{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T16:02:07Z","timestamp":1784131327507,"version":"3.55.0"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031159183","type":"print"},{"value":"9783031159190","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-15919-0_48","type":"book-chapter","created":{"date-parts":[[2022,9,6]],"date-time":"2022-09-06T04:04:59Z","timestamp":1662437099000},"page":"574-585","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["MLPPose: Human Keypoint Localization via\u00a0MLP-Mixer"],"prefix":"10.1007","author":[{"given":"Biao","family":"Guo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qian","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,9,7]]},"reference":[{"key":"48_CR1","unstructured":"Li, B., Dai, Y., Cheng, X., Chen, H., Lin, Y., He, M.: Skeleton based action recognition using translation-scale invariant image mapping and multi-scale deep CNN. In: ICMEW, pp 601\u2013604, July 2017"},{"key":"48_CR2","unstructured":"Li, B., Chen, H., Chen, Y., Dai, Y., He, M.: Skeleton based action recognition using translation-scale invariant image mapping and multi-scale deep CNN. In: ICMEW, pp. 613\u2013616, July 2017"},{"key":"48_CR3","doi-asserted-by":"crossref","unstructured":"Insafutdinov, E., et al.: Arttrack: articulated multi-person tracking in the wild. In: CVPR, pp. 6457\u20136465 (2017)","DOI":"10.1109\/CVPR.2017.142"},{"key":"48_CR4","doi-asserted-by":"crossref","unstructured":"Kulkarni, K.M., Shenoy, S.: Table Tennis stroke recognition using two-dimensional human pose estimation. In: CVPR, pp. 4576\u20134584 (2021)","DOI":"10.1109\/CVPRW53098.2021.00515"},{"key":"48_CR5","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: CVPR, pp. 5693\u20135703 (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"48_CR6","doi-asserted-by":"crossref","unstructured":"Papandreou, G., Zhu, T., Chen, L.C., Gidaris, S., Tompson, J., Murphy, K.: Personlab: person pose estimation and instance segmentation with a bottom-up, part-based, geometric embedding model. In: ECCV, pp 269\u2013286 (2018)","DOI":"10.1007\/978-3-030-01264-9_17"},{"key":"48_CR7","doi-asserted-by":"crossref","unstructured":"Graves, A., et al.: Hybrid computing using a neural network with dynamic external memory. In: Nature, pp. 471\u2013476 (2016)","DOI":"10.1038\/nature20101"},{"key":"48_CR8","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS, pp. 5998\u20136008 (2017)"},{"key":"48_CR9","unstructured":"Dosovitskiy, A., et al.: An image is worth $$16\\times 16$$ words: transformers for image recognition at scale. In: ICLR (2020)"},{"key":"48_CR10","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: ECCV, pp. 213\u2013229, August 2020","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"48_CR11","doi-asserted-by":"crossref","unstructured":"Yu, W., et al.: MetaFormer is actually what you need for vision. arXiv preprint arXiv:2111.11418 (2021)","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"48_CR12","unstructured":"Tolstikhin, I.O., et al.: MLP-mixer: an all-MLP architecture for vision. In: NeurIPS (2017)"},{"key":"48_CR13","doi-asserted-by":"crossref","unstructured":"Wu, H., et al.: CVT: introducing convolutions to vision transformers. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"48_CR14","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., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: 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). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"48_CR15","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: CVPR, pp. 3686\u20133693 (2014)","DOI":"10.1109\/CVPR.2014.471"},{"key":"48_CR16","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). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_29"},{"key":"48_CR17","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, Z., Peng, Y., Zhang, Z., Yu, G., Sun, J.: Cascaded pyramid network for multi-person pose estimation. In: CVPR, pp. 7103\u20137112 (2018)","DOI":"10.1109\/CVPR.2018.00742"},{"key":"48_CR18","doi-asserted-by":"crossref","unstructured":"Xiao, B., Wu, H., Wei, Y.: Simple baselines for human pose estimation and tracking. In: ECCV, pp 466\u2013481 (2018)","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"48_CR19","doi-asserted-by":"crossref","unstructured":"Zheng, S., et al.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: CVPR, pp. 6881\u20136890 (2021)","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"48_CR20","doi-asserted-by":"crossref","unstructured":"Yang, S., Quan, Z., Nie, M., Yang, W.: Transpose: keypoint localization via transformer. In: ICCV, pp. 11802\u201311812 (2021)","DOI":"10.1109\/ICCV48922.2021.01159"},{"key":"48_CR21","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: TokenPose: learning keypoint tokens for human pose estimation. arXiv preprint arXiv:2104.03516 (2021)","DOI":"10.1109\/ICCV48922.2021.01112"},{"key":"48_CR22","unstructured":"Lian, D., Yu, Z., Sun, X., Gao, S.: AS-MLP: an axial shifted MLP architecture for vision. arXiv preprint arXiv:2107.08391 (2021)"},{"key":"48_CR23","unstructured":"Hendrycks, D., Gimpel, K.: Gaussian error linear units (GELUs). arXiv preprint arXiv:1606.08415 (2016)"},{"key":"48_CR24","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"48_CR25","doi-asserted-by":"crossref","unstructured":"Cheng, B., Xiao, B., Wang, J., Shi, H., Huang, T. S., Zhang, L.: Higherhrnet: scale-aware representation learning for bottom-up human pose estimation. In: CVPR, pp. 5386\u20135395 (2020)","DOI":"10.1109\/CVPR42600.2020.00543"},{"key":"48_CR26","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., Fan, D.P., Song, K., Liang, D., Shao, L.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: ICCV, pp. 568\u2013578 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"48_CR27","doi-asserted-by":"crossref","unstructured":"Yue, X., et al.: Vision transformer with progressive sampling. In: ICCV, pp. 387\u2013396 (2021)","DOI":"10.1109\/ICCV48922.2021.00044"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-15919-0_48","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,29]],"date-time":"2023-03-29T08:24:12Z","timestamp":1680078252000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-15919-0_48"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031159183","9783031159190"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-15919-0_48","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"7 September 2022","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":"Bristol","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2022\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"561","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"255","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"45% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}