{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T03:23:20Z","timestamp":1783567400640,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","funder":[{"name":"The Pioneer Centre for AI","award":["DNRF grant number P1"],"award-info":[{"award-number":["DNRF grant number P1"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755857","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:38:54Z","timestamp":1761377934000},"page":"9026-9034","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["MoCount: Motion-Based Repetitive Action Counting"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7583-3501","authenticated-orcid":false,"given":"Ruocheng","family":"Gu","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Jilin University, Changchun, Jilin, China and VitaSight, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8570-2172","authenticated-orcid":false,"given":"Sen","family":"Jia","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Washington, Seattle, WA, USA and VitaSight, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0637-8959","authenticated-orcid":false,"given":"Yule","family":"Ma","sequence":"additional","affiliation":[{"name":"Anhui Normal University, Wuhu, Anhui, China and VitaSight, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5037-6052","authenticated-orcid":false,"given":"Jinqin","family":"Zhong","sequence":"additional","affiliation":[{"name":"Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8877-2421","authenticated-orcid":false,"given":"Jenq-Neng","family":"Hwang","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2929-0828","authenticated-orcid":false,"given":"Lei","family":"Li","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, WA, USA and VitaSight, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.promfg.2020.01.288"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"e_1_3_2_1_3_1","first-page":"4","article-title":"Is space-time attention all you need for video understanding?","volume":"2","author":"Bertasius Gedas","year":"2021","unstructured":"Gedas Bertasius, Heng Wang, and Lorenzo Torresani. 2021. Is space-time attention all you need for video understanding?. In ICML, Vol. 2. 4.","journal-title":"ICML"},{"key":"e_1_3_2_1_4_1","first-page":"536","article-title":"On the theory of filter amplifiers","volume":"7","author":"Stephen Butterworth","year":"1930","unstructured":"Stephen Butterworth et al., 1930. On the theory of filter amplifiers. Wireless Engineer, Vol. 7, 6 (1930), 536-541.","journal-title":"Wireless Engineer"},{"key":"e_1_3_2_1_5_1","volume-title":"The role of deductive and inductive reasoning in large language models. arXiv preprint arXiv:2410.02892","author":"Cai Chengkun","year":"2024","unstructured":"Chengkun Cai, Xu Zhao, Haoliang Liu, Zhongyu Jiang, Tianfang Zhang, Zongkai Wu, Jenq-Neng Hwang, Serge Belongie, and Lei Li. 2024. The role of deductive and inductive reasoning in large language models. arXiv preprint arXiv:2410.02892 (2024)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2013.01.013"},{"key":"e_1_3_2_1_7_1","unstructured":"MMPose Contributors. 2020. Openmmlab pose estimation toolbox and benchmark."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.868681"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01040"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"e_1_3_2_1_11_1","volume-title":"Long short-term memory. Neural computation","author":"Hochreiter Sepp","year":"1997","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long short-term memory. Neural computation, Vol. 9, 8 (1997), 1735-1780."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01843"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.113"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00057"},{"key":"e_1_3_2_1_15_1","volume-title":"Human Motion Instruction Tuning. arXiv preprint arXiv:2411.16805","author":"Li Lei","year":"2024","unstructured":"Lei Li, Sen Jia, Wang Jianhao, Zhongyu Jiang, Feng Zhou, Ju Dai, Tianfang Zhang, Wu Zongkai, and Jenq-Neng Hwang. 2024. Human Motion Instruction Tuning. arXiv preprint arXiv:2411.16805 (2024)."},{"key":"e_1_3_2_1_16_1","volume-title":"Chatmotion: A multimodal multi-agent for human motion analysis. arXiv preprint arXiv:2502.18180","author":"Li Lei","year":"2025","unstructured":"Lei Li, Sen Jia, Jianhao Wang, Zhaochong An, Jiaang Li, Jenq-Neng Hwang, and Serge Belongie. 2025. Chatmotion: A multimodal multi-agent for human motion analysis. arXiv preprint arXiv:2502.18180 (2025)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2023.08.003"},{"key":"e_1_3_2_1_18_1","volume-title":"Asian conference on computer vision. Springer, 332-347","author":"Li Sijin","year":"2014","unstructured":"Sijin Li and Antoni B Chan. 2014. 3d human pose estimation from monocular images with deep convolutional neural network. In Asian conference on computer vision. Springer, 332-347."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00637"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01112"},{"key":"e_1_3_2_1_21_1","volume-title":"Graph canvas for controllable 3d scene generation. arXiv preprint arXiv:2412.00091","author":"Liu Libin","year":"2024","unstructured":"Libin Liu, Shen Chen, Sen Jia, Jingzhe Shi, Zhongyu Jiang, Can Jin, Wu Zongkai, Jenq-Neng Hwang, and Lei Li. 2024. Graph canvas for controllable 3d scene generation. arXiv preprint arXiv:2412.00091 (2024)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.288"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073596"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534970"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00794"},{"key":"e_1_3_2_1_27_1","first-page":"83314","article-title":"Scaling law for time series forecasting","volume":"37","author":"Shi Jingzhe","year":"2024","unstructured":"Jingzhe Shi, Qinwei Ma, Huan Ma, and Lei Li. 2024. Scaling law for time series forecasting. Advances in Neural Information Processing Systems, Vol. 37 (2024), 83314-83344.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the Asian Conference on Computer Vision. 3056-3073","author":"Sinha Saptarshi","year":"2024","unstructured":"Saptarshi Sinha, Alexandros Stergiou, and Dima Damen. 2024. Every shot counts: Using exemplars for repetition counting in videos. In Proceedings of the Asian Conference on Computer Vision. 3056-3073."},{"key":"e_1_3_2_1_29_1","volume-title":"Amir Roshan Zamir, and Mubarak Shah","author":"Soomro Khurram","year":"2012","unstructured":"Khurram Soomro, Amir Roshan Zamir, and Mubarak Shah. 2012. UCF101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_33"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.214"},{"key":"e_1_3_2_1_32_1","first-page":"959","article-title":"The function space of an activity. In 2006 IEEE computer society conference on computer vision and pattern recognition (CVPR'06), Vol. 1","author":"Veeraraghavan Ashok","year":"2006","unstructured":"Ashok Veeraraghavan, Rama Chellappa, and Amit K Roy-Chowdhury. 2006. The function space of an activity. In 2006 IEEE computer society conference on computer vision and pattern recognition (CVPR'06), Vol. 1. IEEE, 959-968.","journal-title":"IEEE"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2015.00028"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CBMI.2015.7153605"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"e_1_3_2_1_36_1","volume-title":"Poserac: Pose saliency transformer for repetitive action counting. arXiv preprint arXiv:2303.08450","author":"Yao Ziyu","year":"2023","unstructured":"Ziyu Yao, Xuxin Cheng, and Yuexian Zou. 2023. Poserac: Pose saliency transformer for repetitive action counting. arXiv preprint arXiv:2303.08450 (2023)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00075"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01145"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755857","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:15:34Z","timestamp":1765340134000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755857"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":38,"alternative-id":["10.1145\/3746027.3755857","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755857","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}