{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T06:12:50Z","timestamp":1759385570332},"reference-count":38,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2022,2,1]]},"DOI":"10.1587\/transinf.2021edp7117","type":"journal-article","created":{"date-parts":[[2022,1,31]],"date-time":"2022-01-31T22:17:02Z","timestamp":1643667422000},"page":"415-426","source":"Crossref","is-referenced-by-count":2,"title":["Gender Recognition Using a Gaze-Guided Self-Attention Mechanism Robust Against Background Bias in Training Samples"],"prefix":"10.1587","volume":"E105.D","author":[{"given":"Masashi","family":"NISHIYAMA","sequence":"first","affiliation":[{"name":"Graduate School of Engineering, Tottori University"}]},{"given":"Michiko","family":"INOUE","sequence":"additional","affiliation":[{"name":"Graduate School of Engineering, Tottori University"}]},{"given":"Yoshio","family":"IWAI","sequence":"additional","affiliation":[{"name":"Graduate School of Engineering, Tottori University"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] C.B. Ng, Y.H. Tay, and B.-M. Goi, \u201cRecognizing human gender in computer vision: a survey,\u201d Proceedings of the Pacific Rim International Conference on Artificial Intelligence, pp.335-346, 2012. 10.1007\/978-3-642-32695-0_31","DOI":"10.1007\/978-3-642-32695-0_31"},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] S.A. Khan, M. Nazir, S. Akram, and N. Riaz, \u201cGender classification using image processing techniques: A survey,\u201d Proceedings of the IEEE 14th International Multitopic Conference, pp.25-30, 2011. 10.1109\/inmic.2011.6151483","DOI":"10.1109\/INMIC.2011.6151483"},{"key":"3","doi-asserted-by":"publisher","unstructured":"[3] M. Fayyaz, M. Yasmin, M. Sharif, and M. Raza, \u201cJ-ldfr: joint low-level and deep neural network feature representations for pedestrian gender classification,\u201d Neural Computing and Applications, pp.1-31, 2020. 10.1007\/s00521-020-05015-1","DOI":"10.1007\/s00521-020-05015-1"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] C. Tang, L. Sheng, Z.-X. Zhang, and X. Hu, \u201cImproving pedestrian attribute recognition with weakly-supervised multi-scale attribute-specific localization,\u201d Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp.4996-5005, 2019. 10.1109\/iccv.2019.00510","DOI":"10.1109\/ICCV.2019.00510"},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] H. Zeng, H. Ai, Z. Zhuang, and L. Chen, \u201cMulti-task learning via co-attentive sharing for pedestrian attribute recognition,\u201d Proceedings of the IEEE International Conference on Multimedia and Expo, pp.1-6, 2020. 10.1109\/icme46284.2020.9102757","DOI":"10.1109\/ICME46284.2020.9102757"},{"key":"6","unstructured":"[6] K. Xiao, L. Engstrom, A. Ilyas, and A. Madry, \u201cNoise or signal: The role of image backgrounds in object recognition,\u201d CoRR, abs\/2006.09994, 2020."},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] Y. Yu, J. Choi, Y. Kim, K. Yoo, S. Lee, and G. Kim, \u201cSupervising neural attention models for video captioning by human gaze data,\u201d Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.6119-6127, 2017. 10.1109\/cvpr.2017.648","DOI":"10.1109\/CVPR.2017.648"},{"key":"8","unstructured":"[8] T. Qiao, J. Dong, and D. Xu, \u201cExploring human-like attention supervision in visual question answering,\u201d Proceedings of the 32nd AAAI Conference on Artificial Intelligence, pp.7300-7307, 2018."},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] J. Wu, S.-H. Zhong, Z. Ma, S.J. Heinen, and J. Jiang, \u201cGaze aware deep learning model for video summarization,\u201d Proceedings of the Pacific Rim Conference on Multimedia, vol.11165, pp.285-295, 2018. 10.1007\/978-3-030-00767-6_27","DOI":"10.1007\/978-3-030-00767-6_27"},{"key":"10","doi-asserted-by":"publisher","unstructured":"[10] Y. Xia, Z. Liu, Y. Yan, Y. Chen, L. Zhang, and R. Zimmermann,\u201cMedia quality assessment by perceptual gaze-shift patterns discovery,\u201d IEEE Transactions on Multimedia, vol.19, no.8, pp.1811-1820, 2017. 10.1109\/tmm.2017.2679900","DOI":"10.1109\/TMM.2017.2679900"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] N. Murrugarra-Llerena and A. Kovashka, \u201cLearning attributes from human gaze,\u201d Proceedings of the IEEE Winter Conference on Applications of Computer Vision, pp.510-519, 2017. 10.1109\/wacv.2017.63","DOI":"10.1109\/WACV.2017.63"},{"key":"12","doi-asserted-by":"publisher","unstructured":"[12] M. Nishiyama, R. Matsumoto, H. Yoshimura, and Y. Iwai, \u201cExtracting discriminative features using task-oriented gaze maps measured from observers for personal attribute classification,\u201d Pattern Recognition Letters, vol.112, pp.241-248, 2018. 10.1016\/j.patrec.2018.08.001","DOI":"10.1016\/j.patrec.2018.08.001"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] H. Sattar, A. Bulling, and M. Fritz, \u201cPredicting the category and attributes of visual search targets using deep gaze pooling,\u201d Proceedings of the IEEE International Conference on Computer Vision Workshops, pp.2740-2748, 2017. 10.1109\/iccvw.2017.322","DOI":"10.1109\/ICCVW.2017.322"},{"key":"14","unstructured":"[14] H. Zhang, I. Goodfellow, D. Metaxas, and A. Odena, \u201cSelf-attention generative adversarial networks,\u201d CoRR, abs\/1805.08318, 2018."},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] S. Woo, J. Park, J.-Y. Lee, and I.S. Kweon, \u201cCbam: Convolutional block attention module,\u201d Proceedings of the European Conference on Computer Vision, vol.11211, pp.3-19, 2018. 10.1007\/978-3-030-01234-2_1","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] S. Zhuoran, Z. Mingyuan, Z. Haiyu, Y. Shuai, and L. Hongsheng, \u201cEfficient attention: Attention with linear complexities,\u201d Proceedings of the Winter Conference on Applications of Computer Vision, 2021. 10.1109\/wacv48630.2021.00357","DOI":"10.1109\/WACV48630.2021.00357"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] F. Wang, M. Jiang, C. Qian, S. Yang, C. Li, H. Zhang, X. Wang, and X. Tang, \u201cResidual attention network for image classification,\u201d Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.6450-6458, 2017. 10.1109\/cvpr.2017.683","DOI":"10.1109\/CVPR.2017.683"},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] X. Wang, R. Girshick, A. Gupta, and K. He, \u201cNon-local neural networks,\u201d Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp.7794-7803, 2018. 10.1109\/cvpr.2018.00813","DOI":"10.1109\/CVPR.2018.00813"},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] J. Hu, L. Shen, and G. Sun, \u201cSqueeze-and-excitation networks,\u201d Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp.7132-7141, 2018. 10.1109\/cvpr.2018.00745","DOI":"10.1109\/CVPR.2018.00745"},{"key":"20","doi-asserted-by":"crossref","unstructured":"[20] C. Song, Y. Huang, W. Ouyang, and L. Wang, \u201cMask-guided contrastive attention model for person re-identification,\u201d Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp.1179-1188, 2018. 10.1109\/cvpr.2018.00129","DOI":"10.1109\/CVPR.2018.00129"},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] J. Yang, J. Fan, Y. Wang, Y. Wang, W. Gan, L. Liu, and W. Wu, \u201cHierarchical feature embedding for attribute recognition,\u201d Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp.13052-13061, 2020. 10.1109\/cvpr42600.2020.01307","DOI":"10.1109\/CVPR42600.2020.01307"},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] K. Han, J. Guo, C. Zhang, and M. Zhu, \u201cAttribute-aware attention model for fine-grained representation learning,\u201d Proceedings of the 26th ACM International Conference on Multimedia, p.2040-2048, 2018. 10.1145\/3240508.3240550","DOI":"10.1145\/3240508.3240550"},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] Z. Yang, L. Huang, Y. Chen, Z. Wei, S. Ahn, G. Zelinsky, D. Samaras, and M. Hoai, \u201cPredicting goal-directed human attention using inverse reinforcement learning,\u201d Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.193-202, 2020. 10.1109\/cvpr42600.2020.00027","DOI":"10.1109\/CVPR42600.2020.00027"},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] J. Xu, L. Mukherjee, Y. Li, J. Warner, J.M. Rehg, and V. Singh, \u201cGaze-enabled egocentric video summarization via constrained submodular maximization,\u201d Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.2235-2244, 2015. 10.1109\/cvpr.2015.7298836","DOI":"10.1109\/CVPR.2015.7298836"},{"key":"25","doi-asserted-by":"publisher","unstructured":"[25] Y. Sugano, Y. Ozaki, H. Kasai, K. Ogaki, and Y. Sato, \u201cImage preference estimation with a data-driven approach: A comparative study between gaze and image features,\u201d Eye Movement Research, vol.7, no.3, pp.862-875, 2014. 10.16910\/jemr.7.3.5","DOI":"10.16910\/jemr.7.3.5"},{"key":"26","doi-asserted-by":"crossref","unstructured":"[26] N. Karessli, Z. Akata, B. Schiele, and A. Bulling, \u201cGaze embeddings for zero-shot image classification,\u201d Proceedings of the IEEE conference on computer vision and pattern recognition, pp.4525-4534, 2017. 10.1109\/cvpr.2017.679","DOI":"10.1109\/CVPR.2017.679"},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] K. He, G. Gkioxari, P. Dollar, and R. Girshick, \u201cMask r-cnn,\u201d Proceedings of the IEEE International Conference on Computer Vision, pp.2980-2988, 2017. 10.1109\/iccv.2017.322","DOI":"10.1109\/ICCV.2017.322"},{"key":"28","doi-asserted-by":"crossref","unstructured":"[28] D. Novotny, S. Albanie, D. Larlus, and A. Vedaldi, \u201cSemi-convolutional operators for instance segmentation,\u201d Proceedings of the European Conference on Computer Vision, vol.11205, pp.89-105, 2018. 10.1007\/978-3-030-01246-5_6","DOI":"10.1007\/978-3-030-01246-5_6"},{"key":"29","doi-asserted-by":"publisher","unstructured":"[29] V. Badrinarayanan, A. Kendall, and R. Cipolla, \u201cSegnet: A deep convolutional encoder-decoder architecture for image segmentation,\u201d IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.39, no.12, pp.2481-2495, 2017. 10.1109\/tpami.2016.2644615","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"30","doi-asserted-by":"publisher","unstructured":"[30] S.K. Choudhury, P.K. Sa, S. Bakshi, and B. Majhi, \u201cAn evaluation of background subtraction for object detection vis-a-vis mitigating challenging scenarios,\u201d IEEE Access, vol.4, pp.6133-6150, 2016. 10.1109\/access.2016.2608847","DOI":"10.1109\/ACCESS.2016.2608847"},{"key":"31","doi-asserted-by":"crossref","unstructured":"[31] I. Setitra and S. Larabi, \u201cBackground subtraction algorithms with post-processing: A review,\u201d Proceedings of the 22nd International Conference on Pattern Recognition, pp.2436-2441, 2014. 10.1109\/icpr.2014.421","DOI":"10.1109\/ICPR.2014.421"},{"key":"32","doi-asserted-by":"publisher","unstructured":"[32] M. Babaee, D.T. Dinh, and G. Rigoll, \u201cA deep convolutional neural network for video sequence background subtraction,\u201d Pattern Recognition, vol.76, pp.635-649, 2018. 10.1016\/j.patcog.2017.09.040","DOI":"10.1016\/j.patcog.2017.09.040"},{"key":"33","doi-asserted-by":"crossref","unstructured":"[33] Y. Deng, P. Luo, C.C. Loy, and X. Tang, \u201cPedestrian attribute recognition at far distance,\u201d ACM, pp.789-792, 2014. 10.1145\/2647868.2654966","DOI":"10.1145\/2647868.2654966"},{"key":"34","doi-asserted-by":"publisher","unstructured":"[34] M. Bindemann, \u201cScene and screen center bias early eye movements in scene viewing,\u201d Vision Research, vol.50, no.23, pp.2577-2587, 2010. 10.1016\/j.visres.2010.08.016","DOI":"10.1016\/j.visres.2010.08.016"},{"key":"35","doi-asserted-by":"crossref","unstructured":"[35] G. Antipov, S.-A. Berrani, N. Ruchaud, and J.-L. Dugelay, \u201cLearned vs. hand-crafted features for pedestrian gender recognition,\u201d Proceedings of the 23rd ACM International Conference on Multimedia, pp.1263-1266, 2015. 10.1145\/2733373.2806332","DOI":"10.1145\/2733373.2806332"},{"key":"36","unstructured":"[36] J. Jia, H. Huang, W. Yang, X. Chen, and K. Huang, \u201cRethinking of pedestrian attribute recognition: Realistic datasets with efficient method,\u201d CoRR, abs\/2005.11909, 2020."},{"key":"37","unstructured":"[37] D. Li, Z. Zhang, X. Chen, H. Ling, and K. Huang, \u201cA richly annotated dataset for pedestrian attribute recognition,\u201d CoRR, abs\/1603.07054, 2016."},{"key":"38","doi-asserted-by":"crossref","unstructured":"[38] H. Zhao, J. Jia, and V. Koltun, \u201cExploring self-attention for image recognition,\u201d Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp.10073-10082, 2020. 10.1109\/cvpr42600.2020.01009","DOI":"10.1109\/CVPR42600.2020.01009"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E105.D\/2\/E105.D_2021EDP7117\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,5]],"date-time":"2022-02-05T03:50:35Z","timestamp":1644033035000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E105.D\/2\/E105.D_2021EDP7117\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,1]]},"references-count":38,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2021edp7117","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,1]]},"article-number":"2021EDP7117"}}