{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T17:47:33Z","timestamp":1777398453563,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":63,"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":"the Fundamental Research Funds for the Central Universities","award":["JZ2024HGTG0309, JZ2024AHST0337, JZ2023YQTD0072, and 226-2022-00051"],"award-info":[{"award-number":["JZ2024HGTG0309, JZ2024AHST0337, JZ2023YQTD0072, and 226-2022-00051"]}]},{"name":"the Major Project of Anhui Province","award":["202203a05020011"],"award-info":[{"award-number":["202203a05020011"]}]},{"name":"the National Natural Science Foundation of China","award":["62272144,72188101,62020106007 and U20A20183"],"award-info":[{"award-number":["62272144,72188101,62020106007 and U20A20183"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680670","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"330-339","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Cluster-Phys: Facial Clues Clustering Towards Efficient Remote Physiological Measurement"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-9467-6296","authenticated-orcid":false,"given":"Wei","family":"Qian","sequence":"first","affiliation":[{"name":"School of Computer Science and Information Engineering, School of Artificial Intelligence, Hefei University of Technology, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5083-2145","authenticated-orcid":false,"given":"Kun","family":"Li","sequence":"additional","affiliation":[{"name":"CCAI, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2594-254X","authenticated-orcid":false,"given":"Dan","family":"Guo","sequence":"additional","affiliation":[{"name":"Hefei University of Technology & Institute of Artificial Intelligence (IAI), Hefei Comprehensive National Science Center, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3514-5413","authenticated-orcid":false,"given":"Bin","family":"Hu","sequence":"additional","affiliation":[{"name":"Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, Lanzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3094-7735","authenticated-orcid":false,"given":"Meng","family":"Wang","sequence":"additional","affiliation":[{"name":"Hefei University of Technology & Institute of Artificial Intelligence (IAI), Hefei Comprehensive National Science Center, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2017.10.017"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_22"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2013.2266196"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1088\/0967-3334\/35\/9\/1913"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2016.02.001"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00396"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3358415"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/BTAS.2017.8272721"},{"key":"e_1_3_2_1_9_1","volume-title":"rPPG-Based Heart Rate Estimation using Spatial-Temporal Attention Network","author":"Hu Min","year":"2021","unstructured":"Min Hu, Dong Guo, Mingxing Jiang, Fei Qian, Xiaohua Wang, and Fuji Ren. 2021. rPPG-Based Heart Rate Estimation using Spatial-Temporal Attention Network. IEEE Transactions on Cognitive and Developmental Systems (2021)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2020.3026481"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00244"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01300"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01606-8"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.415"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_24"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25217"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-022-3783-3"},{"key":"e_1_3_2_1_18_1","first-page":"1","article-title":"Transformerbased Visual Grounding with Cross-modality Interaction","volume":"19","author":"Li Kun","year":"2023","unstructured":"Kun Li, Jiaxiu Li, Dan Guo, Xun Yang, and Meng Wang. 2023. Transformerbased Visual Grounding with Cross-modality Interaction. ACM Transactions on Multimedia Computing, Communications and Applications 19, 6 (2023), 1--19.","journal-title":"ACM Transactions on Multimedia Computing, Communications and Applications"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01341"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00043"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.543"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01882"},{"key":"e_1_3_2_1_23_1","first-page":"19400","article-title":"Multi-task temporal shift attention networks for on-device contactless vitals measurement","volume":"33","author":"Liu Xin","year":"2020","unstructured":"Xin Liu, Josh Fromm, Shwetak Patel, and Daniel McDuff. 2020. Multi-task temporal shift attention networks for on-device contactless vitals measurement. In Advances in Neural Information Processing Systems, Vol. 33. 19400--19411.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00498"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2021.3124967"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01222"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01783"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8546321"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2947204"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_18"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2019.8756554"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00491"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2010.2086456"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1364\/OE.18.010762"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2024.3356713"},{"key":"e_1_3_2_1_36_1","volume-title":"Joint Spatial-Temporal Modeling and Contrastive Learning for Self-supervised Heart Rate Measurement. arXiv preprint arXiv:2406.04942","author":"Qian Wei","year":"2024","unstructured":"Wei Qian, Qi Li, Kun Li, Xinke Wang, Xiao Sun, Meng Wang, and Dan Guo. 2024. Joint Spatial-Temporal Modeling and Contrastive Learning for Self-supervised Heart Rate Measurement. arXiv preprint arXiv:2406.04942 (2024)."},{"key":"e_1_3_2_1_37_1","volume-title":"International Conference on Learning Representations. 1--14","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. In International Conference on Learning Representations. 1--14."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2021.3051176"},{"key":"e_1_3_2_1_39_1","volume-title":"New insights on super-high resolution for video-based heart rate estimation with a semi-blind source separation method. Computers in biology and medicine 116","author":"Song Rencheng","year":"2020","unstructured":"Rencheng Song, Senle Zhang, Juan Cheng, Chang Li, and Xun Chen. 2020. New insights on super-high resolution for video-based heart rate estimation with a semi-blind source separation method. Computers in biology and medicine 116 (2020), 103535."},{"key":"e_1_3_2_1_40_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 14464--14474","author":"Speth Jeremy","year":"2023","unstructured":"Jeremy Speth, Nathan Vance, Patrick Flynn, and Adam Czajka. 2023. Noncontrastive unsupervised learning of physiological signals from video. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 14464--14474."},{"key":"e_1_3_2_1_41_1","volume-title":"Proceedings of the British Machine Vision Conference. 3--6.","author":"Franc Vojtech","year":"2018","unstructured":"Vojtech Franc, and Jir\u00ed Matas. 2018. Visual heart rate estimation with convolutional neural network. In Proceedings of the British Machine Vision Conference. 3--6."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_29"},{"key":"e_1_3_2_1_43_1","volume-title":"Unsupervised and Weaklysupervised Video-based Remote Physiological Measurement via Spatiotemporal Contrast","author":"Sun Zhaodong","year":"2024","unstructured":"Zhaodong Sun and Xiaobai Li. 2024. Contrast-Phys+: Unsupervised and Weaklysupervised Video-based Remote Physiological Measurement via Spatiotemporal Contrast. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341105.3373905"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.263"},{"key":"e_1_3_2_1_46_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems. 5998--6008."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1364\/OE.16.021434"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28342"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2016.2609282"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAU.1967.1161901"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185561"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28435"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00551"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.22489\/CinC.2018.072"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3007086"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3089908"},{"key":"e_1_3_2_1_57_1","volume-title":"Proceedings of the British Machine Vision Conference. 1--12","author":"Yu Zitong","year":"2019","unstructured":"Zitong Yu, Xiaobai Li, and Guoying Zhao. 2019. Remote photoplethysmograph signal measurement from facial videos using spatio-temporal networks. In Proceedings of the British Machine Vision Conference. 1--12."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00024"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01758-1"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00415"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3298650"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223688"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02142-3"}],"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\/3664647.3680670","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680670","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:57Z","timestamp":1750295877000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680670"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":63,"alternative-id":["10.1145\/3664647.3680670","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680670","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"}}]}}