{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T16:37:56Z","timestamp":1783096676746,"version":"3.54.6"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,7,23]],"date-time":"2023-07-23T00:00:00Z","timestamp":1690070400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,23]],"date-time":"2023-07-23T00:00:00Z","timestamp":1690070400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100020950","name":"National Science and Technology Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020950","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,7,23]]},"DOI":"10.23919\/mva57639.2023.10215538","type":"proceedings-article","created":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T17:35:01Z","timestamp":1692725701000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["ViTVO: Vision Transformer based Visual Odometry with Attention Supervision"],"prefix":"10.23919","author":[{"given":"Chu-Chi","family":"Chiu","sequence":"first","affiliation":[{"name":"National Tsing Hua University,Elsa Lab,Department of Computer Science,Hsinchu,Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hsuan-Kung","family":"Yang","sequence":"additional","affiliation":[{"name":"National Tsing Hua University,Elsa Lab,Department of Computer Science,Hsinchu,Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao-Wei","family":"Chen","sequence":"additional","affiliation":[{"name":"National Tsing Hua University,Elsa Lab,Department of Computer Science,Hsinchu,Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Wen","family":"Chen","sequence":"additional","affiliation":[{"name":"National Tsing Hua University,Elsa Lab,Department of Computer Science,Hsinchu,Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chun-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"National Tsing Hua University,Elsa Lab,Department of Computer Science,Hsinchu,Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Exploring self-attention for visual odometry","author":"Damirchi","year":"2020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00924"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340890"},{"key":"ref4","article-title":"Instance-wise depth and motion learning from monocular videos","author":"Lee","year":"2019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10161306"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20876-9_19"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i06.6608"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-05545-8"},{"key":"ref9","first-page":"422","article-title":"Transformer-based deep monocular visual odometry for edge devices","volume-title":"Proc. the 31st FRUCT Conf.","author":"Klochkov"},{"key":"ref10","article-title":"An empirical evaluation of sequence-based deep learning architectures for visual odometry","author":"Parisotto","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981835"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICPICS55264.2022.9873538"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00255"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33783-3_44"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.09.029"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3144958"},{"key":"ref17","article-title":"TartanVO: A generalizable learning-based vo","volume-title":"Proc. Conf. on Robot Learning (CoRL)","author":"Wang"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00061"},{"key":"ref19","article-title":"Attention is all you need","volume-title":"Proc. Conf. on Neural Information Processing Systems (NeurIPS)","author":"Vaswani"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00212"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/123"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.74"}],"event":{"name":"2023 18th International Conference on Machine Vision and Applications (MVA)","location":"Hamamatsu, Japan","start":{"date-parts":[[2023,7,23]]},"end":{"date-parts":[[2023,7,25]]}},"container-title":["2023 18th International Conference on Machine Vision and Applications (MVA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10215492\/10215533\/10215538.pdf?arnumber=10215538","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T18:58:53Z","timestamp":1709319533000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10215538\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,23]]},"references-count":22,"URL":"https:\/\/doi.org\/10.23919\/mva57639.2023.10215538","relation":{},"subject":[],"published":{"date-parts":[[2023,7,23]]}}}