{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:58:05Z","timestamp":1740099485655,"version":"3.37.3"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030304867"},{"type":"electronic","value":"9783030304874"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-30487-4_37","type":"book-chapter","created":{"date-parts":[[2019,9,8]],"date-time":"2019-09-08T19:02:47Z","timestamp":1567969367000},"page":"471-483","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["The Same Size Dilated Attention Network for Keypoint Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4314-1017","authenticated-orcid":false,"given":"Yuan","family":"Chang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5028-4684","authenticated-orcid":false,"given":"Zixuan","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiwei","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,9,9]]},"reference":[{"key":"37_CR1","unstructured":"Ali apparel keypoints dataset. \n                      https:\/\/tianchi.aliyun.com\/competition\/entrance\/231670\/information\/"},{"key":"37_CR2","doi-asserted-by":"publisher","unstructured":"Andriluka, M., Roth, S., Schiele, B.: Pictorial structures revisited: people detection and articulated pose estimation. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1014\u20131021. IEEE (2009). \n                      https:\/\/doi.org\/10.1109\/cvprw.2009.5206754","DOI":"10.1109\/cvprw.2009.5206754"},{"key":"37_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"717","DOI":"10.1007\/978-3-319-46478-7_44","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Bulat","year":"2016","unstructured":"Bulat, A., Tzimiropoulos, G.: Human pose estimation via convolutional part heatmap regression. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 717\u2013732. Springer, Cham (2016). \n                      https:\/\/doi.org\/10.1007\/978-3-319-46478-7_44"},{"issue":"4","key":"37_CR4","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/tpami.2017.2699184","volume":"40","author":"LC Chen","year":"2018","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834\u2013848 (2018). \n                      https:\/\/doi.org\/10.1109\/tpami.2017.2699184","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"37_CR5","doi-asserted-by":"publisher","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv preprint \n                      arXiv:1706.05587\n                      \n                     (2017). \n                      https:\/\/doi.org\/10.4271\/2018-01-1635","DOI":"10.4271\/2018-01-1635"},{"key":"37_CR6","doi-asserted-by":"publisher","unstructured":"Chen, Y., Wang, Z., Peng, Y., Zhang, Z., Yu, G., Sun, J.: Cascaded pyramid network for multi-person pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7103\u20137112 (2018). \n                      https:\/\/doi.org\/10.1109\/cvpr.2018.00742","DOI":"10.1109\/cvpr.2018.00742"},{"key":"37_CR7","doi-asserted-by":"publisher","unstructured":"Dantone, M., Gall, J., Leistner, C., Van Gool, L.: Human pose estimation using body parts dependent joint regressors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3041\u20133048 (2013). \n                      https:\/\/doi.org\/10.1109\/cvpr.2013.391","DOI":"10.1109\/cvpr.2013.391"},{"key":"37_CR8","doi-asserted-by":"publisher","unstructured":"Dong, X., Yan, Y., Ouyang, W., Yang, Y.: Style aggregated network for facial landmark detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 379\u2013388 (2018). \n                      https:\/\/doi.org\/10.1109\/cvpr.2018.00047","DOI":"10.1109\/cvpr.2018.00047"},{"key":"37_CR9","doi-asserted-by":"publisher","unstructured":"Gkioxari, G., Arbelaez, P., Bourdev, L., Malik, J.: Articulated pose estimation using discriminative armlet classifiers. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3342\u20133349 (2013). \n                      https:\/\/doi.org\/10.1109\/cvpr.2013.429","DOI":"10.1109\/cvpr.2013.429"},{"key":"37_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"728","DOI":"10.1007\/978-3-319-46493-0_44","volume-title":"Computer Vision \u2013 ECCV 2016","author":"G Gkioxari","year":"2016","unstructured":"Gkioxari, G., Toshev, A., Jaitly, N.: Chained predictions using convolutional neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 728\u2013743. Springer, Cham (2016). \n                      https:\/\/doi.org\/10.1007\/978-3-319-46493-0_44"},{"key":"37_CR11","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016). \n                      https:\/\/doi.org\/10.1109\/cvpr.2016.90","DOI":"10.1109\/cvpr.2016.90"},{"key":"37_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1007\/978-3-319-46466-4_3","volume-title":"Computer Vision \u2013 ECCV 2016","author":"E Insafutdinov","year":"2016","unstructured":"Insafutdinov, E., Pishchulin, L., Andres, B., Andriluka, M., Schiele, B.: DeeperCut: a deeper, stronger, and faster multi-person pose estimation model. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 34\u201350. Springer, Cham (2016). \n                      https:\/\/doi.org\/10.1007\/978-3-319-46466-4_3"},{"key":"37_CR13","doi-asserted-by":"publisher","unstructured":"Jie, H., Li, S., Gang, S., Jie, H., Li, S., Gang, S.: Squeeze-and-excitation networks (2017). \n                      https:\/\/doi.org\/10.1109\/cvpr.2018.00745","DOI":"10.1109\/cvpr.2018.00745"},{"key":"37_CR14","doi-asserted-by":"publisher","unstructured":"Johnson, S., Everingham, M.: Learning effective human pose estimation from inaccurate annotation. In: CVPR 2011, pp. 1465\u20131472. IEEE (2011). \n                      https:\/\/doi.org\/10.1109\/cvpr.2011.5995318","DOI":"10.1109\/cvpr.2011.5995318"},{"key":"37_CR15","doi-asserted-by":"publisher","unstructured":"Li, Y., Zhang, X., Chen, D.: Csrnet: Dilated convolutional neural networks for understanding the highly congested scenes (2018). \n                      https:\/\/doi.org\/10.1109\/cvpr.2018.00120","DOI":"10.1109\/cvpr.2018.00120"},{"key":"37_CR16","doi-asserted-by":"publisher","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017). \n                      https:\/\/doi.org\/10.1109\/cvpr.2017.106","DOI":"10.1109\/cvpr.2017.106"},{"key":"37_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). \n                      https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"37_CR18","doi-asserted-by":"publisher","unstructured":"Liu, N., Han, J., Yang, M.H.: Picanet: learning pixel-wise contextual attention for saliency detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3089\u20133098 (2018). \n                      https:\/\/doi.org\/10.1109\/cvpr.2018.00326","DOI":"10.1109\/cvpr.2018.00326"},{"key":"37_CR19","doi-asserted-by":"publisher","unstructured":"Merget, D., Rock, M., Rigoll, G.: Robust facial landmark detection via a fully-convolutional local-global context network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 781\u2013790 (2018). \n                      https:\/\/doi.org\/10.1109\/cvpr.2018.00088","DOI":"10.1109\/cvpr.2018.00088"},{"key":"37_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/978-3-319-46484-8_29","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Newell","year":"2016","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 483\u2013499. Springer, Cham (2016). \n                      https:\/\/doi.org\/10.1007\/978-3-319-46484-8_29"},{"key":"37_CR21","doi-asserted-by":"publisher","unstructured":"Papandreou, G., et al.: Towards accurate multi-person pose estimation in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4903\u20134911 (2017). \n                      https:\/\/doi.org\/10.1109\/cvpr.2017.395","DOI":"10.1109\/cvpr.2017.395"},{"key":"37_CR22","doi-asserted-by":"publisher","unstructured":"Pishchulin, L., Andriluka, M., Gehler, P., Schiele, B.: Poselet conditioned pictorial structures. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 588\u2013595 (2013). \n                      https:\/\/doi.org\/10.1109\/cvpr.2013.82","DOI":"10.1109\/cvpr.2013.82"},{"key":"37_CR23","doi-asserted-by":"publisher","unstructured":"Sapp, B., Taskar, B.: Modec: multimodal decomposable models for human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3674\u20133681 (2013). \n                      https:\/\/doi.org\/10.1109\/cvpr.2013.471","DOI":"10.1109\/cvpr.2013.471"},{"key":"37_CR24","doi-asserted-by":"publisher","unstructured":"Sapp, B., Jordan, C., Taskar, B.: Adaptive pose priors for pictorial structures. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 422\u2013429. IEEE (2010). \n                      https:\/\/doi.org\/10.1109\/cvpr.2010.5540182","DOI":"10.1109\/cvpr.2010.5540182"},{"issue":"3","key":"37_CR25","doi-asserted-by":"publisher","first-page":"035215","DOI":"10.1063\/1.5024463","volume":"8","author":"Aichun Zhu","year":"2018","unstructured":"Tompson, J.J., Jain, A., LeCun, Y., Bregler, C.: Joint training of a convolutional network and a graphical model for human pose estimation. In: Advances in Neural Information Processing Systems, pp. 1799\u20131807 (2014). \n                      https:\/\/doi.org\/10.1063\/1.5024463","journal-title":"AIP Advances"},{"key":"37_CR26","doi-asserted-by":"publisher","unstructured":"Toshev, A., Szegedy, C.: Deeppose: human pose estimation via deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1653\u20131660 (2014). \n                      https:\/\/doi.org\/10.1109\/cvpr.2014.214","DOI":"10.1109\/cvpr.2014.214"},{"key":"37_CR27","doi-asserted-by":"publisher","unstructured":"Wang, F., et al.: Residual attention network for image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3156\u20133164 (2017). \n                      https:\/\/doi.org\/10.1109\/cvpr.2017.683","DOI":"10.1109\/cvpr.2017.683"},{"key":"37_CR28","doi-asserted-by":"publisher","unstructured":"Wang, P., et al.: Understanding convolution for semantic segmentation (2017). \n                      https:\/\/doi.org\/10.4271\/2018-01-1635","DOI":"10.4271\/2018-01-1635"},{"key":"37_CR29","doi-asserted-by":"publisher","unstructured":"Wei, S.E., Ramakrishna, V., Kanade, T., Sheikh, Y.: Convolutional pose machines. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4724\u20134732 (2016). \n                      https:\/\/doi.org\/10.1109\/cvpr.2016.511","DOI":"10.1109\/cvpr.2016.511"},{"key":"37_CR30","doi-asserted-by":"publisher","unstructured":"Wei, Y., Xiao, H., Shi, H., Jie, Z., Feng, J., Huang, T.S.: Revisiting dilated convolution: A simple approach for weakly- and semi- supervised semantic segmentation (2018). \n                      https:\/\/doi.org\/10.1109\/cvpr.2018.00759","DOI":"10.1109\/cvpr.2018.00759"},{"key":"37_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01234-2_1","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Woo","year":"2018","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 3\u201319. Springer, Cham (2018). \n                      https:\/\/doi.org\/10.1007\/978-3-030-01234-2_1"},{"key":"37_CR32","doi-asserted-by":"publisher","unstructured":"Wu, W., Qian, C., Yang, S., Wang, Q., Cai, Y., Zhou, Q.: Look at boundary: a boundary-aware face alignment algorithm. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2129\u20132138 (2018). \n                      https:\/\/doi.org\/10.1109\/cvpr.2018.00227","DOI":"10.1109\/cvpr.2018.00227"},{"key":"37_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"472","DOI":"10.1007\/978-3-030-01231-1_29","volume-title":"Computer Vision \u2013 ECCV 2018","author":"B Xiao","year":"2018","unstructured":"Xiao, B., Wu, H., Wei, Y.: Simple baselines for human pose estimation and tracking. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 472\u2013487. Springer, Cham (2018). \n                      https:\/\/doi.org\/10.1007\/978-3-030-01231-1_29"},{"key":"37_CR34","doi-asserted-by":"publisher","unstructured":"Xu, J., Zhao, R., Zhu, F., Wang, H., Ouyang, W.: Attention-aware compositional network for person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2119\u20132128 (2018). \n                      https:\/\/doi.org\/10.1109\/cvpr.2018.00226","DOI":"10.1109\/cvpr.2018.00226"},{"key":"37_CR35","doi-asserted-by":"publisher","unstructured":"Yang, W., Li, S., Ouyang, W., Li, H., Wang, X.: Learning feature pyramids for human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1281\u20131290 (2017). \n                      https:\/\/doi.org\/10.1109\/iccv.2017.144","DOI":"10.1109\/iccv.2017.144"},{"key":"37_CR36","doi-asserted-by":"publisher","unstructured":"Yang, Y., Ramanan, D.: Articulated pose estimation with flexible mixtures-of-parts. In: CVPR 2011, pp. 1385\u20131392. IEEE (2011). \n                      https:\/\/doi.org\/10.1109\/cvpr.2011.5995741","DOI":"10.1109\/cvpr.2011.5995741"},{"issue":"14","key":"37_CR37","doi-asserted-by":"publisher","first-page":"18689","DOI":"10.1007\/s11042-018-5653-x","volume":"77","author":"Duc My Vo","year":"2018","unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv preprint \n                      arXiv:1511.07122\n                      \n                     (2015). \n                      https:\/\/doi.org\/10.1007\/s11042-018-5653-x","journal-title":"Multimedia Tools and Applications"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2019: Theoretical Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-30487-4_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,8]],"date-time":"2019-09-08T19:14:38Z","timestamp":1567970078000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-30487-4_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030304867","9783030304874"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-30487-4_37","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"9 September 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}