{"key":"22_CR37","first-page":"1","volume":"14","author":"B Zhao","year":"2017","unstructured":"Zhao, B., Feng, J., Wu, X., Yan, S.: A survey on deep learning-based fine-grained object classification and semantic segmentation. IJAC 14, 1\u201317 (2017)","journal-title":"IJAC"},{"issue":"6","key":"22_CR38","doi-asserted-by":"publisher","first-page":"1245","DOI":"10.1109\/TMM.2017.2648498","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. IEEE Trans. Multimedia 19(6), 1245\u20131256 (2017)","journal-title":"IEEE Trans. Multimedia"},{"key":"22_CR39","doi-asserted-by":"crossref","unstructured":"Zheng, H., Fu, J., Mei, T., Luo, J.: Learning multi-attention convolutional neural network for fine-grained image recognition. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.557"}],"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\/978-3-030-01237-3_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T18:48:47Z","timestamp":1775242127000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01237-3_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012366","9783030012373"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01237-3_22","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":"7 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"}]}}