{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:15:24Z","timestamp":1777889724214,"version":"3.51.4"},"reference-count":70,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02526","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"27209-27219","source":"Crossref","is-referenced-by-count":0,"title":["Egocentric Action-Aware Inertial Localization in Point Clouds with Vision-Language Guidance"],"prefix":"10.1109","author":[{"given":"Mingfang","family":"Zhang","sequence":"first","affiliation":[{"name":"The University of Tokyo"}]},{"given":"Ryo","family":"Yonetani","sequence":"additional","affiliation":[{"name":"CyberAgent AI Lab"}]},{"given":"Yifei","family":"Huang","sequence":"additional","affiliation":[{"name":"The University of Tokyo"}]},{"given":"Liangyang","family":"Ouyang","sequence":"additional","affiliation":[{"name":"The University of Tokyo"}]},{"given":"Ruicong","family":"Liu","sequence":"additional","affiliation":[{"name":"The University of Tokyo"}]},{"given":"Yoichi","family":"Sato","sequence":"additional","affiliation":[{"name":"The University of Tokyo"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Scaniverse","year":"2025"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02209"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2493432.2493449"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12102"},{"key":"ref5","article-title":"Oxiod: The dataset for deep inertial odometry","author":"Chen","year":"2018","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02573"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref8","first-page":"720","article-title":"Scaling egocentric vision: The epic-kitchens dataset","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Damen","year":"2018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01377"},{"key":"ref10","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Un-locking exocentric video-language data for egocentric video representation learning","author":"Dou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Project aria: A new tool for egocentric multi-modal ai research","author":"Engel","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IPIN.2012.6418932"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1109\/IPIN54987.2022.9918108","article-title":"Positioning method of pedestrian dead reckoning based on human activity recognition","volume-title":"IPIN","author":"Zhang","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00536"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00627"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01834"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610243"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196860"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561115"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00649"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02084"},{"key":"ref26","article-title":"Vinci: A real-time embodied smart assistant based on egocentric vision-language model","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01723"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.336"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3130605"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21831"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914554813"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3390\/s151024862"},{"key":"ref33","article-title":"Egocentric video-language pretraining","author":"Qinghong Lin","year":"2022","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Simhand: Mining similar hands for large-scale 3d hand pose pretraining","author":"Lin","year":"2025","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Egohdm: An online egocentric-inertial human motion capture, localization, and dense mapping system","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00071"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3007421"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01643"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref40","first-page":"1610","article-title":"Ovir-3d: Open-vocabulary 3d instance retrieval without training on 3d data","volume-title":"Conference on Robot Learning","author":"Lu","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.883"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/robot.2007.364024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3390\/s16010115"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3390\/app11167259"},{"key":"ref46","article-title":"Modeling fine-grained hand-object dynamics for egocentric video representation learning","volume-title":"International Conference on Learning Representations","author":"Pei","year":"2025"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00487"},{"key":"ref48","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","author":"Ruizhongtai Qi","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2018.2853729"},{"key":"ref50","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_40"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01375"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/2789168.2790099"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i7.16763"},{"key":"ref55","article-title":"Openmask3d: Open-vocabulary 3d instance segmentation","author":"Takmaz","year":"2023","journal-title":"arXiv preprint"},{"key":"ref56","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"International Conference on Machine Learning","author":"Tan","year":"2019"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1049\/PBRA017E"},{"key":"ref59","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems, 30"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01284"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_38"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3592099"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-70994-7_14"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3675095.3676623"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2024.3381717"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01278"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01603"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_18"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00637"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445465.pdf?arnumber=11445465","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:17:52Z","timestamp":1777612672000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445465\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02526","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}