{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:28:26Z","timestamp":1766068106768,"version":"3.29.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,8,26]],"date-time":"2024-08-26T00:00:00Z","timestamp":1724630400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,26]],"date-time":"2024-08-26T00:00:00Z","timestamp":1724630400000},"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":[[2024,8,26]]},"DOI":"10.1109\/ro-man60168.2024.10731184","type":"proceedings-article","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T17:45:45Z","timestamp":1730310345000},"page":"1720-1725","source":"Crossref","is-referenced-by-count":1,"title":["Learning Anomaly Detection Models for Human-Robot Interaction"],"prefix":"10.1109","author":[{"given":"Shota","family":"Mochizuki","sequence":"first","affiliation":[{"name":"Nagoya University,Graduate School of Informatics,Japan"}]},{"given":"Sanae","family":"Yamashita","sequence":"additional","affiliation":[{"name":"Nagoya University,Graduate School of Informatics,Japan"}]},{"given":"Reiko","family":"Yuasa","sequence":"additional","affiliation":[{"name":"Nagoya University,School of Informatics,Japan"}]},{"given":"Tomonori","family":"Kubota","sequence":"additional","affiliation":[{"name":"Nagoya University,Graduate School of Engineering,Japan"}]},{"given":"Kohei","family":"Ogawa","sequence":"additional","affiliation":[{"name":"Nagoya University,Graduate School of Engineering,Japan"}]},{"given":"Ryuichiro","family":"Higashinaka","sequence":"additional","affiliation":[{"name":"Nagoya University,Graduate School of Informatics,Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.birob.2023.100131"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21236\/ada459168"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.sigdial-1.10"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCA.2011.2164243"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2021.1928549"},{"key":"ref6","first-page":"107","article-title":"Simultaneous job interview system using multiple semiautonomous agents","volume-title":"Proc. SIGDIAL","author":"Kawai"},{"key":"ref7","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Devlin"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-9323-9_38"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-9323-9_39"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/GCCE56475.2022.10014052"},{"article-title":"The kinetics human action video dataset","year":"2017","author":"Kay","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref13","first-page":"10078","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume-title":"Proc. NeurIPS","volume":"35","author":"Tong"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00678"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00684"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3623809.3623863"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/sym11091066"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"article-title":"YouTube-8M: A large-scale video classification benchmark","year":"2016","author":"Abu-El-Haija","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413869"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.33540\/2168"},{"issue":"11","key":"ref23","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref24","first-page":"38571","article-title":"ViTPose: Simple vision transformer baselines for human pose estimation","volume-title":"Proc. NeurIPS","author":"Xu"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"}],"event":{"name":"2024 33rd IEEE International Conference on Robot and Human Interactive Communication (ROMAN)","start":{"date-parts":[[2024,8,26]]},"location":"Pasadena, CA, USA","end":{"date-parts":[[2024,8,30]]}},"container-title":["2024 33rd IEEE International Conference on Robot and Human Interactive Communication (ROMAN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10731142\/10731137\/10731184.pdf?arnumber=10731184","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T04:02:51Z","timestamp":1732680171000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10731184\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,26]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/ro-man60168.2024.10731184","relation":{},"subject":[],"published":{"date-parts":[[2024,8,26]]}}}