{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T22:45:43Z","timestamp":1779144343156,"version":"3.51.4"},"reference-count":54,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2018,8,25]],"date-time":"2018-08-25T00:00:00Z","timestamp":1535155200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100007161","name":"Secretar\u00eda de Investigaci\u00f3n y Posgrado, Instituto Polit\u00e9cnico Nacional","doi-asserted-by":"publisher","award":["SIP2017"],"award-info":[{"award-number":["SIP2017"]}],"id":[{"id":"10.13039\/501100007161","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2019,4]]},"DOI":"10.1007\/s11042-018-6515-2","type":"journal-article","created":{"date-parts":[[2018,8,25]],"date-time":"2018-08-25T01:33:58Z","timestamp":1535160838000},"page":"9553-9576","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Saliency-based selection of visual content for deep convolutional neural networks"],"prefix":"10.1007","volume":"78","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7090-1048","authenticated-orcid":false,"given":"A. Montoya","family":"Obeso","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J.","family":"Benois-Pineau","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M. S. Garc\u00eda","family":"V\u00e1zquez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A. A. Ram\u00edrez","family":"Acosta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,8,25]]},"reference":[{"issue":"11","key":"6515_CR1","doi-asserted-by":"publisher","first-page":"2189","DOI":"10.1109\/TPAMI.2012.28","volume":"34","author":"B Alexe","year":"2012","unstructured":"Alexe B, Deselaers T, Ferrari V (2012) Measuring the objectness of image windows. IEEE Trans Pattern Anal Mach Intell 34(11):2189\u20132202","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6515_CR2","doi-asserted-by":"crossref","unstructured":"Ali H, Seifert C, Jindal N, Paletta L, Paar G (2007) Window detection in facades. In: 2007 14th international conference on image analysis and processing, ICIAP 2007. IEEE, pp 837\u2013842","DOI":"10.1109\/ICIAP.2007.4362880"},{"key":"6515_CR3","doi-asserted-by":"crossref","unstructured":"Benois-Pineau J, Callet PL (eds) (2017) Visual content indexing and retrieval with psychovisual models. Springer, Heidelberg","DOI":"10.1007\/978-3-319-57687-9"},{"key":"6515_CR4","doi-asserted-by":"publisher","unstructured":"Benois-Pineau J, Mitrea M (2017) Extraction of saliency in images and video: Problems, methods and applications. A survey. In: 2017 Seventh international conference on image processing theory, tools and applications (IPTA). IEEE, Montreal, Canada. https:\/\/doi.org\/10.1109\/IPTA.2017.8310116 . https:\/\/hal.archives-ouvertes.fr\/hal-01766387","DOI":"10.1109\/IPTA.2017.8310116"},{"key":"6515_CR5","doi-asserted-by":"crossref","unstructured":"Berg AC, Grabler F, Malik J (2007) Parsing images of architectural scenes. In: IEEE 11th international conference on 2007 computer vision, ICCV 2007. IEEE, pp 1\u20138","DOI":"10.1109\/ICCV.2007.4409091"},{"issue":"1","key":"6515_CR6","doi-asserted-by":"publisher","first-page":"011,019","DOI":"10.1117\/1.JEI.26.1.011019","volume":"26","author":"N Bhowmik","year":"2017","unstructured":"Bhowmik N, Gouet-Brunet V, Bloch G, Besson S (2017) Combination of image descriptors for the exploration of cultural photographic collections. J Electron Imag 26(1):011,019\u2013011,019","journal-title":"J Electron Imag"},{"key":"6515_CR7","doi-asserted-by":"publisher","first-page":"418","DOI":"10.1016\/j.image.2015.05.006","volume":"39","author":"V Buso","year":"2015","unstructured":"Buso V, Gonz\u00e1lez-d\u00edaz I, Benois-Pineau J (2015) Goal-oriented top-down probabilistic visual attention model for recognition of manipulated objects in egocentric videos. Sig Proc Image Commun 39:418\u2013431. https:\/\/doi.org\/10.1016\/j.image.2015.05.006","journal-title":"Sig Proc Image Commun"},{"key":"6515_CR8","unstructured":"Buswell GT (1935) How people look at pictures: a study of the psychology and perception in art"},{"key":"6515_CR9","doi-asserted-by":"crossref","unstructured":"Bylinskii Z, Recasens A, Borji A, Oliva A, Torralba A, Durand F (2016) Where should saliency models look next?. In: European conference on computer vision. Springer, pp 809\u2013824","DOI":"10.1007\/978-3-319-46454-1_49"},{"key":"6515_CR10","doi-asserted-by":"crossref","unstructured":"de Carvalho Soares R, da Silva IR, Guliato D (2012) Spatial locality weighting of features using saliency map with a bag-of-visual-words approach. In: 2012 IEEE 24th international conference on tools with artificial intelligence (ICTAI), vol 1. IEEE, pp 1070\u20131075","DOI":"10.1109\/ICTAI.2012.151"},{"key":"6515_CR11","unstructured":"De San Roman PP, Benois-Pineau J, Domenger JP, De Rugy A, Paclet F, Cataert D (2017) Saliency driven object recognition in egocentric videos with deep cnn: toward application in assistance to neuroprostheses Computer Vision and Image Understanding"},{"issue":"2","key":"6515_CR12","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1007\/s11263-017-1006-x","volume":"124","author":"A Ghodrati","year":"2017","unstructured":"Ghodrati A, Diba A, Pedersoli M, Tuytelaars T, Van Gool L (2017) Deepproposals: hunting objects and actions by cascading deep convolutional layers. Int J Comput Vis 124(2):115\u2013131. https:\/\/doi.org\/10.1007\/s11263-017-1006-x","journal-title":"Int J Comput Vis"},{"key":"6515_CR13","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"key":"6515_CR14","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 580\u2013587","DOI":"10.1109\/CVPR.2014.81"},{"key":"6515_CR15","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1016\/j.patcog.2016.03.007","volume":"56","author":"I Gonz\u00e1lez-D\u00edaz","year":"2016","unstructured":"Gonz\u00e1lez-D\u00edaz I, Buso V, Benois-Pineau J (2016) Perceptual modeling in the problem of active object recognition in visual scenes. Pattern Recogn 56:129\u2013141","journal-title":"Pattern Recogn"},{"key":"6515_CR16","unstructured":"GPU NDIDL (2015) Training system"},{"key":"6515_CR17","doi-asserted-by":"crossref","unstructured":"Harel J, Koch C, Perona P (2007) Graph-based visual saliency. In: Advances in neural information processing systems, pp 545\u2013552","DOI":"10.7551\/mitpress\/7503.003.0073"},{"key":"6515_CR18","doi-asserted-by":"crossref","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","DOI":"10.1109\/CVPR.2016.90"},{"key":"6515_CR19","unstructured":"Howard AG (2013) Some improvements on deep convolutional neural network based image classification. arXiv: 1312.5402"},{"issue":"3","key":"6515_CR20","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1038\/35058500","volume":"2","author":"L Itti","year":"2001","unstructured":"Itti L, Koch C (2001) Computational modelling of visual attention. Nature Rev Neuroscience 2(3):194","journal-title":"Nature Rev Neuroscience"},{"key":"6515_CR21","doi-asserted-by":"crossref","unstructured":"Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, Guadarrama S, Darrell T (2014) Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM international conference on multimedia. ACM, pp 675\u2013678","DOI":"10.1145\/2647868.2654889"},{"key":"6515_CR22","unstructured":"Krizhevsky A, Sutskever I, Hinton G (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097\u20131105"},{"key":"6515_CR23","doi-asserted-by":"crossref","unstructured":"Liu Z, Wang J, Liu W (2005) Building extraction from high resolution imagery based on multi-scale object oriented classification and probabilistic hough transform. In: 2005 Proceedings of the IEEE international geoscience and remote sensing symposium, 2005. IGARSS\u201905, vol 4. IEEE, pp 2250\u20132253","DOI":"10.1109\/IGARSS.2005.1525421"},{"key":"6515_CR24","doi-asserted-by":"crossref","unstructured":"Llamas J, Lerones PM, Zalama E, G\u00f3mez-garc\u00eda-bermejo J (2016) Applying deep learning techniques to cultural heritage images within the inception project. In: Euro-mediterranean conference. Springer, pp 25\u201332","DOI":"10.1007\/978-3-319-48974-2_4"},{"issue":"3","key":"6515_CR25","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1109\/TPAMI.2012.98","volume":"35","author":"V Mahadevan","year":"2013","unstructured":"Mahadevan V, Vasconcelos N (2013) Biologically inspired object tracking using center-surround saliency mechanisms. IEEE Trans Pattern Anal Mach Intell 35 (3):541\u2013554","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6515_CR26","first-page":"842","volume":"2012","author":"S Mathe","year":"2012","unstructured":"Mathe S, Sminchisescu C (2012) Dynamic eye movement datasets and learnt saliency models for visual action recognition. Computer Vision\u2013ECCV 2012:842\u2013856","journal-title":"Computer Vision\u2013ECCV"},{"key":"6515_CR27","first-page":"171","volume":"3816","author":"M Mathias","year":"2011","unstructured":"Mathias M, Martinovic A, Weissenberg J, Haegler S, Van Gool L (2011) Automatic architectural style recognition. ISPRS-international archives of the photogrammetry. Remote Sens Spatial Inform Sci 3816:171\u2013176","journal-title":"Remote Sens Spatial Inform Sci"},{"key":"6515_CR28","unstructured":"Nesterov Y (1983) A method of solving a convex programming problem with convergence rate o (1\/k2). In: Soviet mathematics Doklady, vol 27, pp 372\u2013376"},{"issue":"1","key":"6515_CR29","doi-asserted-by":"publisher","first-page":"011,016","DOI":"10.1117\/1.JEI.26.1.011016","volume":"26","author":"AM Obeso","year":"2016","unstructured":"Obeso AM, Benois-Pineau J, Acosta AAR, V\u00e1zquez MSG (2016) Architectural style classification of mexican historical buildings using deep convolutional neural networks and sparse features. J Electron Imag 26(1):011,016. https:\/\/doi.org\/10.1117\/1.JEI.26.1.011016","journal-title":"J Electron Imag"},{"key":"6515_CR30","unstructured":"Obeso AM, Reyes LMA, Rodriguez ML, Cruz MHM, V\u00e1zquez MSG, Benois-Pineau J, Fuentes LMZ, Martinez EC, Secundino JAF, Martinez JLR et al (2016) Image annotation for mexican buildings database. In: International society for optics and photonics of the SPIE optical engineering+ applications, pp 99,700y\u201399,700y"},{"key":"6515_CR31","doi-asserted-by":"crossref","unstructured":"Obeso AM, V\u00e1zquez MSG, Acosta AAR, Benois-Pineau J (2017) Connoisseur: classification of styles of mexican architectural heritage with deep learning and visual attention prediction. In: Proceedings of the 15th international workshop on content-based multimedia indexing, vol 16. ACM","DOI":"10.1145\/3095713.3095730"},{"key":"6515_CR32","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1016\/j.dsp.2014.09.005","volume":"36","author":"A Papushoy","year":"2015","unstructured":"Papushoy A, Bors AG (2015) Image retrieval based on query by saliency content. Digital Signal Process 36:156\u2013173","journal-title":"Digital Signal Process"},{"issue":"1","key":"6515_CR33","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1109\/TPAMI.2016.2537320","volume":"39","author":"J Pont-Tuset","year":"2017","unstructured":"Pont-Tuset J, Arbel\u00e1ez P, Barron JT, Marques F, Malik J (2017) Multiscale combinatorial grouping for image segmentation and object proposal generation. IEEE Trans Pattern Anal Mach Intell 39(1):128\u2013140. https:\/\/doi.org\/10.1109\/TPAMI.2016.2537320","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6515_CR34","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: towards real-time object detection with region proposal networks. In: Advances in neural information processing systems, pp 91\u201399"},{"key":"6515_CR35","doi-asserted-by":"crossref","unstructured":"Ren X, Gu C (2010) Figure-ground segmentation improves handled object recognition in egocentric video. In: 2010 IEEE conference on Computer vision and pattern recognition (CVPR). IEEE, pp 3137\u20133144","DOI":"10.1109\/CVPR.2010.5540074"},{"issue":"3","key":"6515_CR36","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, Berg AC, Fei-Fei L (2015) Imagenet large scale visual recognition challenge. International Journal of Computer Vision (IJCV) 115(3):211\u2013252. https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"International Journal of Computer Vision (IJCV)"},{"key":"6515_CR37","doi-asserted-by":"crossref","unstructured":"San Biagio M, Bazzani L, Cristani M, Murino V (2014) Weighted bag of visual words for object recognition. In: 2014 IEEE international conference on image processing (ICIP). IEEE, pp 2734\u20132738","DOI":"10.1109\/ICIP.2014.7025553"},{"key":"6515_CR38","unstructured":"Sermanet P, Eigen D, Zhang X, Mathieu M, Fergus R, LeCun Y (2013) Overfeat: integrated recognition, localization and detection using convolutional networks. CoRR arXiv: 1312.6229"},{"key":"6515_CR39","doi-asserted-by":"crossref","unstructured":"Shalunts G (2015) Architectural style classification of building facade towers. In: International symposium on visual computing. Springer, pp 285\u2013294","DOI":"10.1007\/978-3-319-27857-5_26"},{"key":"6515_CR40","doi-asserted-by":"crossref","unstructured":"Shalunts G, Haxhimusa Y, Sablatnig R (2011) Architectural style classification of building facade windows. In: International symposium on visual computing. Springer, pp 280\u2013289","DOI":"10.1007\/978-3-642-24031-7_28"},{"key":"6515_CR41","unstructured":"Shalunts G, Haxhimusa Y, Sablatnig R (2012) Classification of gothic and baroque architectural elements. In: 2012 19th international conference on systems, signals and image processing (IWSSIP). IEEE, pp 316\u2013319"},{"key":"6515_CR42","doi-asserted-by":"crossref","unstructured":"Sharma G, Jurie F, Schmid C (2012) Discriminative spatial saliency for image classification. In: 2012 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 3506\u20133513","DOI":"10.1109\/CVPR.2012.6248093"},{"issue":"1","key":"6515_CR43","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1109\/76.350781","volume":"5","author":"T Sikora","year":"1995","unstructured":"Sikora T, Makai B (1995) Shape-adaptive dct for generic coding of video. IEEE Trans Circuit Syst Video Technol 5(1):59\u201362","journal-title":"IEEE Trans Circuit Syst Video Technol"},{"key":"6515_CR44","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv: 1409.1556"},{"issue":"5","key":"6515_CR45","doi-asserted-by":"publisher","first-page":"1826","DOI":"10.1016\/j.patcog.2013.11.028","volume":"47","author":"Y Su","year":"2014","unstructured":"Su Y, Zhao Q, Zhao L, Gu D (2014) Abrupt motion tracking using a visual saliency embedded particle filter. Pattern Recogn 47(5):1826\u20131834","journal-title":"Pattern Recogn"},{"key":"6515_CR46","unstructured":"Sutskever I, Martens J, Dahl G, Hinton G (2013) On the importance of initialization and momentum in deep learning. In: International conference on machine learning, pp 1139\u20131147"},{"key":"6515_CR47","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"issue":"2","key":"6515_CR48","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JRR Uijlings","year":"2013","unstructured":"Uijlings JRR, Van De Sande KEA, Gevers T, Smeulders AWM (2013) Selective search for object recognition. Int J Comput Vis 104(2):154\u2013171. https:\/\/doi.org\/10.1007\/s11263-013-0620-5","journal-title":"Int J Comput Vis"},{"key":"6515_CR49","doi-asserted-by":"publisher","unstructured":"Viola PA, Jones MJ (2001) Rapid object detection using a boosted cascade of simple features. In: 2001 IEEE computer society conference on computer vision and pattern recognition (CVPR 2001), with CD-ROM, 8-14 December 2001, Kauai, HI, USA, pp 511\u2013518. https:\/\/doi.org\/10.1109\/CVPR.2001.990517","DOI":"10.1109\/CVPR.2001.990517"},{"issue":"7","key":"6515_CR50","doi-asserted-by":"publisher","first-page":"1150","DOI":"10.1109\/TCSVT.2012.2226528","volume":"23","author":"Q Wang","year":"2013","unstructured":"Wang Q, Yuan Y, Yan P (2013) Visual saliency by selective contrast. IEEE Trans Circuit Syst Video Technol 23(7):1150\u20131155","journal-title":"IEEE Trans Circuit Syst Video Technol"},{"issue":"2","key":"6515_CR51","doi-asserted-by":"publisher","first-page":"660","DOI":"10.1109\/TSMCB.2012.2214210","volume":"43","author":"Q Wang","year":"2013","unstructured":"Wang Q, Yuan Y, Yan P, Li X (2013) Saliency detection by multiple-instance learning. IEEE Trans Cybern 43(2):660\u2013672","journal-title":"IEEE Trans Cybern"},{"key":"6515_CR52","doi-asserted-by":"crossref","unstructured":"Xu Z, Tao D, Zhang Y, Wu J, Tsoi AC (2014) Architectural style classification using multinomial latent logistic regression. In: European conference on computer vision. Springer, pp 600\u2013615","DOI":"10.1007\/978-3-319-10590-1_39"},{"key":"6515_CR53","unstructured":"Zeiler MD, Fergus R (2014) Visualizing and understanding convolutional networks. In: European conference on computer vision. Springer, pp 818\u2013833"},{"issue":"2","key":"6515_CR54","doi-asserted-by":"publisher","first-page":"19","DOI":"10.3923\/ijscomp.2010.19.28","volume":"5","author":"B Zhang","year":"2010","unstructured":"Zhang B, Song Y, Guan SU, Zhang Y (2010) Historic chinese architectures image retrieval by svm and pyramid histogram of oriented gradients features. Int J Soft Comput 5(2):19\u201328","journal-title":"Int J Soft Comput"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-6515-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-018-6515-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-6515-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T15:37:47Z","timestamp":1693841867000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-018-6515-2"}},"subtitle":["Application to architectural style classification"],"short-title":[],"issued":{"date-parts":[[2018,8,25]]},"references-count":54,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2019,4]]}},"alternative-id":["6515"],"URL":"https:\/\/doi.org\/10.1007\/s11042-018-6515-2","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,8,25]]},"assertion":[{"value":"29 November 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 June 2018","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 August 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 August 2018","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}