{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:24:51Z","timestamp":1766067891415,"version":"3.28.0"},"reference-count":27,"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\/iros55552.2023.10342467","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T19:17:55Z","timestamp":1702495075000},"page":"3228-3233","source":"Crossref","is-referenced-by-count":8,"title":["Semantic Scene Difference Detection in Daily Life Patroling by Mobile Robots Using Pre-Trained Large-Scale Vision-Language Model"],"prefix":"10.1109","author":[{"given":"Yoshiki","family":"Obinata","sequence":"first","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Tokyo,Japan,113\u20138656"}]},{"given":"Kento","family":"Kawaharazuka","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Tokyo,Japan,113\u20138656"}]},{"given":"Naoaki","family":"Kanazawa","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Tokyo,Japan,113\u20138656"}]},{"given":"Naoya","family":"Yamaguchi","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Tokyo,Japan,113\u20138656"}]},{"given":"Naoto","family":"Tsukamoto","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Tokyo,Japan,113\u20138656"}]},{"given":"Iori","family":"Yanokura","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Tokyo,Japan,113\u20138656"}]},{"given":"Shingo","family":"Kitagawa","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Tokyo,Japan,113\u20138656"}]},{"given":"Koki","family":"Shinjo","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Tokyo,Japan,113\u20138656"}]},{"given":"Kei","family":"Okada","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Tokyo,Japan,113\u20138656"}]},{"given":"Masayuki","family":"Inaba","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Tokyo,Japan,113\u20138656"}]}],"member":"263","reference":[{"key":"ref1","first-page":"15","article-title":"Bayesian netwcrks: A model cf self-activated memory for evidential reasoning","volume-title":"Proceedings of the 7th conference of the Cognitive Science Society, University of California, Irvine, CA, USA","author":"Pearl"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177699147"},{"key":"ref3","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref5","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","article-title":"Bert: Pretraining of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"Raffel","year":"2019","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref9","article-title":"Do as i can and not as i say: Grounding language in robotic affordances","author":"Ahn","year":"2022","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160390"},{"key":"ref11","article-title":"Robotic applications of pretrained vision-language models to various recognition behaviors","author":"Kawaharazuka","year":"2023","journal-title":"arXiv preprint"},{"key":"ref12","first-page":"53","article-title":"Neural modular control for embodied question answering","volume-title":"The 2nd Conference on Robot Learning","author":"Das"},{"key":"ref13","first-page":"492","article-title":"Lm-nav: Robotic navigation with large pretrained models of language, vision, and action","volume-title":"The 6th Conference on Robot Learning","author":"Shah"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref16","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref17","article-title":"Grounded language-image pretraining","author":"Li","year":"2022","journal-title":"CVPR"},{"key":"ref18","article-title":"Glipv2: Unifying localization and vision-language understanding","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref19","first-page":"23318","article-title":"Ofa: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"International Conference on Machine Learning","author":"Wang"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref21","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-021-03439-5"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20610"},{"volume-title":"sentence-transformers\/all-mpnet-base-v2","year":"2022","key":"ref24"},{"key":"ref25","first-page":"16857","article-title":"Mpnet: Masked and permuted pretraining for language understanding","volume":"33","author":"Song","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","first-page":"1","article-title":"Fetch and freight: Standard platforms for service robot applications","volume-title":"Workshop on autonomous mobile service robots","author":"Wise"},{"key":"ref27","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2023,10,1]]},"location":"Detroit, MI, USA","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\/10342467.pdf?arnumber=10342467","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T15:24:42Z","timestamp":1709220282000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10342467\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10342467","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}