{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:16:01Z","timestamp":1765520161672,"version":"3.48.0"},"reference-count":35,"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\/iros60139.2025.11246615","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"2653-2660","source":"Crossref","is-referenced-by-count":0,"title":["J-ORA: A Framework and Multimodal Dataset for Japanese Object Identification, Reference, Action Prediction in Robot Perception"],"prefix":"10.1109","author":[{"given":"Jesse","family":"Atuhurra","sequence":"first","affiliation":[{"name":"NAIST,Division of Information Science,Nara,Japan"}]},{"given":"Hidetaka","family":"Kamigaito","sequence":"additional","affiliation":[{"name":"NAIST,Division of Information Science,Nara,Japan"}]},{"given":"Taro","family":"Watanabe","sequence":"additional","affiliation":[{"name":"NAIST,Division of Information Science,Nara,Japan"}]},{"given":"Koichiro","family":"Yoshino","sequence":"additional","affiliation":[{"name":"NAIST,Division of Information Science,Nara,Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801408"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00774"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01324"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.121"},{"key":"ref6","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"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN47096.2020.9223340"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1215"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981578"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206772"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20097"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.319"},{"key":"ref13","first-page":"558","article-title":"A gaze-grounded visual question answering dataset for clarifying ambiguous Japanese questions","volume-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)","author":"Inadumi"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2025.3590359\/mm1"},{"article-title":"A spoken language dataset of descriptions for speech-based grounded language learning","volume-title":"NeurIPS Datasets and Benchmarks","author":"Kebe","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.401"},{"article-title":"Clevr-dialog: A diagnostic dataset for multi-round reasoning in visual dialog","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":"Kottur","key":"ref17"},{"article-title":"Open-images: A public dataset for large-scale multi-label and multi-class image classification","year":"2017","author":"Krasin","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206594"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00298"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462970"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.124"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3295255"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6225042"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1081"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_6"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0695-z"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01282"},{"key":"ref30","first-page":"1918","article-title":"Visual question answering dataset for bilingual image understanding: A study of cross-lingual transfer using attention maps","volume-title":"Proceedings of the 27th International Conference on Computational Linguistics","author":"Shimizu"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801517"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5715\/jnlp.31.1107"},{"key":"ref34","article-title":"Caltech-ucsd birds-200-2011","volume-title":"California Institute of Technology, Tech. Rep. CNS-TR-2011-001","author":"Wah","year":"2011"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3651029"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11246615.pdf?arnumber=11246615","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:12:27Z","timestamp":1765519947000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246615\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246615","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}