{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T12:33:40Z","timestamp":1774528420647,"version":"3.50.1"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2022,1,7]],"date-time":"2022-01-07T00:00:00Z","timestamp":1641513600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,7]],"date-time":"2022-01-07T00:00:00Z","timestamp":1641513600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach. Intell. Res."],"published-print":{"date-parts":[[2022,4]]},"DOI":"10.1007\/s11633-022-1321-8","type":"journal-article","created":{"date-parts":[[2022,1,8]],"date-time":"2022-01-08T17:02:21Z","timestamp":1641661341000},"page":"153-168","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Pedestrian Attribute Recognition in Video Surveillance Scenarios Based on View-attribute Attention Localization"],"prefix":"10.1007","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7036-9098","authenticated-orcid":false,"given":"Wei-Chen","family":"Chen","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8716-7687","authenticated-orcid":false,"given":"Xin-Yi","family":"Yu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6916-974X","authenticated-orcid":false,"given":"Lin-Lin","family":"Ou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,1,7]]},"reference":[{"key":"1321_CR1","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1109\/ICCVW.2015.51","volume-title":"Person attribute recognition with a jointly-trained holistic CNN model","author":"P Sudowe","year":"2015","unstructured":"P. Sudowe, H. Spitzer, B. Leibe. Person attribute recognition with a jointly-trained holistic CNN model. In Proceedings of IEEE International Conference on Computer Vision Workshop, IEEE, Santiago, Chile, pp. 329\u2013377, 2015. DOI: https:\/\/doi.org\/10.1109\/ICCVW.2015.51."},{"key":"1321_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ICME.2018.8486604","volume-title":"Pose guided deep model for pedestrian attribute recognition in surveillance scenarios","author":"D W Li","year":"2018","unstructured":"D. W. Li, X. T. Chen, Z. Zhang, K. Q. Huang. Pose guided deep model for pedestrian attribute recognition in surveillance scenarios. In Proceedings of IEEE International Conference on Multimedia and Expo, IEEE, San Diego, USA, pp. 1\u20136, 2018. DOI: https:\/\/doi.org\/10.1109\/ICME.2018.8486604."},{"key":"1321_CR3","doi-asserted-by":"publisher","first-page":"1543","DOI":"10.1109\/ICCV.2011.6126413","volume-title":"Describing people: A poselet-based approach to attribute classification","author":"L Bourdev","year":"2011","unstructured":"L. Bourdev, S. Maji, J. Malik. Describing people: A poselet-based approach to attribute classification. In Proceedings of International Conference on Computer Vision, IEEE, Barcelona, Spain, pp. 1543\u20131550, 2011. DOI: https:\/\/doi.org\/10.1109\/ICCV.2011.6126413."},{"key":"1321_CR4","unstructured":"P. Z. Liu, X. H. Liu, J. J. Yan, J. Shao. Localization guided learning for pedestrian attribute recognition, [Online], Available: https:\/\/arxiv.org\/abs\/1808.09102, 2018."},{"issue":"4","key":"1321_CR5","doi-asserted-by":"publisher","first-page":"1575","DOI":"10.1109\/TIP.2018.2878349","volume":"28","author":"D W Li","year":"1919","unstructured":"D. W. Li, Z. Zhang, X. T. Chen, K. Q. Huang. A richly annotated pedestrian dataset for person retrieval in real surveillance scenarios. IEEE Transactions on Image Processing, vol. 28, no. 4, pp. 1575\u20131590, 1919. DOI: https:\/\/doi.org\/10.1109\/TIP.2018.2878349.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1321_CR6","doi-asserted-by":"publisher","first-page":"708","DOI":"10.1007\/978-3-030-01252-6_42","volume-title":"Deep imbalanced attribute classification using visual attention aggregation","author":"N Sarafianos","year":"2018","unstructured":"N. Sarafianos, X. Xu, I. A. Kakadiaris. Deep imbalanced attribute classification using visual attention aggregation. In Proceedings of the 15th European Conference on Computer Vision, Springer, Munich, Germany, pp. 708\u2013725, 2018. DOI: https:\/\/doi.org\/10.1007\/978-3-030-01252-6_42."},{"key":"1321_CR7","doi-asserted-by":"publisher","unstructured":"E. Yaghoubi, D. Borza, J. Neves, A. Kumar, H. Proen\u00e7a. An attention-based deep learning model for multiple pedestrian attributes recognition. Image and Vision Computing, vol. 102, Article number 103981, 2020. DOI: https:\/\/doi.org\/10.1016\/j.imavis.2020.103981.","DOI":"10.1016\/j.imavis.2020.103981"},{"issue":"7","key":"1321_CR8","doi-asserted-by":"publisher","first-page":"12394","DOI":"10.1609\/aaai.v34i07.6925","volume":"34","author":"M D Wu","year":"2020","unstructured":"M. D. Wu, D. Huang, Y. F. Guo, Y. H. Wang. Distraction-aware feature learning for human attribute recognition via coarse-to-fine attention mechanism. In Proceedings of AAAI Conference on Artificial Intelligence, vol.34, no.7, pp. 12394\u201312401, 2020. DOI: https:\/\/doi.org\/10.1609\/aaai.v34i07.6925.","journal-title":"Proceedings of AAAI Conference on Artificial Intelligence"},{"key":"1321_CR9","doi-asserted-by":"publisher","first-page":"7132","DOI":"10.1102\/CVPR.2018.00745","volume-title":"Squeeze-and-excitation networks","author":"J Hu","year":"2018","unstructured":"J. Hu, L. Shen, G. Sun. Squeeze-and-excitation networks. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Salt Lake City, USA, pp. 7132\u20137141, 2018. DOI: https:\/\/doi.org\/10.1102\/CVPR.2018.00745."},{"key":"1321_CR10","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01234-2_1","volume-title":"CBAM: Convolutional block attention module","author":"S Woo","year":"2018","unstructured":"S. Woo, J. Park, J. Y. Lee, I. S. Kweon. CBAM: Convolutional block attention module. In Proceedings of the 15th European Conference on Computer Vision, Springer, Munich, Germany, pp. 3\u201319, 2018. DOI: https:\/\/doi.org\/10.1007\/978-3-030-01234-2_1."},{"key":"1321_CR11","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1109\/CVPR.2016.90","volume-title":"Deep residual learning for image recognition","author":"K M He","year":"2016","unstructured":"K. M. He, X. Y. Zhang, S. Q. Ren, J. Sun. Deep residual learning for image recognition. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Las Vegas, USA, pp. 770\u2013778, 2016. DOI: https:\/\/doi.org\/10.1109\/CVPR.2016.90."},{"key":"1321_CR12","unstructured":"D. W. Li, Z. Zhang, X. T. Chen, H. B. Ling, K. Q. Huang. A richly annotated dataset for pedestrian attribute recognition, [Online], Available: https:\/\/arxiv.org\/abs\/1603.07054, April 27, 2016."},{"key":"1321_CR13","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1102\/ICCV.2017.46","volume-title":"HydraPlus-Net: Attentive deep features for pedestrian analysis","author":"X H Liu","year":"2017","unstructured":"X. H. Liu, H. Y. Zhao, M. Q. Tian, L. Sheng, J. Shao, S. Yi, J. J. Yan, X. G. Wang. HydraPlus-Net: Attentive deep features for pedestrian analysis. In Proceedings of IEEE International Conference on Computer Vision, IEEE, Venice, Italy, pp. 350\u2013352, 2017. DOI: https:\/\/doi.org\/10.1102\/ICCV.2017.46."},{"key":"1321_CR14","doi-asserted-by":"publisher","first-page":"475","DOI":"10.1007\/978-3-319-46475-6_30","volume-title":"Deep attributes driven mutti-camera person re-identification","author":"C Su","year":"2016","unstructured":"C. Su, S. L. Zhang, J. L. Xing, W. Gao, Q. Tian. Deep attributes driven mutti-camera person re-identification. In Proceedings of the 14th European Conference on Computer Vision, Springer, Amsterdam, The Netherlands, pp. 475\u2013491, 2016. DOI: https:\/\/doi.org\/10.1007\/978-3-319-46475-6_30."},{"key":"1321_CR15","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1016\/j.patcog.2019.06.006","volume":"95","author":"Y T Lin","year":"2019","unstructured":"Y. T. Lin, L. Zheng, Z. D. Zheng, Y. Wu, Z. L. Hu, C. G. Yan, Y. Yang. Improving person re-identification by attribute and identity learning. Pattern Recognition, vol. 95, pp. 151\u2013161, 2019. DOI: https:\/\/doi.org\/10.1016\/j.patcog.2019.06.006.","journal-title":"Pattern Recognition"},{"key":"1321_CR16","doi-asserted-by":"publisher","first-page":"2133","DOI":"10.1109\/CVPR.2019.00224","volume-title":"Jo\u00ednt discriminative and generative learn\u00edng for person re-identification","author":"Z D Zheng","year":"2012","unstructured":"Z. D. Zheng, X. D. Yang, Z. D. Yu, L. Zheng, Y. Yang, J. Kautz. Jo\u00ednt discriminative and generative learn\u00edng for person re-identification. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Long Beach, USA, pp. 2133\u20132142, 2012. DOI: https:\/\/doi.org\/10.1109\/CVPR.2019.00224."},{"key":"1321_CR17","doi-asserted-by":"publisher","first-page":"5079","DOI":"10.1109\/CVPR.2015.7299143","volume-title":"Pedestrian detection aided by deep learning semantic tasks","author":"Y L Tian","year":"2015","unstructured":"Y. L. Tian, P. Luo, X. G. Wang, X. O. Tang. Pedestrian detection aided by deep learning semantic tasks. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Boston, USA, pp. 5079\u20135087, 2015. DOI: https:\/\/doi.org\/10.1109\/CVPR.2015.7299143."},{"issue":"10","key":"1321_CR18","doi-asserted-by":"publisher","first-page":"2884","DOI":"10.1109\/TCSVT.2017.2781738","volume":"28","author":"X B Liu","year":"2018","unstructured":"X. B. Liu, Y. L. Xu, L. Zhu, Y. D. Mu. A stochastic attribute grammar for robust cross-view human tracking. IEEE Transactions on Circuits and Systems for Video Technology, vol. 28, no. 10, pp. 2884\u20132895, 2018. DOI: https:\/\/doi.org\/10.1109\/TCSVT.2017.2781738.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"8","key":"1321_CR19","doi-asserted-by":"publisher","first-page":"2035","DOI":"10.1109\/TMM.2013.2279658","volume":"15","author":"X W Wang","year":"2013","unstructured":"X. W. Wang, T. Zhang, D. R. Tretter, Q. Lin. Personal clothing retrieval on photo collections by color and attributes. IEEE Transactions on Multimedia, vol. 15, no. 8, pp. 2035\u20132045, 2013. DOI: https:\/\/doi.org\/10.1109\/TMM.2013.2279658.","journal-title":"IEEE Transactions on Multimedia"},{"key":"1321_CR20","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1145\/2578726.2578732","volume-title":"Attribute-based people search: Lessons learnt from a practical surveillance system","author":"R Feris","year":"2014","unstructured":"R. Feris, R. Bobbitt, L. Brown, S. Pankanti. Attribute-based people search: Lessons learnt from a practical surveillance system. In Proceedings of International Conference on Multimedia Retrieval, ACM, Glasgow, UK, pp. 153\u2013160, 2014. DOI: https:\/\/doi.org\/10.1145\/2578726.2578732."},{"key":"1321_CR21","doi-asserted-by":"publisher","first-page":"3337","DOI":"10.1109\/CVPR.2011.5995353","volume-title":"Recognizing human actions by attributes","author":"J E Liu","year":"2011","unstructured":"J. E. Liu, B. Kuipers, S. Savarese. Recognizing human actions by attributes. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Colorado Springs, USA, pp. 3337\u20133344, 2011. DOI: https:\/\/doi.org\/10.1109\/CVPR.2011.5995353."},{"issue":"5","key":"1321_CR22","doi-asserted-by":"publisher","first-page":"500","DOI":"10.1007\/s11633-014-0831-4","volume":"11","author":"X F Ji","year":"2014","unstructured":"X. F. Ji, Q. Q. Wu, Z. J. Ju, Y. Y. Wang. Study of human action recognition based on improved spatio-temporal features. International Journal of Automation and Computing, vol. 11, no. 5, pp. 500\u2013509, 2014. DOI: https:\/\/doi.org\/10.1007\/s11633-014-0831-4.","journal-title":"International Journal of Automation and Computing"},{"issue":"3","key":"1321_CR23","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1007\/s11633-020-1258-8","volume":"18","author":"L F Wu","year":"2021","unstructured":"L. F. Wu, Q. Wang, M. Jian, Y. Qiao, B. X. Zhao. A comprehensive review of group activity recognition in videos. International Journal of Automation and Computing, vol. 18, no. 3, pp. 334\u2013350, 2021. DOI: https:\/\/doi.org\/10.1007\/s11633-020-1258-8.","journal-title":"International Journal of Automation and Computing"},{"issue":"5","key":"1321_CR24","doi-asserted-by":"publisher","first-page":"718","DOI":"10.1007\/s11633-021-1289-9","volume":"18","author":"Z W Xu","year":"2021","unstructured":"Z. W. Xu, X. J. Wu, J. Kittler. STRNet: Triple-stream spatiotemporal relation network for action recognition. International Journal of Automation and Computing, vol. 18, no. 5, pp. 718\u2013730, 2021. DOI: https:\/\/doi.org\/10.1007\/s11633-021-1289-9.","journal-title":"International Journal of Automation and Computing"},{"key":"1321_CR25","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1109\/CVPR42600.2020.00058","volume-title":"SCT: Set constrained temporal transformer for set supervised action segmentation","author":"M Fayyaz","year":"2020","unstructured":"M. Fayyaz, J. Gall. SCT: Set constrained temporal transformer for set supervised action segmentation. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Seattle, USA, pp.498\u2013507, 2020. DOI: https:\/\/doi.org\/10.1109\/CVPR42600.2020.00058."},{"key":"1321_CR26","doi-asserted-by":"publisher","first-page":"10817","DOI":"10.1109\/CVPR42600.2020.01083","volume-title":"Set-constrained viterbi for set-supervised action segmentation","author":"J Li","year":"2020","unstructured":"J. Li, S. Todorovic. Set-constrained viterbi for set-supervised action segmentation. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Seattle, USA, pp. 10817\u201310826, 2020. DOI: https:\/\/doi.org\/10.1109\/CVPR42600.2020.01083."},{"key":"1321_CR27","doi-asserted-by":"publisher","first-page":"14021","DOI":"10.1009\/CVPR42600.2020.01404","volume-title":"Improving action segmentation via graph-based temporal reasoning","author":"Y F Huang","year":"2020","unstructured":"Y. F. Huang, Y. Sugano, Y. Sato. Improving action segmentation via graph-based temporal reasoning. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Seattle, USA, pp. 14021\u201314031, 2020. DOI: https:\/\/doi.org\/10.1009\/CVPR42600.2020.01404."},{"key":"1321_CR28","doi-asserted-by":"publisher","first-page":"9898","DOI":"10.1109\/CVPR42600.2020.00992","volume-title":"Learning a weakly-supervised video actor-action segmentation model with a wise selection","author":"J Chen","year":"2020","unstructured":"J. Chen, Z. H. Li, J. B. Luo, C. L. Xu. Learning a weakly-supervised video actor-action segmentation model with a wise selection. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Seattle, USA, pp.9898\u20139908, 2020. DOI: https:\/\/doi.org\/10.1109\/CVPR42600.2020.00992."},{"key":"1321_CR29","doi-asserted-by":"publisher","first-page":"886","DOI":"10.1109\/CVPR.2005.177","volume-title":"Histograms of oriented gradients for human detection","author":"N Dalal","year":"2005","unstructured":"N. Dalal, B. Triggs. Histograms of oriented gradients for human detection. In Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE, San Diego, USA, pp. 886\u2013893, 2005. DOI: https:\/\/doi.org\/10.1109\/CVPR.2005.177."},{"key":"1321_CR30","doi-asserted-by":"publisher","unstructured":"R. Layne, T. Hospedales, S. G. Gong. Person re-identification by attributes. In Proceedings of British Machine Vision Conference, Surrey, UK, Article number 24, 2012. DOI: https:\/\/doi.org\/10.5244\/C.26.24.","DOI":"10.5244\/C.26.24"},{"key":"1321_CR31","doi-asserted-by":"publisher","first-page":"111","DOI":"10.0109\/CPPR.2015.7486476","volume-title":"Multi-attribute learning for pedestrian attribute recognition m surveillance scenarios","author":"D W Li","year":"2015","unstructured":"D. W. Li, X. T. Chen, K. Q. Huang. Multi-attribute learning for pedestrian attribute recognition m surveillance scenarios. In Proceedings of the 3rd IAPR Asian Conference on Pattern Recognition, IEEE, Kuala Lumpur, Malaysia, pp. 111\u2013115, 2015. DOI: https:\/\/doi.org\/10.0109\/CPPR.2015.7486476."},{"key":"1321_CR32","unstructured":"J. J. Zhang, P. Y. Ren, J. M. Li. Deep template matching for pedestrian attribute recognition with the auxiliary supervision of attribute-wise keypoints, [Online], Available: https:\/\/arxiv.org\/abs\/2011.06798, November 13, 2020."},{"key":"1321_CR33","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1109\/ICCV.2017.65","volume-title":"Attribute recognition by joint recurrent learning of context and correlation","author":"J Y Wang","year":"2017","unstructured":"J. Y. Wang, X. T. Zhu, S. G. Gong, W. Li. Attribute recognition by joint recurrent learning of context and correlation. In Proceedings of IEEE International Conference on Computer Vision, IEEE, Venice, Italy, pp. 531\u2013540, 2017. DOI: https:\/\/doi.org\/10.1109\/ICCV.2017.65."},{"key":"1321_CR34","doi-asserted-by":"publisher","first-page":"3177","DOI":"10.24963\/ijcai.2018\/441","volume-title":"Grouping attribute recognition for pedestrian with joint recurrent learning","author":"X Zhao","year":"2018","unstructured":"X. Zhao, L. F. Sang, G. G. Ding, Y. C. Guo, X. M. Jin. Grouping attribute recognition for pedestrian with joint recurrent learning. In Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI, Stockholm, Sweden, pp. 3177\u20133183, 2018. DOI: https:\/\/doi.org\/10.24963\/ijcai.2018\/441."},{"key":"1321_CR35","doi-asserted-by":"publisher","first-page":"4996","DOI":"10.1109\/ICCV.2019.00510","volume-title":"Improving pedestrian attribute recognition with weakly-supervised multi-scale attribute-specific localization","author":"C F Tang","year":"2019","unstructured":"C. F. Tang, L. Sheng, Z. X. Zhang, X. L. Hu. Improving pedestrian attribute recognition with weakly-supervised multi-scale attribute-specific localization. In Proceedings of IEEE\/CVF International Conference on Computer Vision, IEEE, Seoul, Korea, pp. 4996\u20135005, 2019. DOI: https:\/\/doi.org\/10.1109\/ICCV.2019.00510."},{"key":"1321_CR36","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1007\/978-3-319-10602-1_26","volume-title":"Edge boxes: Locating object proposals from edges","author":"C L Zitnick","year":"2014","unstructured":"C. L. Zitnick, P. Doll\u00e1r. Edge boxes: Locating object proposals from edges. In Proceedings of the 13th European Conference on Computer Vision, Springer, Zurich, Switzerland, pp. 391\u2013405, 2014. DOI: https:\/\/doi.org\/10.1007\/978-3-319-10602-1_26."},{"issue":"7","key":"1321_CR37","doi-asserted-by":"publisher","first-page":"3472","DOI":"10.1109\/TIP.2018.2818438","volume":"27","author":"Z X Feng","year":"2018","unstructured":"Z. X. Feng, J. H. Lai, X. H. Xie. Learning view-specific deep networks for person re-identification. IEEE Transactions on Image Processing, vol. 27, no. 7, pp. 3472\u20133483, 2018. DOI: https:\/\/doi.org\/10.1109\/TIP.2018.2818438.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1321_CR38","doi-asserted-by":"publisher","first-page":"643","DOI":"10.1145\/2671188.2749408","volume-title":"Multi-view face detection using deep convolutional neural networks","author":"S S Farfade","year":"2015","unstructured":"S. S. Farfade, M. J. Saberian, L. J. Li. Multi-view face detection using deep convolutional neural networks. In Proceedings of the 5th ACM on International Conference on Multimedia Retrieval, ACM, Shanghai, China, pp. 643\u2013650, 2015. DOI: https:\/\/doi.org\/10.1145\/2671188.2749408."},{"key":"1321_CR39","doi-asserted-by":"publisher","first-page":"86984","DOI":"10.1109\/ACCESS.2020.2992063","volume":"8","author":"H Sadr","year":"2020","unstructured":"H. Sadr, M. M. Pedram, M. Teshnehlab. Multi-view deep network: A deep model based on learning features from heterogeneous neural networks or sentiment analysis. IEEE Access, vol. 8, pp. 86984\u201386997, 2020. DOI: https:\/\/doi.org\/10.1109\/ACCESS.2020.2992063.","journal-title":"IEEE Access"},{"key":"1321_CR40","doi-asserted-by":"publisher","first-page":"2027","DOI":"10.1109\/CVPR.2017.219","volume-title":"Learning spatial regularization with image-level supervisions or multi-label image classification","author":"F Zhu","year":"2017","unstructured":"F. Zhu, H. S. Li, W. L. Ouyang, N. H. Yu, X. G. Wang. Learning spatial regularization with image-level supervisions or multi-label image classification. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Honolulu, USA, pp. 2027\u20132036, 2017. DOI: https:\/\/doi.org\/10.1109\/CVPR.2017.219."},{"issue":"12","key":"1321_CR41","doi-asserted-by":"publisher","first-page":"6126","DOI":"10.1109\/TIP.2019.2919199","volume":"28","author":"Z C Tan","year":"2019","unstructured":"Z. C. Tan, Y. Yang, J. Wan, H. Y. Hang, G. D. Guo, S. Z. Li. Attention-based pedestrian attribute analysis. IEEE Transactions on Image Processing, vol. 28, no. 12, pp. 6126\u20136140, 2019. DOI: https:\/\/doi.org\/10.1109\/TIP.2019.2919199.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1321_CR42","first-page":"4278","volume-title":"Inception-v4, inception-resnet and the impact of residual connections on learning","author":"C Szegedy","year":"2017","unstructured":"C. Szegedy, S. Ioffe, V. Vanhoucke, A. A. Alemi. Inception-v4, inception-resnet and the impact of residual connections on learning. In Proceedings of the 31st AAAI Conference on Artificial Intelligence, AAAI Press, San Francisco, USA, pp. 4278\u20134284, 2017."},{"key":"1321_CR43","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/CVPR.2015.7298594","volume-title":"Going deeper with convolutions","author":"C Szegedy","year":"2015","unstructured":"C. Szegedy, W. Liu, Y. Q. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, A. Rabinovich. Going deeper with convolutions. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Boston, USA, pp. 1\u20139, 2015. DOI: https:\/\/doi.org\/10.1109\/CVPR.2015.7298594."},{"key":"1321_CR44","first-page":"448","volume-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"S Ioffe","year":"2015","unstructured":"S. Ioffe, C. Szegedy. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In Proceedings of the 32nd International Conference on International Conference on Machine Learning, JMLR, Lille, France, pp. 448\u2013456, 2015."},{"key":"1321_CR45","doi-asserted-by":"publisher","first-page":"2818","DOI":"10.1109\/CVPR.2016.308","volume-title":"Rethinking the inception architecture for computer vision","author":"C Szegedy","year":"2016","unstructured":"C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, Z. Wojna. Rethinking the inception architecture for computer vision. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Las Vegas, USA, pp. 2818\u20132826, 2016. DOI: https:\/\/doi.org\/10.1109\/CVPR.2016.308."},{"key":"1321_CR46","unstructured":"H. Cai, C. Gan, T. Z. Wang, Z. K. Zhang, S. Han. Once-for-all: Train one network and specialize it for efficient deployment, [Online], Available: https:\/\/arxiv.org\/abs\/1908.09791, 2019."},{"key":"1321_CR47","doi-asserted-by":"publisher","first-page":"1314","DOI":"10.1109\/ICCV.2019.00140","volume-title":"Searching for MobileNetV3","author":"A Howard","year":"2019","unstructured":"A. Howard, M. Sandler, B. Chen, W. J. Wang, L. C. Chen, M. X. Tan, G. Chu, V. Vasudevan, Y. K. Zhu, R. M. Pang, H, Adam, Q. Le. Searching for MobileNetV3. In Proceedings of IEEE\/CVF International Conference on Computer Vision, IEEE, Seoul, Korea, pp. 1314\u20131324, 2019. DOI: https:\/\/doi.org\/10.1109\/ICCV.2019.00140."},{"key":"1321_CR48","doi-asserted-by":"publisher","first-page":"789","DOI":"10.1145\/2647868.2654966","volume-title":"Pedestrian attribute recognition at far distance","author":"Y B Deng","year":"2014","unstructured":"Y. B. Deng, P. Luo, C. C. Loy, X. O. Tang. Pedestrian attribute recognition at far distance. In Proceedings of the 22nd ACM International Conference on Multimedia, ACM, Lisboa, Portugal, pp. 789\u2013792, 2014. DOI: https:\/\/doi.org\/10.1145\/2647868.2654966."},{"key":"1321_CR49","unstructured":"M. S. Sarfraz, A. Schumann, Y. Wang, R. Stiefelhagen. Deep view-sensitive pedestrian attribute inference in an end-to-end model, [Online], Available: https:\/\/arxiv.org\/abs\/1707.06089, July 19, 2017."},{"key":"1321_CR50","doi-asserted-by":"publisher","first-page":"729","DOI":"10.1109\/CVPR.2019.00082","volume-title":"Visual attention consistency under image transforms for multi-label image classification","author":"H Guo","year":"2019","unstructured":"H. Guo, K. Zheng, X. C. Fan, H. K. Yu, S. Wang. Visual attention consistency under image transforms for multi-label image classification. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Long Beach, USA, pp. 729\u2013739, 2019. DOI: https:\/\/doi.org\/10.1109\/CVPR.2019.00082."},{"key":"1321_CR51","unstructured":"J. Jia, H. J. Huang, W. J. Yang, X. T. Chen, K. Q. Huang. Rethinking of pedestrian attribute recognition: Realistic datasets with efficient method, [Online], Available: https:\/\/arxiv.org\/abs\/2005.11909, May 26, 2020."},{"key":"1321_CR52","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ICME46284.2020.9102757","volume-title":"Multi-task learning via co-attentive sharing for pedestrian attribute recognition","author":"H T Zeng","year":"2020","unstructured":"H. T. Zeng, H. Z. Ai, Z. J. Zhuang, L. Chen. Multi-task learning via co-attentive sharing for pedestrian attribute recognition. In Proceedings of IEEE International Conference on Multimedia and Expo, IEEE, London, UK, pp. 1\u20136, 2020. DOI: https:\/\/doi.org\/10.1109\/ICME46284.2020.9102757."},{"key":"1321_CR53","unstructured":"X. Y. Yu, W. C. Chen, Y. F. Jin, L. L. Ou. Pedestrian View-attribute Location and Recognition Method in Video Surveillance Scene Based on Attention Mechanism, CN113361336A, September 2021. (in Chinese)"}],"container-title":["Machine Intelligence Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11633-022-1321-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11633-022-1321-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11633-022-1321-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T20:51:00Z","timestamp":1666558260000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11633-022-1321-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,7]]},"references-count":53,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,4]]}},"alternative-id":["1321"],"URL":"https:\/\/doi.org\/10.1007\/s11633-022-1321-8","relation":{},"ISSN":["2731-538X","2731-5398"],"issn-type":[{"value":"2731-538X","type":"print"},{"value":"2731-5398","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,7]]},"assertion":[{"value":"20 June 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 December 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 January 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}