{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T03:54:45Z","timestamp":1777694085537,"version":"3.51.4"},"reference-count":91,"publisher":"SAGE Publications","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["ICA"],"published-print":{"date-parts":[[2020,12,21]]},"abstract":"<jats:p>In recent years we have witnessed significant progress in the performance of object detection in images. This advance stems from the use of rich discriminative features produced by deep models and the adoption of new training techniques. Although these techniques have been extensively used in the mainstream deep learning-based models, it is still an open issue to analyze their impact in alternative, and computationally more efficient, ensemble-based approaches. In this paper we evaluate the impact of the adoption of data augmentation, bounding box refinement and multi-scale processing in the context of multi-class Boosting-based object detection. In our experiments we show that use of these training advancements significantly improves the object detection performance.<\/jats:p>","DOI":"10.3233\/ica-200636","type":"journal-article","created":{"date-parts":[[2020,7,3]],"date-time":"2020-07-03T13:31:13Z","timestamp":1593783073000},"page":"81-96","source":"Crossref","is-referenced-by-count":11,"title":["Improving multi-class Boosting-based object detection"],"prefix":"10.1177","volume":"28","author":[{"given":"Jos\u00e9 Miguel","family":"Buenaposada","sequence":"first","affiliation":[{"name":"ETSII, Universidad Rey Juan Carlos, M\u00f3stoles, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luis","family":"Baumela","sequence":"additional","affiliation":[{"name":"Departamento de Inteligencia Artificial, Universidad Polit\u00e9cnica de Madrid, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"key":"10.3233\/ICA-200636_ref2","doi-asserted-by":"crossref","unstructured":"Ferrari V, Marin-Jimenez M, Zisserman A. Progressive Search Space Reduction for Human Pose Estimation. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition; 2008.","DOI":"10.1109\/CVPR.2008.4587468"},{"key":"10.3233\/ICA-200636_ref3","doi-asserted-by":"crossref","unstructured":"Chen X, Kundu K, Zhang Z, Ma H, Fidler S, Urtasun R. Monocular 3D Object Detection for Autonomous Driving. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition; 2016. pp. 2147\u20132156.","DOI":"10.1109\/CVPR.2016.236"},{"issue":"4","key":"10.3233\/ICA-200636_ref4","doi-asserted-by":"crossref","first-page":"321","DOI":"10.3233\/ICA-180577","article-title":"Vehicle type detection by ensembles of convolutional neural networks operating on super-resolved images","volume":"25","author":"Molina-Cabello","year":"2018","journal-title":"Integrated Computer-Aided Engineering"},{"key":"10.3233\/ICA-200636_ref5","doi-asserted-by":"crossref","unstructured":"Jaderberg M, Vedaldi A, Zisserman A. Deep Features for Text Spotting. In: Proc. European Conf. Computer Vision; 2014.","DOI":"10.1007\/978-3-319-10593-2_34"},{"key":"10.3233\/ICA-200636_ref6","unstructured":"Viola PA, Jones MJ. Fast and Robust Classification using Asymmetric AdaBoost and a Detector Cascade. In: Conf. Neural Information Processing Systems; 2001. pp. 1311\u20131318."},{"key":"10.3233\/ICA-200636_ref7","doi-asserted-by":"crossref","unstructured":"Dalal N, Triggs B. Histograms of oriented gradients for human detection. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition. Vol. 1; 2005. pp. 886\u2013893.","DOI":"10.1109\/CVPR.2005.177"},{"issue":"8","key":"10.3233\/ICA-200636_ref8","doi-asserted-by":"crossref","first-page":"1532","DOI":"10.1109\/TPAMI.2014.2300479","article-title":"Fast feature pyramids for object detection","volume":"36","author":"Dollar","year":"2014","journal-title":"IEEE Trans Pattern Analysis and Machine Intelligence"},{"issue":"11","key":"10.3233\/ICA-200636_ref9","doi-asserted-by":"crossref","first-page":"2188","DOI":"10.1109\/TPAMI.2011.70","article-title":"Hough forests for object detection, tracking, and action recognition","volume":"33","author":"Gall","year":"2011","journal-title":"IEEE Trans Pattern Analysis and Machine Intelligence"},{"key":"10.3233\/ICA-200636_ref10","unstructured":"Ren S, He K, Girshick R, Sun J. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. In: Conf. Neural Information Processing Systems; 2015."},{"key":"10.3233\/ICA-200636_ref11","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A. You Only Look Once: Unified, Real-Time Object Detection. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition; 2016.","DOI":"10.1109\/CVPR.2016.91"},{"key":"10.3233\/ICA-200636_ref12","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed SE, Fu C, et al. SSD: Single Shot MultiBox Detector. In: Proc. European Conf. Computer Vision; 2016. pp. 21\u201337.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"10.3233\/ICA-200636_ref13","doi-asserted-by":"crossref","unstructured":"Zhang S, Benenson R, Schiele B. Filtered channel features for pedestrian detection. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition; 2015.","DOI":"10.1109\/CVPR.2015.7298784"},{"key":"10.3233\/ICA-200636_ref14","doi-asserted-by":"crossref","unstructured":"Benenson R, Mathias M, Timofte R, Van Gool L. Pedestrian detection at 100 frames per second. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition; 2012.","DOI":"10.1109\/CVPR.2012.6248017"},{"key":"10.3233\/ICA-200636_ref15","doi-asserted-by":"crossref","unstructured":"Mathias M, Benenson R, Pedersoli M, Van Gool L. Face detection without bells and whistles. In: Proc. European Conf. Computer Vision; 2014.","DOI":"10.1007\/978-3-319-10593-2_47"},{"issue":"5","key":"10.3233\/ICA-200636_ref16","doi-asserted-by":"crossref","first-page":"2511","DOI":"10.1109\/TITS.2015.2409889","article-title":"Learning to detect vehicles by clustering appearance patterns","volume":"16","author":"Ohn-Bar","year":"2015","journal-title":"IEEE Trans Intelligent Transportation Systems"},{"issue":"10","key":"10.3233\/ICA-200636_ref17","doi-asserted-by":"crossref","first-page":"2071","DOI":"10.1109\/TPAMI.2015.2389830","article-title":"Regionlets for generic object detection","volume":"37","author":"Wang","year":"2015","journal-title":"IEEE Trans Pattern Analysis and Machine Intelligence"},{"issue":"3","key":"10.3233\/ICA-200636_ref18","doi-asserted-by":"crossref","first-page":"197","DOI":"10.3233\/ICA-2010-0345","article-title":"Enhanced probabilistic neural network with local decision circles: a robust classifier","volume":"17","author":"Ahmadlou","year":"2010","journal-title":"Integr Comput-Aided Eng"},{"issue":"12","key":"10.3233\/ICA-200636_ref19","doi-asserted-by":"crossref","first-page":"3074","DOI":"10.1109\/TNNLS.2017.2682102","article-title":"A new neural dynamic classification algorithm","volume":"28","author":"Rafiei","year":"2017","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.3233\/ICA-200636_ref21","doi-asserted-by":"crossref","unstructured":"Ren J, Chen X, Liu J, Sun W, Pang J, Yan Q, et al. Accurate Single Stage Detector Using Recurrent Rolling Convolution. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition; 2017.","DOI":"10.1109\/CVPR.2017.87"},{"key":"10.3233\/ICA-200636_ref22","doi-asserted-by":"crossref","unstructured":"Juranek R, Herout A, Dubska M, Zemcik P. Real-Time Pose Estimation Piggybacked on Object Detection. In: Proc. Int\u2019l Conf. Computer Vision; 2015.","DOI":"10.1109\/ICCV.2015.274"},{"key":"10.3233\/ICA-200636_ref23","doi-asserted-by":"crossref","unstructured":"Yang F, Choi W, Lin Y. Exploit All the Layers: Fast and Accurate CNN Object Detector With Scale Dependent Pooling and Cascaded Rejection Classifiers. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition; 2016.","DOI":"10.1109\/CVPR.2016.234"},{"key":"10.3233\/ICA-200636_ref24","doi-asserted-by":"crossref","first-page":"467","DOI":"10.1016\/j.patcog.2018.02.022","article-title":"BAdaCost: multi-class boosting with costs","volume":"79","author":"Fern\u00e1ndez-Baldera","year":"2018","journal-title":"Pattern Recognition"},{"key":"10.3233\/ICA-200636_ref25","doi-asserted-by":"crossref","unstructured":"Ohn-Bar E, Trivedi MM. To Boost or Not to Boost? On the Limits of Boosted Trees for Object Detection. In: Proc. Int\u2019l Conf. Pattern Recognition; 2016.","DOI":"10.1109\/ICPR.2016.7900151"},{"issue":"2","key":"10.3233\/ICA-200636_ref26","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1214\/aos\/1016218223","article-title":"Additive logistic regression: a statistical view of boosting","volume":"28","author":"Friedman","year":"2000","journal-title":"The Annals of Statistics"},{"key":"10.3233\/ICA-200636_ref27","doi-asserted-by":"crossref","unstructured":"Fern\u00e1ndez-Baldera A, Buenaposada JM, Baumela L. Multi-class Boosting for Imbalanced Data. In: Proc. of Iberian Conf. Pattern Recognition and Image Analysis; 2015. pp. 57\u201364.","DOI":"10.1007\/978-3-319-19390-8_7"},{"key":"10.3233\/ICA-200636_ref28","doi-asserted-by":"crossref","first-page":"349","DOI":"10.4310\/SII.2009.v2.n3.a8","article-title":"Multi-class AdaBoost","volume":"2","author":"Zhu","year":"2009","journal-title":"Statistics and its Interface"},{"key":"10.3233\/ICA-200636_ref29","unstructured":"Zhang C, Viola PA. Multiple-Instance Pruning For Learning Efficient Cascade Detectors. In: Conf. Neural Information Processing Systems; 2007. pp. 1681\u20131688."},{"key":"10.3233\/ICA-200636_ref30","unstructured":"Yang B, Yan J, Lei Z, Li SZ. Aggregate channel features for multi-view face detection. In: IEEE Int\u2019l J. Conference on Biometrics; 2014. pp. 1\u20138."},{"key":"10.3233\/ICA-200636_ref31","doi-asserted-by":"crossref","unstructured":"Hu P, Ramanan D. Finding Tiny Faces. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition; 2017.","DOI":"10.1109\/CVPR.2017.166"},{"key":"10.3233\/ICA-200636_ref32","doi-asserted-by":"crossref","unstructured":"Dollar P, Belongie S, Perona P. The Fastest Pedestrian Detector in the West. In: Proc. British Machine Vision Conf.; 2010. pp.\u00a068.1\u201311.","DOI":"10.5244\/C.24.68"},{"key":"10.3233\/ICA-200636_ref33","unstructured":"Nam W, Dollar P. Local Decorrelation For Improved Pedestrian Detection. In: Conf. Neural Information Processing Systems; 2014."},{"key":"10.3233\/ICA-200636_ref34","doi-asserted-by":"crossref","unstructured":"Geiger A, Lenz P, Urtasun R. Are we ready for Autonomous Driving? The KITTI Vision Benchmark Suite. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition; 2012.","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"10.3233\/ICA-200636_ref36","doi-asserted-by":"crossref","unstructured":"Buenaposada JM, Baumela L. Boosting Object Detection in Cyberphysical Systems. In: Understanding the Brain Function and Emotions, LNCS volume 11486. Cham: Springer International Publishing; 2019. pp. 309\u2013318.","DOI":"10.1007\/978-3-030-19591-5_32"},{"key":"10.3233\/ICA-200636_ref37","unstructured":"Simonyan K, Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition. In: International Conference on Learning Representations; 2015."},{"issue":"3","key":"10.3233\/ICA-200636_ref38","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"Image net large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"International Journal of Computer Vision (IJCV)"},{"issue":"4","key":"10.3233\/ICA-200636_ref39","doi-asserted-by":"crossref","first-page":"1002","DOI":"10.1109\/TITS.2015.2496795","article-title":"Fast detection of multiple objects in traffic scenes with a common detection framework","volume":"17","author":"Hu","year":"2016","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"10.3233\/ICA-200636_ref40","doi-asserted-by":"crossref","unstructured":"Xiang Y, Choi W, Lin Y, Savarese S. Subcategory-Aware Convolutional Neural Networks for Object Proposals and Detection. In: 2017 IEEE Winter Conference on Applications of Computer Vision (WACV); 2017. pp. 924\u2013933.","DOI":"10.1109\/WACV.2017.108"},{"issue":"3","key":"10.3233\/ICA-200636_ref41","doi-asserted-by":"crossref","first-page":"223","DOI":"10.3233\/ICA-190599","article-title":"Human action recognition using hierarchic body related occupancy maps","volume":"26","author":"Roegiers","year":"2019","journal-title":"Integrated Computer-Aided Engineering"},{"issue":"3","key":"10.3233\/ICA-200636_ref42","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1109\/MC.2018.1731058","article-title":"The cyber-physical systems revolution","volume":"51","author":"Serpanos","year":"2018","journal-title":"Computer"},{"issue":"3","key":"10.3233\/ICA-200636_ref43","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1109\/MC.2009.81","article-title":"Cyber-physical systems","volume":"42","author":"Wolf","year":"2009","journal-title":"Computer"},{"issue":"3","key":"10.3233\/ICA-200636_ref44","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1561\/2300000023","article-title":"Micro-scale mobile robotics","volume":"2","author":"Diller","year":"2013","journal-title":"Foundations and Trends in Robotics"},{"issue":"1","key":"10.3233\/ICA-200636_ref46","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1145\/1007730.1007736","article-title":"Learning from imbalanced data sets with boosting and data generation: the DataBoost-IM approach","volume":"6","author":"Guo","year":"2004","journal-title":"SIGKDD Explorations Newsletter"},{"issue":"7","key":"10.3233\/ICA-200636_ref47","doi-asserted-by":"crossref","first-page":"1423","DOI":"10.1109\/TPAMI.2011.225","article-title":"Trainable convolution filters and their application to face recognition","volume":"34","author":"Kumar","year":"2012","journal-title":"IEEE Trans Pattern Analysis and Machine Intelligence"},{"issue":"6","key":"10.3233\/ICA-200636_ref48","doi-asserted-by":"crossref","first-page":"1148","DOI":"10.1109\/TPAMI.2014.2362759","article-title":"Demographic estimation from face images: human vs. machine performance","volume":"37","author":"Han","year":"2015","journal-title":"IEEE Trans Pattern Analysis and Machine Intelligence"},{"issue":"7","key":"10.3233\/ICA-200636_ref50","doi-asserted-by":"crossref","first-page":"1270","DOI":"10.1109\/TPAMI.2007.70772","article-title":"Multiscale categorical object recognition using contour fragments","volume":"30","author":"Shotton","year":"2008","journal-title":"IEEE Trans Pattern Analysis and Machine Intelligence"},{"key":"10.3233\/ICA-200636_ref51","doi-asserted-by":"crossref","unstructured":"Mahamud S, Hebert M, Shi J. Object recognition using boosted discriminants. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition. Vol. 1; 2001. pp. I\u2013551\u2013I\u2013558.","DOI":"10.1109\/CVPR.2001.990522"},{"key":"10.3233\/ICA-200636_ref53","unstructured":"Freund Y, Schapire RE. Experiments with a New Boosting Algorithm. In: Proc. Int\u2019l Conf. on Machine Learning; 1996. pp. 148\u2013156."},{"key":"10.3233\/ICA-200636_ref54","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1006\/jcss.1997.1504","article-title":"A decision theoretic generalization of on-line learning and an application to boosting","volume":"55","author":"Freund","year":"1997","journal-title":"J of Computer and System Sciences"},{"key":"10.3233\/ICA-200636_ref55","unstructured":"Schapire RE. Using Output Codes to Boost Multiclass Learning Problems. In: Proc. Int\u2019l Conf. on Machine Learning; 1997. pp. 313\u2013321."},{"key":"10.3233\/ICA-200636_ref56","doi-asserted-by":"crossref","unstructured":"O\u2019Brien DB, Gupta MR, Gray RM. Cost-sensitive Multi-class classification from probability estimates. In: Proc. Int\u2019l Conf. on Machine Learning; 2008. pp. 712\u2013719.","DOI":"10.1145\/1390156.1390246"},{"key":"10.3233\/ICA-200636_ref57","doi-asserted-by":"crossref","unstructured":"Ting KM, Zheng Z. Boosting cost-sensitive trees. In: Proc. International Conference on Discovery Science; 1998. pp. 244\u2013255.","DOI":"10.1007\/3-540-49292-5_22"},{"key":"10.3233\/ICA-200636_ref58","doi-asserted-by":"crossref","unstructured":"Domingos P. MetaCost: A General Method for Making Classifiers Cost-Sensitive. In: Proc. Int\u2019l Conf. on Knowledge Discovery and Data Mining; 1999. pp. 155\u2013164.","DOI":"10.1145\/312129.312220"},{"key":"10.3233\/ICA-200636_ref59","unstructured":"Fan W, Stolfo SJ, Zhang J, Chan PK. AdaCost: Misclassification Cost-sensitive Boosting. In: Proc. Int\u2019l Conf. on Machine Learning; 1999. pp. 97\u2013105."},{"key":"10.3233\/ICA-200636_ref60","doi-asserted-by":"crossref","unstructured":"Guruswami V, Sahai A. Multiclass learning, boosting and error correcting codes. In: Proc. Annual Conference on Learning Theory; 1999. pp. 145\u2013155.","DOI":"10.1145\/307400.307429"},{"key":"10.3233\/ICA-200636_ref61","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1023\/A:1007614523901","article-title":"Improved boosting algorithms using confidence-rated predictions","volume":"37","author":"Schapire","year":"1999","journal-title":"Machine Learning"},{"key":"10.3233\/ICA-200636_ref62","first-page":"113","article-title":"Reducing multiclass to binary: a unifying approach for margin classifiers","volume":"1","author":"Allwein","year":"2000","journal-title":"J of Machine Learning Research"},{"key":"10.3233\/ICA-200636_ref63","doi-asserted-by":"crossref","unstructured":"Ting KM. A Comparative Study of Cost-Sensitive Boosting Algorithms. In: Proc. Int\u2019l Conf. on Machine Learning; 2000. pp. 983\u2013990.","DOI":"10.1007\/3-540-45164-1_42"},{"key":"10.3233\/ICA-200636_ref64","unstructured":"Elkan C. The Foundations of Cost-Sensitive Learning. In: Proc. Int\u2019l Joint Conf. on Artificial Intelligence; 2001. pp. 973\u2013978."},{"key":"10.3233\/ICA-200636_ref65","doi-asserted-by":"crossref","unstructured":"Abe N, Zadrozny B, Langford J. An iterative method for multi-class cost-sensitive learning. In: Proc. Int\u2019l Conf. on Knowledge Discovery and Data Mining; 2004. pp. 3\u201311.","DOI":"10.1145\/1014052.1014056"},{"key":"10.3233\/ICA-200636_ref66","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1198\/016214504000000098","article-title":"Multicategory Support Vector Machines: theory and application to the classification of microarray data and satellite radiance data","volume":"99","author":"Lee","year":"2004","journal-title":"J American Statistical Association"},{"key":"10.3233\/ICA-200636_ref67","doi-asserted-by":"crossref","unstructured":"Torralba A, Murphy KP, Freeman WT. Sharing Features: Efficient Boosting Procedures for Multiclass Object Detection. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition; 2004. pp. 762\u2013769.","DOI":"10.1109\/CVPR.2004.1315241"},{"issue":"2","key":"10.3233\/ICA-200636_ref68","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1023\/B:VISI.0000013087.49260.fb","article-title":"Robust real-time face detection","volume":"57","author":"Viola","year":"2004","journal-title":"Int\u2019l JComputer Vision"},{"key":"10.3233\/ICA-200636_ref69","doi-asserted-by":"crossref","unstructured":"Bourdev L, Brandt J. Robust object detection via soft cascade. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition. Vol. 2; 2005. pp. 236\u2013243.","DOI":"10.1109\/CVPR.2005.310"},{"key":"10.3233\/ICA-200636_ref70","doi-asserted-by":"crossref","unstructured":"Sun Y, Wong AKC, Wang Y. Parameter Inference of Cost-Sensitive Boosting Algorithms. In: Proc. Int\u2019l Conf. on Machine Learning and Data Mining; 2005. pp. 21\u201330.","DOI":"10.1007\/11510888_3"},{"key":"10.3233\/ICA-200636_ref71","first-page":"1","article-title":"Statistical comparisons of classifiers over multiple data sets","volume":"7","author":"Demsar","year":"2006","journal-title":"J of Machine Learning Research"},{"key":"10.3233\/ICA-200636_ref72","doi-asserted-by":"crossref","unstructured":"Sun Y, Kamel MS, Wang Y. Boosting for Learning Multiple Classes with Imbalanced Class Distribution. In: Proc. Int\u2019l Conference on Data Mining; 2006. pp. 592\u2013602.","DOI":"10.1109\/ICDM.2006.29"},{"key":"10.3233\/ICA-200636_ref73","doi-asserted-by":"crossref","unstructured":"Masnadi-Shirazi H, Vasconcelos N. Asymmetric Boosting. In: Proc. Int\u2019l Conf. on Machine Learning; 2007. pp. 609\u2013619.","DOI":"10.1145\/1273496.1273573"},{"issue":"12","key":"10.3233\/ICA-200636_ref74","doi-asserted-by":"crossref","first-page":"3358","DOI":"10.1016\/j.patcog.2007.04.009","article-title":"Cost-sensitive boosting for classification of imbalanced data","volume":"40","author":"Sun","year":"2007","journal-title":"Pattern Recognition"},{"key":"10.3233\/ICA-200636_ref75","doi-asserted-by":"crossref","unstructured":"Lozano AC, Abe N. Multi-class Cost-sensitive Boosting with p-norm Loss Functions. In: Proc. Int\u2019l Conf. on Knowledge Discovery and Data Mining; 2008. pp. 506\u2013514.","DOI":"10.1145\/1401890.1401953"},{"key":"10.3233\/ICA-200636_ref76","doi-asserted-by":"crossref","first-page":"1290","DOI":"10.1214\/08-AOAS198","article-title":"New multicategory boosting algorithms based on multicategory fisher-consistent losses","volume":"2","author":"Zou","year":"2008","journal-title":"Annals of Applied Statistics"},{"issue":"9","key":"10.3233\/ICA-200636_ref77","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.1109\/TKDE.2008.239","article-title":"Learning from imbalanced data","volume":"21","author":"He","year":"2009","journal-title":"IEEE Trans on Konwledge and Data Engineering"},{"issue":"7","key":"10.3233\/ICA-200636_ref78","doi-asserted-by":"crossref","first-page":"1572","DOI":"10.1016\/j.patcog.2008.12.011","article-title":"A closed-form reduction of multi-class cost-sensitive learning to weighted multi-class learning","volume":"42","author":"Xia","year":"2009","journal-title":"Pattern Recognition"},{"issue":"3","key":"10.3233\/ICA-200636_ref79","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1111\/j.1467-8640.2010.00358.x","article-title":"On multi-class cost-sensitive learning","volume":"26","author":"Zhou","year":"2010","journal-title":"Computational Intelligence"},{"issue":"2","key":"10.3233\/ICA-200636_ref80","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","article-title":"The pascal visual object classes (VOC) challenge","volume":"88","author":"Everingham","year":"2010","journal-title":"Int\u2019l JComputer Vision"},{"key":"10.3233\/ICA-200636_ref82","doi-asserted-by":"crossref","unstructured":"\u00f6stinger MK, Wohlhart P, Roth PM, Bischof H. Annotated Facial Landmarks in the Wild: A large-scale, real-world database for facial landmark localization. In: Proc. Int\u2019l Conf. Computer Vision Workshops; 2011. pp. 2144\u20132151.","DOI":"10.1109\/ICCVW.2011.6130513"},{"issue":"2","key":"10.3233\/ICA-200636_ref83","doi-asserted-by":"crossref","first-page":"294","DOI":"10.1109\/TPAMI.2010.71","article-title":"Cost-sensitive boosting","volume":"33","author":"Masnadi-Shirazi","year":"2011","journal-title":"IEEE Trans Pattern Analysis and Machine Intelligence"},{"key":"10.3233\/ICA-200636_ref84","unstructured":"Saberian MJ, Vasconcelos N. Multiclass Boosting: Theory and Algorithms. In: Conf. Neural Information Processing Systems; 2011."},{"issue":"3","key":"10.3233\/ICA-200636_ref85","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1016\/j.patrec.2011.10.022","article-title":"Shedding light on the asymmetric learning capability of AdaBoost","volume":"33","author":"Landesa-V\u00e1zquez","year":"2012","journal-title":"Pattern Recognition Letters"},{"key":"10.3233\/ICA-200636_ref86","doi-asserted-by":"crossref","unstructured":"Liu X, Zhou Z. Towards Cost-Sensitive Learning for Real-World Applications. In: Pacific-Asia Conf. Knowledge Discovery and Data Mining Workshops. Vol. 7104; 2012. pp.\u00a0494\u2013505.","DOI":"10.1007\/978-3-642-28320-8_42"},{"key":"10.3233\/ICA-200636_ref87","unstructured":"Zhu X, Ramanan D. Face detection, pose estimation, and landmark localization in the wild. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition; 2012. pp. 2879\u20132886."},{"key":"10.3233\/ICA-200636_ref88","doi-asserted-by":"crossref","unstructured":"Benenson R, Mathias M, Tuytelaars T, Van Gool L. Seeking the strongest rigid detector. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition; 2013.","DOI":"10.1109\/CVPR.2013.470"},{"key":"10.3233\/ICA-200636_ref89","doi-asserted-by":"crossref","unstructured":"Mathias M, Benenson R, Timofte R, Van Gool L. Handling Occlusions with Franken-classifiers. In: Proc. Int\u2019l Conf. Computer Vision; 2013.","DOI":"10.1109\/ICCV.2013.190"},{"issue":"1","key":"10.3233\/ICA-200636_ref90","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1080\/10618600.2011.643151","article-title":"Boosting the generalized margin in cost-sensitive multiclass classification","volume":"22","author":"Wang","year":"2013","journal-title":"J Computational and Graphical Statistics"},{"issue":"5","key":"10.3233\/ICA-200636_ref91","doi-asserted-by":"crossref","first-page":"2080","DOI":"10.1016\/j.patcog.2013.11.024","article-title":"Multi-class boosting with asymmetric weak-learners","volume":"47","author":"Fern\u00e1ndez-Baldera","year":"2014","journal-title":"Pattern Recognition"},{"key":"10.3233\/ICA-200636_ref92","doi-asserted-by":"crossref","unstructured":"Benenson R, Omran M, Hosang J, Schiele B. Ten years of pedestrian detection, what have we learned? In: Proc. European Conf. Computer Vision, CVRSUAD Workshop; 2014.","DOI":"10.1007\/978-3-319-16181-5_47"},{"key":"10.3233\/ICA-200636_ref93","unstructured":"Parambath SAP, Usunier N, Grandvalet Y. Optimizing F-measures by Cost-sensitive Classification. In: Conf. Neural Information Processing Systems; 2014. pp. 2123\u20132131."},{"issue":"9","key":"10.3233\/ICA-200636_ref94","doi-asserted-by":"crossref","first-page":"1829","DOI":"10.1109\/TPAMI.2015.2497699","article-title":"Learning and-or model to represent context and occlusion for car detection and viewpoint estimation","volume":"38","author":"Wu","year":"2016","journal-title":"IEEE Trans Pattern Analysis and Machine Intelligence"},{"key":"10.3233\/ICA-200636_ref95","doi-asserted-by":"crossref","unstructured":"Yang B, Yan J, Lei Z, Li SZ. Convolutional Channel Features. In: Proc. Int\u2019l Conf. Computer Vision; 2015. pp. 82\u201390.","DOI":"10.1109\/ICCV.2015.18"},{"issue":"2\u20133","key":"10.3233\/ICA-200636_ref96","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1007\/s10994-016-5572-x","article-title":"Cost-sensitive boosting algorithms: do we really need them","volume":"104","author":"Nikolaou","year":"2016","journal-title":"Machine Learning"},{"key":"10.3233\/ICA-200636_ref97","doi-asserted-by":"crossref","unstructured":"Cai Z, Fan Q, Feris RS, Vasconcelos N. In: A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection. Springer; 2016. pp. 354\u2013370.","DOI":"10.1007\/978-3-319-46493-0_22"},{"key":"10.3233\/ICA-200636_ref98","doi-asserted-by":"crossref","unstructured":"Oeljeklaus M, Hoffmann F, Bertram T. A Fast Multi-Task CNN for Spatial Understanding of Traffic Scenes. In: 2018 21st International Conference on Intelligent Transportation Systems (ITSC); 2018. pp. 2825\u20132830.","DOI":"10.1109\/ITSC.2018.8569822"}],"container-title":["Integrated Computer-Aided Engineering"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/ICA-200636","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:14:25Z","timestamp":1777454065000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/ICA-200636"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,21]]},"references-count":91,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.3233\/ica-200636","relation":{},"ISSN":["1069-2509","1875-8835"],"issn-type":[{"value":"1069-2509","type":"print"},{"value":"1875-8835","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,12,21]]}}}