{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T13:44:15Z","timestamp":1780494255743,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":21,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,11,25]],"date-time":"2022-11-25T00:00:00Z","timestamp":1669334400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,11,25]]},"DOI":"10.1145\/3577164.3577184","type":"proceedings-article","created":{"date-parts":[[2023,4,4]],"date-time":"2023-04-04T22:10:10Z","timestamp":1680646210000},"page":"128-134","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Attention-based Vision Transformer for Human Activity Classification using mmWave Radar"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3475-7813","authenticated-orcid":false,"given":"Zhaoyue","family":"Wang","sequence":"first","affiliation":[{"name":"School of Electronics and Communication Engineering, Guangzhou University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9883-7508","authenticated-orcid":false,"given":"Sha","family":"Huan","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Guangzhou University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0299-0864","authenticated-orcid":false,"given":"Limei","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Guangzhou University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1951-3714","authenticated-orcid":false,"given":"Qingyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Guangzhou University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0433-1926","authenticated-orcid":false,"given":"Jiajun","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Guangzhou University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0839-5898","authenticated-orcid":false,"given":"Zegui","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Guangzhou University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,4,4]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18178\/joig.9.2.55-60"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2018.2890128"},{"key":"e_1_3_2_1_3_1","first-page":"1","volume-title":"FMCW Radar-Based Anomaly Detection in Toilet by Supervised Machine Learning Classifier,\" 2019 IEEE Global Communications Conference (GLOBECOM)","author":"Takabatake W.","year":"2019","unstructured":"W. Takabatake, K. Yamamoto, K. Toyoda, T. Ohtsuki, Y. Shibata and A. Nagate, \"FMCW Radar-Based Anomaly Detection in Toilet by Supervised Machine Learning Classifier,\" 2019 IEEE Global Communications Conference (GLOBECOM), 2019, pp. 1-6."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2014.2370945"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3070138"},{"key":"e_1_3_2_1_6_1","volume-title":"Pattern Recognit.","volume":"102","author":"Zhang R.","year":"2020","unstructured":"R. Zhang , \"Multi-camera multi-player tracking with deep player identification in sports video\", Pattern Recognit., vol. 102, 2020."},{"key":"e_1_3_2_1_7_1","unstructured":"F. J. Abdu Y. Zhang and Z. Deng \"Activity Classification Based on Feature Fusion of FMCW Radar Human Motion Micro-Doppler Signatures \" in IEEE Sensors Journal."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/RADAR42522.2020.9114787"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2020.3006386"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2006.1603402"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2009.2012849"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1049\/iet-rsn.2013.0165"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2015.2491329"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2018.2806940"},{"key":"e_1_3_2_1_15_1","volume-title":"Two-stream convolution augmented transformer for human activity recognition[C]\/\/Proceedings of the AAAI Conference on Artificial Intelligence","year":"2021","unstructured":"Li B, Cui W, Wang W, Two-stream convolution augmented transformer for human activity recognition[C]\/\/Proceedings of the AAAI Conference on Artificial Intelligence. 2021, 35(1): 286-293."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2021.3118836.https:"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSENS.2018.2889060"},{"key":"e_1_3_2_1_18_1","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani A.","year":"2017","unstructured":"A. Vaswani , \"Attention is all you need\", Adv. Neural Inf. Process. Syst., pp. 5998-6008, 2017.","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"e_1_3_2_1_19_1","volume-title":"Transformers for Image Recognition at Scale","year":"2021","unstructured":"Kolesnikov, Alexander, \"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.\" (2021)."},{"key":"e_1_3_2_1_20_1","unstructured":"Smith Steven W. \"The scientist and engineer's guide to digital signal processing.\" (1997)."},{"key":"e_1_3_2_1_21_1","volume-title":"Scaling up capacity and resolution.\" Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","year":"2022","unstructured":"Liu, Ze, \"Swin transformer v2: Scaling up capacity and resolution.\" Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2022.."}],"event":{"name":"VSIP 2022: 2022 4th International Conference on Video, Signal and Image Processing","location":"Shanghai China","acronym":"VSIP 2022"},"container-title":["Proceedings of the 2022 4th International Conference on Video, Signal and Image Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3577164.3577184","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3577164.3577184","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:51:10Z","timestamp":1750182670000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3577164.3577184"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,25]]},"references-count":21,"alternative-id":["10.1145\/3577164.3577184","10.1145\/3577164"],"URL":"https:\/\/doi.org\/10.1145\/3577164.3577184","relation":{},"subject":[],"published":{"date-parts":[[2022,11,25]]},"assertion":[{"value":"2023-04-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}