{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T09:12:45Z","timestamp":1760346765511,"version":"3.40.5"},"reference-count":41,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2019,3,1]],"date-time":"2019-03-01T00:00:00Z","timestamp":1551398400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Signal Processing: Image Communication"],"published-print":{"date-parts":[[2019,3]]},"DOI":"10.1016\/j.image.2018.12.009","type":"journal-article","created":{"date-parts":[[2018,12,22]],"date-time":"2018-12-22T02:08:50Z","timestamp":1545444530000},"page":"69-79","update-policy":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":16,"special_numbering":"C","title":["Vehicle joint make and model recognition with multiscale attention windows"],"prefix":"10.1016","volume":"72","author":[{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0002-5046-3842","authenticated-orcid":false,"given":"Sina","family":"Ghassemi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Attilio","family":"Fiandrotti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emanuele","family":"Caimotti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gianluca","family":"Francini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Enrico","family":"Magli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.image.2018.12.009_b1","series-title":"Advances in Neural Information Processing Systems","first-page":"73","article-title":"Subordinate class recognition using relational object models","author":"Hillel","year":"2007"},{"key":"10.1016\/j.image.2018.12.009_b2","series-title":"Computer Vision and Pattern Recognition, CVPR, 2012 IEEE Conference on","first-page":"3474","article-title":"Discovering localized attributes for fine-grained recognition","author":"Duan","year":"2012"},{"issue":"1","key":"10.1016\/j.image.2018.12.009_b3","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1109\/TITS.2013.2294646","article-title":"Symmetrical surf and its applications to vehicle detection and vehicle make and model recognition","volume":"15","author":"Hsieh","year":"2014","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"6","key":"10.1016\/j.image.2018.12.009_b4","doi-asserted-by":"crossref","first-page":"3182","DOI":"10.1109\/TITS.2015.2437998","article-title":"Recognition of car makes and models from a single traffic-camera image","volume":"16","author":"He","year":"2015","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"1","key":"10.1016\/j.image.2018.12.009_b5","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1109\/TITS.2017.2749961","article-title":"A cascaded part-based system for fine-grained vehicle classification","volume":"19","author":"Biglari","year":"2018","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.image.2018.12.009_b6","doi-asserted-by":"crossref","unstructured":"F. Chabot, M. Chaouch, J. Rabarisoa, C. Teuli\u00e8re, T. Chateau, Deep manta: A coarse-to-fine many-task network for joint 2D and 3D vehicle analysis from monocular image, in:Proc. IEEE Conf. Comput. Vis. Pattern Recognit, CVPR, 2017, pp. 2040\u20132049.","DOI":"10.1109\/CVPR.2017.198"},{"key":"10.1016\/j.image.2018.12.009_b7","series-title":"Image Processing, ICIP, 2015 IEEE International Conference on","first-page":"745","article-title":"Exploiting effects of parts in fine-grained categorization of vehicles","author":"Liao","year":"2015"},{"issue":"4","key":"10.1016\/j.image.2018.12.009_b8","doi-asserted-by":"crossref","first-page":"926","DOI":"10.1109\/TITS.2015.2494586","article-title":"Multipart vehicle detection using symmetry-derived analysis and active learning","volume":"17","author":"Satzoda","year":"2016","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"11","key":"10.1016\/j.image.2018.12.009_b9","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.image.2018.12.009_b10","series-title":"Advances in Neural Information Processing Systems","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"Krizhevsky","year":"2012"},{"year":"2015","series-title":"Going Deeper with Convolutions","author":"Szegedy","key":"10.1016\/j.image.2018.12.009_b11"},{"key":"10.1016\/j.image.2018.12.009_b12","doi-asserted-by":"crossref","first-page":"358","DOI":"10.1016\/j.image.2016.06.007","article-title":"Spatial\u2013temporal convolutional neural networks for anomaly detection and localization in crowded scenes","volume":"47","author":"Zhou","year":"2016","journal-title":"Signal Process., Image Commun."},{"key":"10.1016\/j.image.2018.12.009_b13","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1016\/j.image.2017.09.001","article-title":"Deep learning assisted robust visual tracking with adaptive particle filtering","volume":"60","author":"Qian","year":"2018","journal-title":"Signal Process., Image Commun."},{"key":"10.1016\/j.image.2018.12.009_b14","doi-asserted-by":"crossref","DOI":"10.1016\/j.image.2018.04.011","article-title":"Locating splicing forgery by fully convolutional networks and conditional random field","author":"Liu","year":"2018","journal-title":"Signal Process., Image Commun."},{"key":"10.1016\/j.image.2018.12.009_b15","doi-asserted-by":"crossref","DOI":"10.1016\/j.image.2018.05.015","article-title":"A deep learning approach to patch-based image inpainting forensics","author":"Zhu","year":"2018","journal-title":"Signal Process., Image Commun."},{"key":"10.1016\/j.image.2018.12.009_b16","unstructured":"V. Nair, G.E. Hinton, Rectified linear units improve restricted boltzmann machines, in: Proceedings of the 27th International Conference on Machine Learning, ICML-10, 2010, pp. 807\u2013814."},{"key":"10.1016\/j.image.2018.12.009_b17","unstructured":"T.S. Cohen, M. Welling, Transformation properties of learned visual representations, 2014, arXiv preprint arXiv:1412.7659."},{"key":"10.1016\/j.image.2018.12.009_b18","series-title":"Computer Vision and Pattern Recognition, CVPR, 2015 IEEE Conference on","first-page":"991","article-title":"Understanding image representations by measuring their equivariance and equivalence","author":"Lenc","year":"2015"},{"key":"10.1016\/j.image.2018.12.009_b19","series-title":"Advances in Neural Information Processing Systems","first-page":"2017","article-title":"Spatial transformer networks","author":"Jaderberg","year":"2015"},{"key":"10.1016\/j.image.2018.12.009_b20","first-page":"5","article-title":"Reading digits in natural images with unsupervised feature learning","volume":"Vol. 2011","author":"Netzer","year":"2011"},{"year":"2011","series-title":"The Caltech-Ucsd Birds-200-2011 Dataset","author":"Wah","key":"10.1016\/j.image.2018.12.009_b21"},{"key":"10.1016\/j.image.2018.12.009_b22","series-title":"Multimedia Signal Processing, MMSP, 2017 IEEE 19th International Workshop on","first-page":"1","article-title":"Fine-grained vehicle classificationusing deep residual networks with multiscale attention windows","author":"Ghassemi","year":"2017"},{"key":"10.1016\/j.image.2018.12.009_b23","doi-asserted-by":"crossref","unstructured":"S. Zagoruyko, N. Komodakis, Wide residual networks, 2016, arXiv preprint arXiv:1605.07146.","DOI":"10.5244\/C.30.87"},{"key":"10.1016\/j.image.2018.12.009_b24","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.image.2018.12.009_b25","doi-asserted-by":"crossref","unstructured":"L. Yang, P. Luo, C. Change\u00a0Loy, X. Tang, A large-scale car dataset for fine-grained categorization and verification, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 3973\u20133981.","DOI":"10.1109\/CVPR.2015.7299023"},{"key":"10.1016\/j.image.2018.12.009_b26","series-title":"Computer Vision Workshops, ICCVW, 2013 IEEE International Conference on","first-page":"554","article-title":"3D object representations for fine-grained categorization","author":"Krause","year":"2013"},{"key":"10.1016\/j.image.2018.12.009_b27","series-title":"IEEE Conference on Computer Vision and Pattern Recognition","first-page":"580","article-title":"Rich feature hierarchies for accurate object detection and semantic segmentation","author":"Girshick","year":"2014"},{"key":"10.1016\/j.image.2018.12.009_b28","series-title":"IEEE International Conference on Computer Vision","first-page":"1440","article-title":"Fast R-CNN","author":"Girshick","year":"2015"},{"key":"10.1016\/j.image.2018.12.009_b29","series-title":"Neural Information Processing Systems 28","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"Ren","year":"2015"},{"key":"10.1016\/j.image.2018.12.009_b30","series-title":"European Conference on Computer Vision","first-page":"834","article-title":"Part-based R-CNNs for fine-grained category detection","author":"Zhang","year":"2014"},{"key":"10.1016\/j.image.2018.12.009_b31","series-title":"Intelligent Transportation Systems, ITSC, 2014 IEEE 17th International Conference on","first-page":"3094","article-title":"Vehicle model recognition using geometry and appearance of car emblems from rear view images","author":"Llorca","year":"2014"},{"key":"10.1016\/j.image.2018.12.009_b32","series-title":"Computer Vision and Pattern Recognition, CVPR, 2015 IEEE Conference on","first-page":"5546","article-title":"Fine-grained recognition without part annotations","author":"Krause","year":"2015"},{"issue":"11","key":"10.1016\/j.image.2018.12.009_b33","doi-asserted-by":"crossref","first-page":"3147","DOI":"10.1109\/TITS.2017.2679114","article-title":"Deep CNNs with spatially weighted pooling for fine-grained car recognition","volume":"18","author":"Hu","year":"2017","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.image.2018.12.009_b34","unstructured":"G.E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, R.R. Salakhutdinov, Improving neural networks by preventing co-adaptation of feature detectors, 2012, arXiv preprint arXiv:1207.0580."},{"key":"10.1016\/j.image.2018.12.009_b35","series-title":"Advances in Neural Information Processing Systems","first-page":"950","article-title":"A simple weight decay can improve generalization","author":"Krogh","year":"1992"},{"key":"10.1016\/j.image.2018.12.009_b36","series-title":"Proceedings of COMPSTAT\u20192010","first-page":"177","article-title":"Large-scale machine learning with stochastic gradient descent","author":"Bottou","year":"2010"},{"key":"10.1016\/j.image.2018.12.009_b37","unstructured":"X. Glorot, Y. Bengio, Understanding the difficulty of training deep feedforward neural networks, in: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, 2010, pp. 249\u2013256."},{"key":"10.1016\/j.image.2018.12.009_b38","series-title":"Computer Vision, ICCV, 2013 IEEE International Conference on","first-page":"321","article-title":"Symbiotic segmentation and part localization for fine-grained categorization","author":"Chai","year":"2013"},{"key":"10.1016\/j.image.2018.12.009_b39","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1016\/j.patrec.2014.06.011","article-title":"Revisiting the fisher vector for fine-grained classification","volume":"49","author":"Gosselin","year":"2014","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.image.2018.12.009_b40","doi-asserted-by":"crossref","unstructured":"T.Y. Lin, A. RoyChowdhury, S. Maji, Bilinear CNN models for fine-grained visual recognition, in: Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 1449\u20131457.","DOI":"10.1109\/ICCV.2015.170"},{"key":"10.1016\/j.image.2018.12.009_b41","doi-asserted-by":"crossref","unstructured":"J. Sochor, A. Herout, J. Havel, Boxcars: 3D boxes as CNN input for improved fine-grained vehicle recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 3006\u20133015.","DOI":"10.1109\/CVPR.2016.328"}],"container-title":["Signal Processing: Image Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/api.elsevier.com\/content\/article\/PII:S0923596518307331?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/api.elsevier.com\/content\/article\/PII:S0923596518307331?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2019,11,12]],"date-time":"2019-11-12T18:12:20Z","timestamp":1573582340000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/linkinghub.elsevier.com\/retrieve\/pii\/S0923596518307331"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,3]]},"references-count":41,"alternative-id":["S0923596518307331"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/j.image.2018.12.009","relation":{},"ISSN":["0923-5965"],"issn-type":[{"type":"print","value":"0923-5965"}],"subject":[],"published":{"date-parts":[[2019,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Vehicle joint make and model recognition with multiscale attention windows","name":"articletitle","label":"Article Title"},{"value":"Signal Processing: Image Communication","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/j.image.2018.12.009","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2018 Elsevier B.V. All rights reserved.","name":"copyright","label":"Copyright"}]}}