{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:42:43Z","timestamp":1775230963690,"version":"3.50.1"},"reference-count":46,"publisher":"Tsinghua University Press","issue":"3","license":[{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,4,7]],"date-time":"2021-04-07T00:00:00Z","timestamp":1617753600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Comp. Visual. Med."],"published-print":{"date-parts":[[2021,9]]},"DOI":"10.1007\/s41095-021-0214-z","type":"journal-article","created":{"date-parts":[[2021,4,6]],"date-time":"2021-04-06T16:02:20Z","timestamp":1617724940000},"page":"335-347","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":52,"title":["EfficientPose: Efficient human pose estimation with neural architecture search"],"prefix":"10.26599","volume":"7","author":[{"given":"Wenqiang","family":"Zhang","sequence":"first","affiliation":[{"name":"School of EIC, Huazhong University of Science and Technology, Wuhan 430074, China"}]},{"given":"Jiemin","family":"Fang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Huazhong University of Science and Technology, Wuhan 430074, China; School of EIC, Huazhong University of Science and Technology, Wuhan 430074, China"}]},{"given":"Xinggang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of EIC, Huazhong University of Science and Technology, Wuhan 430074, China"}]},{"given":"Wenyu","family":"Liu","sequence":"additional","affiliation":[{"name":"School of EIC, Huazhong University of Science and Technology, Wuhan 430074, China"}]}],"member":"11138","reference":[{"key":"214_CR1","doi-asserted-by":"crossref","unstructured":"Yang, Y.; Ramanan, D. Articulated pose estimation with flexible mixtures-of-parts. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1385\u20131392, 2011.","DOI":"10.1109\/CVPR.2011.5995741"},{"key":"214_CR2","doi-asserted-by":"crossref","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, 588\u2013595, 2013.","DOI":"10.1109\/CVPR.2013.82"},{"key":"214_CR3","doi-asserted-by":"crossref","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, 1653\u20131660, 2014.","DOI":"10.1109\/CVPR.2014.214"},{"key":"214_CR4","doi-asserted-by":"crossref","unstructured":"Newell, A.; Yang, K. Y.; Deng, J. Stacked hourglass networks for human pose estimation. In: Computer Vision \u2014 ECCV 2016. Lecture Notes in Computer Science, Vol. 9912. Leibe, B.; Matas, J.; Sebe, N.; Welling, M. Eds. Springer Cham, 483\u2013499, 2016.","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"214_CR5","doi-asserted-by":"crossref","unstructured":"Xiao, B.; Wu, H. P.; Wei, Y. C. Simple baselines for human pose estimation and tracking. In: Computer Vision \u2014 ECCV 2018. Lecture Notes in Computer Science, Vol. 11210. Ferrari, V.; Hebert, M.; Sminchisescu, C.; Weiss, Y. Eds. Springer Cham, 472\u2013487, 2018.","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"214_CR6","doi-asserted-by":"crossref","unstructured":"Sun, K.; Xiao, B.; Liu, D.; Wang, J. D. Deep high-resolution representation learning for human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 5686\u20135696, 2019.","DOI":"10.1109\/CVPR.2019.00584"},{"key":"214_CR7","doi-asserted-by":"crossref","unstructured":"Andriluka, M.; Pishchulin, L.; Gehler, P.; Schiele, B. 2D human pose estimation: New benchmark and state of the art analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 3686\u20133693, 2014.","DOI":"10.1109\/CVPR.2014.471"},{"key":"214_CR8","doi-asserted-by":"crossref","unstructured":"Lin, T. Y.; Maire, M.; Belongie, S.; Hays, J.; Perona, P.; Ramanan, D.; Doll\u00e1r, P.; Zitnick, C. L. Microsoft COCO: Common objects in context. In: Computer Vision \u2014 ECCV 2014. Lecture Notes in Computer Science, Vol. 8693. Fleet, D.; Pajdla, T.; Schiele, B.; Tuytelaars, T. Eds. Springer Cham, 740\u2013755, 2014.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"214_CR9","doi-asserted-by":"crossref","unstructured":"Chen, Y. L.; Wang, Z. C.; Peng, Y. X.; Zhang, Z. Q.; Yu, G.; Sun, J. Cascaded pyramid network for multi-person pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 7103\u20137112, 2018.","DOI":"10.1109\/CVPR.2018.00742"},{"key":"214_CR10","unstructured":"Li, W. B.; Wang, Z. C.; Yin, B. Y.; Peng, Q. X.; Su, J. Rethinking on multi-stage networks for human pose estimation. arXiv preprint arXiv:1901.00148, 2019."},{"key":"214_CR11","doi-asserted-by":"crossref","unstructured":"He, K. M.; Zhang, X. Y.; Ren, S. Q.; Sun, J. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770\u2013778, 2016.","DOI":"10.1109\/CVPR.2016.90"},{"key":"214_CR12","unstructured":"Howard, A. G.; Zhu, M. L.; Chen, B.; Kalenichenko, D.; Adam, H. Mobilenets: Efficient convolutional neural networks formobile vision applications. arXiv preprint arXiv:1704.04861, 2017."},{"key":"214_CR13","doi-asserted-by":"crossref","unstructured":"Zoph, B.; Vasudevan, V.; Shlens, J.; Le, Q. V. Learning transferable architectures for scalable image recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 8697\u20138710, 2018.","DOI":"10.1109\/CVPR.2018.00907"},{"key":"214_CR14","doi-asserted-by":"crossref","unstructured":"Real, E.; Aggarwal, A.; Huang, Y. P.; Le, Q. V. Regularized evolution for image classifier architecture search. In: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33, 4780\u20134789, 2019.","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"214_CR15","unstructured":"Bender, G.; Kindermans, P.; Zoph, B.; Vasudevan, V.; Le, Q. Understanding and simplifying one-shot architecture search. In: Proceedings of the 35th International Conference on Machine Learning, 549\u2013558, 2018."},{"key":"214_CR16","unstructured":"Liu, H. X.; Simonyan, K.; Yang, Y. M. DARTS: Differentiable architecture search. In: Proceedings of the 7th International Conference on Learning Representations, 2019."},{"key":"214_CR17","unstructured":"Cai, H.; Zhu, L.; Han, S. ProxylessNAS: Direct neural architecture search on target task and hardware. In: Proceedings of the International Conference on Learning Representations, 2019."},{"key":"214_CR18","doi-asserted-by":"crossref","unstructured":"Wu, B.; Dai, X.; Zhang, P.; Wang, Y.; Sun, F.; Wu, Y.; Tian, Y.; Vajda, P.; Jia, Y.; Keutzer, K. Fbnet: Hardware-aware efficient convNet design via differentiable neural architecture search. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 10726\u201310734, 2019.","DOI":"10.1109\/CVPR.2019.01099"},{"key":"214_CR19","doi-asserted-by":"crossref","unstructured":"Liu, C. X.; Chen, L. C.; Schroff, F.; Adam, H.; Hua, W.; Yuille, A. L.; Fei-Fei, L. Auto-DeepLab: Hierarchical neural architecture search for semantic image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 82\u201392, 2019.","DOI":"10.1109\/CVPR.2019.00017"},{"key":"214_CR20","doi-asserted-by":"crossref","unstructured":"Zhang, Y.; Qiu, Z.; Liu, J.; Yao, T.; Liu, D.; Mei, T. Customizable architecture search forsemantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 11633\u201311642, 2019.","DOI":"10.1109\/CVPR.2019.01191"},{"key":"214_CR21","doi-asserted-by":"crossref","unstructured":"Ghiasi, G.; Lin, T. Y.; Le, Q. V. NAS-FPN: Learning scalable feature pyramid architecture for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 7029\u20137038, 2019.","DOI":"10.1109\/CVPR.2019.00720"},{"key":"214_CR22","doi-asserted-by":"crossref","unstructured":"Fang, J. M.; Sun, Y. Z.; Zhang, Q.; Peng, K. J.; Wang, X. G. FNA++: Fast network adaptation via parameter remapping and architecture search. In: Proceedings of the International Conference on Learning Representations, 2020.","DOI":"10.1109\/TPAMI.2020.3044416"},{"key":"214_CR23","doi-asserted-by":"crossref","unstructured":"Yang, W.; Li, S.; Ouyang, W. L.; Li, H. S.; Wang, X. G. Learning feature pyramids for human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, 1290\u20131299, 2017.","DOI":"10.1109\/ICCV.2017.144"},{"key":"214_CR24","doi-asserted-by":"crossref","unstructured":"Bulat, A.; Tzimiropoulos, G. Binarized convolutional landmark localizers for human pose estimation and face alignment with limited resources. In: Proceedings of the IEEE International Conference on Computer Vision, 3726\u20133734, 2017.","DOI":"10.1109\/ICCV.2017.400"},{"key":"214_CR25","doi-asserted-by":"crossref","unstructured":"Tang, Z. Q.; Peng, X.; Geng, S. J.; Wu, L. F.; Zhang, S. T.; Metaxas, D. Quantized densely connected U-nets for efficient landmark localization. In: Computer Vision \u2014 ECCV 2018. Lecture Notes in Computer Science, Vol. 11207. Ferrari, V.; Hebert, M.; Sminchisescu, C.; Weiss, Y. Eds. Springer Cham, 348\u2013364, 2018.","DOI":"10.1007\/978-3-030-01219-9_21"},{"key":"214_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, F.; Zhu, X. T.; Ye, M. Fast human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 3512\u20133521, 2019.","DOI":"10.1109\/CVPR.2019.00363"},{"key":"214_CR27","doi-asserted-by":"crossref","unstructured":"Wei, S. H.; Ramakrishna, V.; Kanade, T.; Sheikh, Y. Convolutional pose machines. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 4724\u20134732, 2016.","DOI":"10.1109\/CVPR.2016.511"},{"key":"214_CR28","doi-asserted-by":"publisher","unstructured":"Odena, A.; Dumoulin, V.; Olah, C. Deconvolution and checkerboard artifacts. Distill, 2016. Available at https:\/\/doi.org\/10.23915\/distill.","DOI":"10.23915\/distill"},{"key":"214_CR29","unstructured":"Gao, H.; Yuan, H.; Wang, Z.; Ji, S. Pixel deconvolutional networks. arXiv preprint arXiv:1705.06820, 2017."},{"key":"214_CR30","doi-asserted-by":"crossref","unstructured":"Wojna, Z.; Uijlings, J.; Guadarrama, S.; Silberman, N.; Chen, L. C.; Fathi, A.; Uijlings, J. The devil is in the decoder. In: Proceedings of the British Machine Vision Conference, 10.1\u201310.13, 2017.","DOI":"10.5244\/C.31.10"},{"key":"214_CR31","doi-asserted-by":"publisher","first-page":"e9","DOI":"10.1017\/ATSIP.2019.2","volume":"8","author":"Y Sugawara","year":"2019","unstructured":"Sugawara, Y.; Shiota, S.; Kiya, H. Checkerboard artifacts free convolutional neural networks. APSIPA Transactions on Signal and Information Processing Vol. 8, e9, 2019.","journal-title":"APSIPA Transactions on Signal and Information Processing"},{"key":"214_CR32","unstructured":"Tan, M. X.; Le, Q. V. EfficientNet: Rethinking model scaling for convolutional neural networks. arXiv preprint arXiv:1905.11946, 2019."},{"key":"214_CR33","unstructured":"Brock, A.; Lim, T.; Ritchie, J. M.; Weston, N. SMASH: One-shot model architecture search through HyperNetworks. In: Proceedings of the International Conference on Learning Representations, 2018."},{"key":"214_CR34","doi-asserted-by":"crossref","unstructured":"Dong, X. Y.; Yang, Y. Searching for a robust neural architecture in four GPU hours. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 1761\u20131770, 2019.","DOI":"10.1109\/CVPR.2019.00186"},{"key":"214_CR35","unstructured":"Xu, Y. H.; Xie, L. X.; Zhang, X. P.; Chen, X.; Xiong, H. K. PC-DARTS: Partial channel connections for memory-efficient differentiable architecture search. In: Proceedings of the International Conference on Learning Representations, 2019."},{"key":"214_CR36","doi-asserted-by":"crossref","unstructured":"Tan, M. X.; Chen, B.; Pang, R. M.; Vasudevan, V.; Sandler, M.; Howard, A.; Le, Q. V. MnasNet: Platform-aware neural architecture search for mobile. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2815\u20132823, 2019.","DOI":"10.1109\/CVPR.2019.00293"},{"key":"214_CR37","unstructured":"Gong, X. Y.; Chen, W. Y.; Jiang, Y. F.; Yuan, Y.; Wang, Z. Y. AutoPose: Searching multi-scale branch aggregation for pose estimation. arXiv preprint arXiv:2008.07018, 2020."},{"key":"214_CR38","doi-asserted-by":"crossref","unstructured":"Sandler, M.; Howard, A.; Zhu, M. L.; Zhmoginov, A.; Chen, L. C. MobileNetV2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 4510\u20134520, 2018.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"214_CR39","doi-asserted-by":"crossref","unstructured":"Fang, J. M.; Sun, Y. Z.; Zhang, Q.; Li, Y.; Wang, X. G. Densely connected search space for more flexible neural architecture search, In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 10625\u201310634, 2020.","DOI":"10.1109\/CVPR42600.2020.01064"},{"key":"214_CR40","doi-asserted-by":"crossref","unstructured":"Tang, W.; Yu, P.; Wu, Y. Deeply learned compositional models for human pose estimation. In: Computer Vision \u2014 ECCV 2018. Lecture Notes in Computer Science, Vol. 11207. Ferrari, V.; Hebert, M.; Sminchisescu, C.; Weiss, Y. Eds. Springer Cham, 197\u2013214, 2018.","DOI":"10.1007\/978-3-030-01219-9_12"},{"key":"214_CR41","unstructured":"Yang, S.; Yang, W. K.; Cui, Z. Pose neural fabrics search. arXiv preprint arXiv:1909.07068, 2019."},{"key":"214_CR42","unstructured":"Zhang, Z.; Tang, J.; Wu, G. Simple and lightweight human pose estimation. arXiv preprint arXiv:1911.10346, 2019."},{"key":"214_CR43","doi-asserted-by":"crossref","unstructured":"He, K. M.; Gkioxari, G.; Doll\u00e1r, P.; Girshick, R. Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, 2980\u20132988, 2017.","DOI":"10.1109\/ICCV.2017.322"},{"key":"214_CR44","doi-asserted-by":"crossref","unstructured":"Papandreou, G.; Zhu, T.; Kanazawa, N.; Toshev, A.; Tompson, J.; Bregler, C.; Murphy, K. Towards accurate multi-person pose estimation in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 3711\u20133719, 2017.","DOI":"10.1109\/CVPR.2017.395"},{"key":"214_CR45","doi-asserted-by":"crossref","unstructured":"Huang, S. L.; Gong, M. M.; Tao, D. C. A coarse-fine network for keypoint localization. In: Proceedings of the IEEE International Conference on Computer Vision, 3047\u20133056, 2017.","DOI":"10.1109\/ICCV.2017.329"},{"key":"214_CR46","doi-asserted-by":"crossref","unstructured":"Ottelander, T. D.; Dushatskiy, A.; Virgolin, M.; Bosman, P. A. N. Local search is a remarkably strong baseline for neural architecture search. arXiv preprint arXiv:2004.08996, 2020.","DOI":"10.1007\/978-3-030-72062-9_37"}],"container-title":["Computational Visual Media"],"original-title":[],"link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41095-021-0214-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s41095-021-0214-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41095-021-0214-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10750449\/10897488\/10897493.pdf?arnumber=10897493","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:38:34Z","timestamp":1762367914000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10897493\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9]]},"references-count":46,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1007\/s41095-021-0214-z","relation":{},"ISSN":["2096-0662","2096-0433"],"issn-type":[{"value":"2096-0662","type":"electronic"},{"value":"2096-0433","type":"print"}],"subject":[],"published":{"date-parts":[[2021,9]]},"assertion":[{"value":"11 December 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 February 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 April 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}