{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T07:30:58Z","timestamp":1767598258991},"reference-count":29,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"9","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2021,9,1]]},"DOI":"10.1587\/transinf.2021edp7026","type":"journal-article","created":{"date-parts":[[2021,8,31]],"date-time":"2021-08-31T22:19:06Z","timestamp":1630448346000},"page":"1478-1485","source":"Crossref","is-referenced-by-count":7,"title":["Noisy Localization Annotation Refinement for Object Detection"],"prefix":"10.1587","volume":"E104.D","author":[{"given":"Jiafeng","family":"MAO","sequence":"first","affiliation":[{"name":"Dept. of Information and Communication Eng., The University of Tokyo"}]},{"given":"Qing","family":"YU","sequence":"additional","affiliation":[{"name":"Dept. of Information and Communication Eng., The University of Tokyo"}]},{"given":"Kiyoharu","family":"AIZAWA","sequence":"additional","affiliation":[{"name":"Dept. of Information and Communication Eng., The University of Tokyo"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] J. Mao, Q. Yu, and K. Aizawa, \u201cNoisy localization annotation refinement for object detection,\u201d 2020 IEEE Int. Conf. Image Process. (ICIP), pp.2006-2010, 2020. 10.1109\/ICIP40778.2020.9190728","DOI":"10.1109\/ICIP40778.2020.9190728"},{"key":"2","doi-asserted-by":"publisher","unstructured":"[2] S. Ren, K. He, R. Girshick, and J. Sun, \u201cFaster r-cnn: Towards real-time object detection with region proposal networks,\u201d IEEE Trans. Pattern Anal. Mach. Intell., vol.39, no.6, pp.1137-1149, June 2016. 10.1109\/TPAMI.2016.2577031","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] R. Girshick, J. Donahue, T. Darrell, and J. Malik, \u201cRich feature hierarchies for accurate object detection and semantic segmentation,\u201d CVPR, pp.580-587, 2014. 10.1109\/CVPR.2014.81","DOI":"10.1109\/CVPR.2014.81"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] R. Girshick, \u201cFast r-cnn,\u201d ICCV, pp.1440-1448, 2015. 10.1109\/ICCV.2015.169","DOI":"10.1109\/ICCV.2015.169"},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] K. He, G. Gkioxari, P. Doll\u00e1r, and R. Girshick, \u201cMask r-cnn,\u201d ICCV, pp.2961-2969, 2017. 10.1109\/ICCV.2017.322","DOI":"10.1109\/ICCV.2017.322"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, \u201cYou only look once: Unified, real-time object detection,\u201d CVPR, pp.779-788, 2016. 10.1109\/CVPR.2016.91","DOI":"10.1109\/CVPR.2016.91"},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] J. Redmon and A. Farhadi, \u201cYolo9000: better, faster, stronger,\u201d CVPR, pp.7263-7271, 2017. 10.1109\/CVPR.2017.690","DOI":"10.1109\/CVPR.2017.690"},{"key":"8","unstructured":"[8] J. Redmon and A. Farhadi, \u201cYolov3: An incremental improvement,\u201d arXiv preprint arXiv:1804.02767, 2018."},{"key":"9","unstructured":"[9] A. Bochkovskiy, C.Y. Wang, and H.Y.M. Liao, \u201cYolov4: Optimal speed and accuracy of object detection,\u201d arXiv preprint arXiv:2004.10934, 2020."},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.Y. Fu, and A.C. Berg, \u201cSsd: Single shot multibox detector,\u201d ECCV, pp.21-37, Springer, 2016. 10.1007\/978-3-319-46448-0_2","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] T.Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Doll\u00e1r, and C.L. Zitnick, \u201cMicrosoft coco: Common objects in context,\u201d ECCV, pp.740-755, Springer, 2014. 10.1007\/978-3-319-10602-1_48","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] J. Deng, W. Dong, R. Socher, L.J. Li, K. Li, and L. Fei-Fei, \u201cImagenet: A large-scale hierarchical image database,\u201d CVPR, pp.248-255, 2009. 10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] D.P. Papadopoulos, J.R. Uijlings, F. Keller, and V. Ferrari, \u201cExtreme clicking for efficient object annotation,\u201d ICCV, pp.4930-4939, 2017. 10.1109\/ICCV.2017.528","DOI":"10.1109\/ICCV.2017.528"},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] E. David, S. Madec, P. Sadeghi-Tehran, H. Aasen, B. Zheng, S. Liu, N. Kirchgessner, G. Ishikawa, K. Nagasawa, M.A. Badhon, C. Pozniak, B. de Solan, A. Hund, S.C. Chapman, F. Baret, I. Stavness, and W. Guo, \u201cGlobal wheat head detection (gwhd) dataset: a large and diverse dataset of high resolution rgb labelled images to develop and benchmark wheat head detection methods,\u201d arXiv preprint arXiv:2005.02162, 2020.","DOI":"10.34133\/2020\/3521852"},{"key":"15","unstructured":"[15] T. Xiao, T. Xia, Y. Yang, C. Huang, and X. Wang, \u201cLearning from massive noisy labeled data for image classification,\u201d CVPR, pp.2691-2699, 2015. 10.1109\/CVPR.2015.7298885"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] Y. He, C. Zhu, J. Wang, M. Savvides, and X. Zhang, \u201cBounding box regression with uncertainty for accurate object detection,\u201d CVPR, pp.2888-2897, 2019. 10.1109\/CVPR.2019.00300","DOI":"10.1109\/CVPR.2019.00300"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] P. Tang, X. Wang, X. Bai, and W. Liu, \u201cMultiple instance detection network with online instance classifier refinement,\u201d CVPR, pp.2843-2851, 2017. 10.1109\/CVPR.2017.326","DOI":"10.1109\/CVPR.2017.326"},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] I. Misra, A. Shrivastava, and M. Hebert, \u201cWatch and learn: Semi-supervised learning of object detectors from videos,\u201d Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp.3593-3602, 2015. 10.1109\/CVPR.2015.7298982","DOI":"10.1109\/CVPR.2015.7298982"},{"key":"19","doi-asserted-by":"publisher","unstructured":"[19] M. Everingham, L. Van Gool, C.K.I. Williams, J. Winn, and A. Zisserman, \u201cThe pascal visual object classes (voc) challenge,\u201d IJCV, vol.88, no.2, pp.303-338, 2010. 10.1007\/s11263-009-0275-4","DOI":"10.1007\/s11263-009-0275-4"},{"key":"20","doi-asserted-by":"crossref","unstructured":"[20] S. Zhang, L. Wen, X. Bian, Z. Lei, and S.Z. Li, \u201cSingle-shot refinement neural network for object detection,\u201d CVPR, 2018. 10.1109\/CVPR.2018.00442","DOI":"10.1109\/CVPR.2018.00442"},{"key":"21","unstructured":"[21] D. Arpit, S. Jastrz\u0119bski, N. Ballas, D. Krueger, E. Bengio, M.S. Kanwal, T. Maharaj, A. Fischer, A. Courville, Y. Bengio, and S. Lacoste-Julien, \u201cA closer look at memorization in deep networks,\u201d ICML, pp.233-242, 2017."},{"key":"22","unstructured":"[22] I.J. Goodfellow, J. Shlens, and C. Szegedy, \u201cExplaining and harnessing adversarial examples,\u201d arXiv preprint arXiv:1412.6572, 2014."},{"key":"23","unstructured":"[23] A. Vahdat, \u201cToward robustness against label noise in training deep discriminative neural networks,\u201d NeurIPS, pp.5596-5605, 2017."},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] G. Patrini, A. Rozza, A. Krishna Menon, R. Nock, and L. Qu, \u201cMaking deep neural networks robust to label noise: A loss correction approach,\u201d CVPR, pp.1944-1952, 2017. 10.1109\/CVPR.2017.240","DOI":"10.1109\/CVPR.2017.240"},{"key":"25","unstructured":"[25] S. Sukhbaatar, J.B. Estrach, M. Paluri, L. Bourdev, and R. Fergus, \u201cTraining convolutional networks with noisy labels,\u201d ICLR, 2015."},{"key":"26","unstructured":"[26] H. Zhang, M. Cisse, Y.N. Dauphin, and D. Lopez-Paz, \u201cmixup: Beyond empirical risk minimization,\u201d arXiv preprint arXiv:1710.09412, 2017."},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] D. Tanaka, D. Ikami, T. Yamasaki, and K. Aizawa, \u201cJoint optimization framework for learning with noisy labels,\u201d CVPR, pp.5552-5560, 2018. 10.1109\/CVPR.2018.00582","DOI":"10.1109\/CVPR.2018.00582"},{"key":"28","doi-asserted-by":"crossref","unstructured":"[28] S. Chadwick and P. Newman, \u201cTraining object detectors with noisy data,\u201d 2019 IEEE Intelligent Vehicles Symposium (IV), pp.1319-1325, 2019. 10.1109\/IVS.2019.8814137","DOI":"10.1109\/IVS.2019.8814137"},{"key":"29","doi-asserted-by":"crossref","unstructured":"[29] K. He, X. Zhang, S. Ren, and J. Sun, \u201cDeep residual learning for image recognition,\u201d Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp.770-778, 2016. 10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E104.D\/9\/E104.D_2021EDP7026\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,4]],"date-time":"2021-09-04T03:57:10Z","timestamp":1630727830000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E104.D\/9\/E104.D_2021EDP7026\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,1]]},"references-count":29,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2021]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2021edp7026","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,1]]},"article-number":"2021EDP7026"}}