{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T07:54:11Z","timestamp":1768031651749,"version":"3.49.0"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,1]]},"DOI":"10.1109\/iros55552.2023.10342417","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T19:17:55Z","timestamp":1702495075000},"page":"9846-9852","source":"Crossref","is-referenced-by-count":4,"title":["MoEmo Vision Transformer: Integrating Cross-Attention and Movement Vectors in 3D Pose Estimation for HRI Emotion Detection"],"prefix":"10.1109","author":[{"given":"David C.","family":"Jeong","sequence":"first","affiliation":[{"name":"Santa Clara University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianma","family":"Shen","sequence":"additional","affiliation":[{"name":"Santa Clara University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongji","family":"Liu","sequence":"additional","affiliation":[{"name":"Santa Clara University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raghav","family":"Kapoor","sequence":"additional","affiliation":[{"name":"Santa Clara University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Casey","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Santa Clara University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Song","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, ShanghaiTech University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christopher A.","family":"Kitts","sequence":"additional","affiliation":[{"name":"Santa Clara University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-017-9677-2"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jamda.2010.10.002"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364909102796"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02026"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.173"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2929257"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2006.2004"},{"key":"ref9","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Internatl Conference on Learning Representations","author":"Dosovitskiy","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1111\/j.1460-2466.1972.tb00163.x"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3222784"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2930434"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00403"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00403"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.5220\/0010359506690679"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00576"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00259"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.212"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2916866"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00339"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01215-y"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594385"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1080\/1047840X.2019.1693866"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1957656.1957786"},{"key":"ref27","article-title":"Expression of emotion and intention by robot body movement","volume-title":"Proceedings of the 5th Internatl Conf. on autonomous systems","author":"Nakata","year":"1998"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICIEV.2019.8858536"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.5772\/50228"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248052"},{"key":"ref31","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Internatl Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1037\/a0037250"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-40621-3_35"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_27"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_27"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3371382.3377432"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2009.5354145"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00464"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1167\/13.12.7"},{"key":"ref41","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593974"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0113647"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00926"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3193749"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00791"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351062"},{"key":"ref48","article-title":"Auto-conditioned recurrent networks for extended complex human motion synthesis","volume-title":"Internatl Conference on Learning Representations","author":"Zhou","year":"2018"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Detroit, MI, USA","start":{"date-parts":[[2023,10,1]]},"end":{"date-parts":[[2023,10,5]]}},"container-title":["2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10341341\/10341342\/10342417.pdf?arnumber=10342417","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T01:16:58Z","timestamp":1705022218000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10342417\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10342417","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}