{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T04:31:10Z","timestamp":1722659470346},"reference-count":38,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Fundamentals"],"published-print":{"date-parts":[[2020,1,1]]},"DOI":"10.1587\/transfun.2019tsp0001","type":"journal-article","created":{"date-parts":[[2019,12,31]],"date-time":"2019-12-31T22:06:20Z","timestamp":1577829980000},"page":"231-242","source":"Crossref","is-referenced-by-count":6,"title":["Attribute-Aware Loss Function for Accurate Semantic Segmentation Considering the Pedestrian Orientations"],"prefix":"10.1587","volume":"E103.A","author":[{"given":"Mahmud Dwi","family":"SULISTIYO","sequence":"first","affiliation":[{"name":"Graduate School of Informatics, Nagoya University"},{"name":"School of Computing, Telkom University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yasutomo","family":"KAWANISHI","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Nagoya University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daisuke","family":"DEGUCHI","sequence":"additional","affiliation":[{"name":"Information Strategy Office, Nagoya University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ichiro","family":"IDE","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Nagoya University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takatsugu","family":"HIRAYAMA","sequence":"additional","affiliation":[{"name":"Institutes of Innovation for Future Society, Nagoya University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiang-Yu","family":"ZHENG","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Indiana University-Purdue University Indianapolis"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroshi","family":"MURASE","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Nagoya University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"publisher","unstructured":"[1] V. Badrinarayanan, A. Kendall, and R. Cipolla, \u201cSegNet: A deep convolutional encoder-decoder architecture for image segmentation,\u201d IEEE Trans. Pattern Anal. Mach. Intell., vol.39, no.12, pp.2481-2495, Dec. 2017. 10.1109\/tpami.2016.2644615","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"2","unstructured":"[2] A. Van Etten, D. Lindenbaum, and T.M. Bacastow, \u201cSpaceNet: A remote sensing dataset and challenge series,\u201d Computing Research Repository arXiv preprint, arXiv:1807.01232, July 2018."},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] O. Ronneberger, P. Fischer, and T. Brox, \u201cU-Net: Convolutional networks for biomedical image segmentation,\u201d Proc. 18th Int. Conf. on Medical Image Computing and Computer-Assisted Intervention, pp.234-241, Oct. 2015. 10.1007\/978-3-319-24574-4_28","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"4","unstructured":"[4] H.R. Roth, C. Shen, H. Oda, M. Oda, Y. Hayashi, K. Misawa, and K. Mori, \u201cDeep learning and its application to medical image segmentation,\u201d Med. Imag. Tech., vol.36, no.2, pp.63-71, March 2018."},{"key":"5","doi-asserted-by":"publisher","unstructured":"[5] K. Khan, N. Ahmad, K. Ullah, and I. Din, \u201cMulticlass semantic segmentation of faces using CRFs,\u201d Turk. J. Electr. Eng. Co., vol.25, no.4, pp.3164-3174, July 2017. 10.3906\/elk-1607-332","DOI":"10.3906\/elk-1607-332"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] B.J. Meyer and T. Drummond, \u201cImproved semantic segmentation for robotic applications with hierarchical conditional random fields,\u201d Proc. 2017 IEEE Int. Conf. on Robotics and Automation, pp.5258-5265, May 2017. 10.1109\/icra.2017.7989617","DOI":"10.1109\/ICRA.2017.7989617"},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] M. Elhoseiny, S. Huang, and A. Elgammal, \u201cWeather classification with deep convolutional neural networks,\u201d Proc. 2015 IEEE Int. Conf. on Image Processing, pp.3349-3353, Sept. 2015. 10.1109\/icip.2015.7351424","DOI":"10.1109\/ICIP.2015.7351424"},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] T. Wu and A. Ranganathan, \u201cVehicle localization using road markings,\u201d Proc. 2013 IEEE Intelligent Vehicles Symposium, pp.1185-1190, June 2013. 10.1109\/ivs.2013.6629627","DOI":"10.1109\/IVS.2013.6629627"},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] D. Wong, D. Deguchi, I. Ide, and H. Murase, \u201cVision-based vehicle localization using a visual street map with embedded SURF scale,\u201d Proc. European Conf. on Computer Vision 2014 Workshops, pp.167-179, Sept. 2014. 10.1007\/978-3-319-16178-5_11","DOI":"10.1007\/978-3-319-16178-5_11"},{"key":"10","doi-asserted-by":"publisher","unstructured":"[10] X. Liu and Z. Deng, \u201cSegmentation of drivable road using deep fully convolutional residual network with pyramid pooling,\u201d Cogn. Comput., vol.10, no.2, pp.272-281, April 2018. 10.1007\/s12559-017-9524-y","DOI":"10.1007\/s12559-017-9524-y"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] F. Shinmura, Y. Kawanishi, D. Deguchi, T. Hirayama, I. Ide, H. Murase, and H. Fujiyoshi, \u201cEstimation of driver's insight for safe passing based on pedestrian attributes,\u201d Proc. 21st IEEE Int. Conf. on Intelligent Transportation Systems, pp.1041-1046, Nov. 2018. 10.1109\/itsc.2018.8569955","DOI":"10.1109\/ITSC.2018.8569955"},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] J. Long, E. Shelhamer, and T. Darrell, \u201cFully convolutional networks for semantic segmentation,\u201d Proc. 2015 IEEE Conf. on Computer Vision and Pattern Recognition, pp.3431-3440, June 2015. 10.1109\/cvpr.2015.7298965","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"13","unstructured":"[13] A. Kendall, V. Badrinarayanan, and R. Cipolla, \u201cBayesian SegNet: Model uncertainty in deep convolutional encoder-decoder architectures for scene understanding,\u201d Computing Research Repository arXiv preprint, arXiv:1511.02680, Nov. 2015."},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] H. Zhao, J. Shi, X. Qi, X. Wang, and J. Jia, \u201cPyramid scene parsing network,\u201d Proc. 2017 IEEE Conf. on Computer Vision and Pattern Recognition, pp.2881-2890, June 2017. 10.1109\/cvpr.2017.660","DOI":"10.1109\/CVPR.2017.660"},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] K. He, G. Gkioxari, P. Doll\u00e1r, and R. Girshick, \u201cMask R-CNN,\u201d Proc. 2017 IEEE Int. Conf. on Computer Vision, pp.2961-2969, Sept. 2017. 10.1109\/iccv.2017.322","DOI":"10.1109\/ICCV.2017.322"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] H. Zhao, X. Qi, X. Shen, J. Shi, and J. Jia, \u201cICNet for real-time semantic segmentation on high-resolution images,\u201d Proc. European Conf. on Computer Vision 2018, pp.405-420, Sept. 2018. 10.1007\/978-3-030-01219-9_25","DOI":"10.1007\/978-3-030-01219-9_25"},{"key":"17","doi-asserted-by":"publisher","unstructured":"[17] L.C. Chen, G. Papandreou, I. Kokkinos, K. Murphy, and A.L. Yuille, \u201cDeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs,\u201d IEEE Trans. Pattern Anal. Mach. Intell., vol.40, no.4, pp.834-848, April 2018. 10.1109\/tpami.2017.2699184","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"18","unstructured":"[18] L.C. Chen, G. Papandreou, F. Schroff, and H. Adam, \u201cRethinking atrous convolution for semantic image segmentation,\u201d Computing Research Repository arXiv preprint, arXiv:1706.05587, June 2017."},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] L.C. Chen, Y. Zhu, G. Papandreou, F. Schroff, and H. Adam, \u201cEncoder-decoder with atrous separable convolution for semantic image segmentation,\u201d Proc. European Conf. on Computer Vision 2018, pp.801-818, Sept. 2018. 10.1007\/978-3-030-01234-2_49","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"20","doi-asserted-by":"publisher","unstructured":"[20] G.J. Brostow, J. Fauqueur, and R. Cipolla, \u201cSemantic object classes in video: A high-definition ground truth database,\u201d Pattern Recogn. Lett., vol.30, no.2, pp.88-97, Jan. 2009. 10.1016\/j.patrec.2008.04.005","DOI":"10.1016\/j.patrec.2008.04.005"},{"key":"21","doi-asserted-by":"publisher","unstructured":"[21] A. Geiger, P. Lenz, C. Stiller, and R. Urtasun, \u201cVision meets robotics: The KITTI dataset,\u201d Int. J. Robo. Res., vol.32, no.11, pp.1231-1237, Sept. 2013. 10.1177\/0278364913491297","DOI":"10.1177\/0278364913491297"},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] M. Cordts, M. Omran, S. Ramos, T. Rehfeld, M. Enzweiler, R. Benenson, U. Franke, S. Roth, and B. Schiele, \u201cThe Cityscapes dataset for semantic urban scene understanding,\u201d Proc. 2016 IEEE Conf. on Computer Vision and Pattern Recognition, pp.3213-3223, June 2016. 10.1109\/cvpr.2016.350","DOI":"10.1109\/CVPR.2016.350"},{"key":"23","unstructured":"[23] M.D. Sulistiyo, Y. Kawanishi, D. Deguchi, I. Ide, and H. Murase, \u201cA preliminary study of attribute-aware semantic segmentation for pedestrian understanding,\u201d Proc. 2017 Electric\/Electronic\/Information Engineering Related Society Tokai Sectors Joint Convention, no.A2-7, Sept. 2017."},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] M.D. Sulistiyo, Y. Kawanishi, D. Deguchi, T. Hirayama, I. Ide, J.Y. Zheng, and H. Murase, \u201cAttribute-aware semantic segmentation of road scenes for understanding pedestrian orientations,\u201d Proc. 21st IEEE Int. Conf. on Intelligent Transportation Systems, pp.2698-2703, Nov. 2018. 10.1109\/itsc.2018.8569372","DOI":"10.1109\/ITSC.2018.8569372"},{"key":"25","unstructured":"[25] X. Liu, Z. Deng, and Y. Yang, \u201cRecent progress in semantic image segmentation,\u201d Computing Research Repository arXiv preprint, arXiv:1809.10198, Sept. 2018."},{"key":"26","unstructured":"[26] M. Cordts, M. Omran, S. Ramos, T. Scharw\u00e4chter, M. Enzweiler, R. Benenson, U. Franke, S. Roth, and B. Schiele, \u201cThe Cityscapes dataset,\u201d CVPR 2015 Workshop on the Future of Datasets in Vision, June 2015."},{"key":"27","unstructured":"[27] K. Simonyan and A. Zisserman, \u201cVery deep convolutional networks for large-scale image recognition,\u201d Computing Research Repository arXiv preprint, arXiv:1409.1556, Sept. 2014."},{"key":"28","doi-asserted-by":"crossref","unstructured":"[28] K. He, X. Zhang, S. Ren, and J. Sun, \u201cDeep residual learning for image recognition,\u201d Proc. 2016 IEEE Conf. on Computer Vision and Pattern Recognition, pp.770-778, June 2016. 10.1109\/cvpr.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"29","doi-asserted-by":"publisher","unstructured":"[29] M. Everingham, L. Van Gool, C.K. Williams, J. Winn, and A. Zisserman, \u201cThe Pascal visual object classes (VOC) challenge,\u201d Int. J. Comput. Vis., vol.88, no.2, pp.303-338, June 2010. 10.1007\/s11263-009-0275-4","DOI":"10.1007\/s11263-009-0275-4"},{"key":"30","unstructured":"[30] S. Ren, K. He, R. Girshick, and J. Sun, \u201cFaster R-CNN: Towards real-time object detection with region proposal networks,\u201d Proc. 28th Int. Conf. on Neural Information Processing Systems, pp.91-99, Dec. 2015."},{"key":"31","doi-asserted-by":"publisher","unstructured":"[31] Y. Zhang and Q. Yang, \u201cAn overview of multi-task learning,\u201d Natl. Sci. Rev., vol.5, no.1, pp.30-43, Sept. 2017. 10.1093\/nsr\/nwx105","DOI":"10.1093\/nsr\/nwx105"},{"key":"32","unstructured":"[32] S. Ruder, \u201cAn overview of multi-task learning in deep neural networks,\u201d Computing Research Repository arXiv preprint, arXiv:1706.05098, June 2017."},{"key":"33","doi-asserted-by":"crossref","unstructured":"[33] Y. Lu, D. Allegra, M. Anthimopoulos, F. Stanco, G.M. Farinella, and S. Mougiakakou, \u201cA multi-task learning approach for meal assessment,\u201d Proc. 2018 Joint Workshop on Multimedia for Cooking and Eating Activities and Multimedia Assisted Dietary Management, pp.46-52, July 2018. 10.1145\/3230519.3230593","DOI":"10.1145\/3230519.3230593"},{"key":"34","doi-asserted-by":"crossref","unstructured":"[34] D.C. Luvizon, D. Picard, and H. Tabia, \u201c2D\/3D pose estimation and action recognition using multitask deep learning,\u201d Proc. 2018 IEEE Conf. on Computer Vision and Pattern Recognition, pp.5137-5146, June 2018. 10.1109\/cvpr.2018.00539","DOI":"10.1109\/CVPR.2018.00539"},{"key":"35","unstructured":"[35] Z. Deng, \u201cPyTorch for semantic segmentation,\u201d https:\/\/github.com\/zijundeng\/pytorch-semantic-segmentation\/, 2017."},{"key":"36","doi-asserted-by":"crossref","unstructured":"[36] M. Enzweiler and D.M. Gavrila, \u201cIntegrated pedestrian classification and orientation estimation,\u201d Proc. 2010 IEEE Conf. on Computer Vision and Pattern Recognition, pp.982-989, June 2010. 10.1109\/cvpr.2010.5540110","DOI":"10.1109\/CVPR.2010.5540110"},{"key":"37","doi-asserted-by":"crossref","unstructured":"[37] S. Zhang, R. Benenson, and B. Schiele, \u201cCityPersons: A diverse dataset for pedestrian detection,\u201d Proc. 2017 IEEE Conf. on Computer Vision and Pattern Recognition, pp.3213-3221, July 2017. 10.1109\/cvpr.2017.474","DOI":"10.1109\/CVPR.2017.474"},{"key":"38","doi-asserted-by":"crossref","unstructured":"[38] A. Podili, C. Zhang, and V. Prasanna, \u201cFast and efficient implementation of convolutional neural networks on FPGA,\u201d Proc. 28th IEEE Int. Conf. on Application-specific Systems, Architectures and Processors, pp.11-18, July 2017. 10.1109\/asap.2017.7995253","DOI":"10.1109\/ASAP.2017.7995253"}],"container-title":["IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transfun\/E103.A\/1\/E103.A_2019TSP0001\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,1,6]],"date-time":"2020-01-06T05:26:01Z","timestamp":1578288361000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transfun\/E103.A\/1\/E103.A_2019TSP0001\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1,1]]},"references-count":38,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020]]}},"URL":"https:\/\/doi.org\/10.1587\/transfun.2019tsp0001","relation":{},"ISSN":["0916-8508","1745-1337"],"issn-type":[{"value":"0916-8508","type":"print"},{"value":"1745-1337","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,1,1]]}}}