{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T22:48:27Z","timestamp":1772837307213,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62332019"],"award-info":[{"award-number":["62332019"]}]},{"name":"Distinguished Young Scholars Funding of Dalian","award":["2022RJ01"],"award-info":[{"award-number":["2022RJ01"]}]},{"name":"Ningbo Major Research and Development Plan Project of China","award":["2023Z225"],"award-info":[{"award-number":["2023Z225"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022ZD0210500"],"award-info":[{"award-number":["2022ZD0210500"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681401","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"2833-2841","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Adaptive Vision Transformer for Event-Based Human Pose Estimation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1049-6317","authenticated-orcid":false,"given":"Nannan","family":"Yu","sequence":"first","affiliation":[{"name":"Dalian University of Technology, Dalian, Liaoning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1736-6863","authenticated-orcid":false,"given":"Tao","family":"Ma","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, Liaoning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0061-5465","authenticated-orcid":false,"given":"Jiqing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Dalian Martime University, Dalian, Liaoning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5402-7503","authenticated-orcid":false,"given":"Yuji","family":"Zhang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, Liaoning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3790-3046","authenticated-orcid":false,"given":"Qirui","family":"Bao","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, Liaoning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8497-611X","authenticated-orcid":false,"given":"Xiaopeng","family":"Wei","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, Liaoning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8046-722X","authenticated-orcid":false,"given":"Xin","family":"Yang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, Liaoning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Event-based visual flow","author":"Benosman Ryad","year":"2013","unstructured":"Ryad Benosman, Charles Clercq, Xavier Lagorce, Sio-Hoi Ieng, and Chiara Bartolozzi. 2013. Event-based visual flow. IEEE transactions on neural networks and learning systems, Vol. 25, 2 (2013), 407--417."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00217"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00742"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00543"},{"key":"e_1_3_2_1_6_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Chen et al. 2022. Efficient human pose estimation via 3d event point cloud. In 3DV.","DOI":"10.1109\/3DV57658.2022.00023"},{"key":"e_1_3_2_1_8_1","unstructured":"Liang et al. 2022. Not all patches are what you need: Expediting vision transformers via token reorganizations. In ICLR."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3326683"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3300741"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00030"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01334"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-019-8266-2"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01112"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00198"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01112"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Qianhui Liu Dong Xing Huajin Tang De Ma and Gang Pan. 2021. Event-based Action Recognition Using Motion Information and Spiking Neural Networks.. In IJCAI. 1743--1749.","DOI":"10.24963\/ijcai.2021\/240"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593805"},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 652--660","author":"Qi Charles R","year":"2017","unstructured":"Charles R Qi, Hao Su, Kaichun Mo, and Leonidas J Guibas. 2017. Pointnet: Deep learning on point sets for 3d classification and segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition. 652--660."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01216"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00150"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.110048"},{"key":"e_1_3_2_1_23_1","volume-title":"Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research","author":"Srivastava Nitish","year":"2014","unstructured":"Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. 2014. Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research, Vol. 15, 1 (2014), 1929--1958."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-023-00020-z"},{"key":"e_1_3_2_1_25_1","volume-title":"International conference on machine learning. PMLR, 10347--10357","author":"Touvron Hugo","year":"2021","unstructured":"Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Herv\u00e9 J\u00e9gou. 2021. Training data-efficient image transformers & distillation through attention. In International conference on machine learning. PMLR, 10347--10357."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3220938"},{"key":"e_1_3_2_1_27_1","volume-title":"Dynamic graph cnn for learning on point clouds. ACM Transactions on Graphics (tog)","author":"Wang Yue","year":"2019","unstructured":"Yue Wang, Yongbin Sun, Ziwei Liu, Sanjay E Sarma, Michael M Bronstein, and Justin M Solomon. 2019. Dynamic graph cnn for learning on point clouds. ACM Transactions on Graphics (tog), Vol. 38, 5 (2019), 1--12."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"e_1_3_2_1_29_1","first-page":"38571","article-title":"Vitpose: Simple vision transformer baselines for human pose estimation","volume":"35","author":"Xu Yufei","year":"2022","unstructured":"Yufei Xu, Jing Zhang, Qiming Zhang, and Dacheng Tao. 2022. Vitpose: Simple vision transformer baselines for human pose estimation. Advances in Neural Information Processing Systems, Vol. 35 (2022), 38571--38584.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01159"},{"key":"e_1_3_2_1_31_1","volume-title":"Hrformer: High-resolution transformer for dense prediction. arXiv preprint arXiv:2110.09408","author":"Yuan Yuhui","year":"2021","unstructured":"Yuhui Yuan, Rao Fu, Lang Huang, Weihong Lin, Chao Zhang, Xilin Chen, and Jingdong Wang. 2021. Hrformer: High-resolution transformer for dense prediction. arXiv preprint arXiv:2110.09408 (2021)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01959-8"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00860"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00943"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1999.791289"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01081"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681401","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681401","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:46Z","timestamp":1750294666000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681401"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":36,"alternative-id":["10.1145\/3664647.3681401","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681401","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}