{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,27]],"date-time":"2024-12-27T05:16:50Z","timestamp":1735276610213,"version":"3.32.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"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":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10801314","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"10013-10019","source":"Crossref","is-referenced-by-count":0,"title":["Map-based Modular Approach for Zero-shot Embodied Question Answering"],"prefix":"10.1109","author":[{"given":"Koya","family":"Sakamoto","sequence":"first","affiliation":[{"name":"Kyoto University,Graduate School of Informatics,Japan"}]},{"given":"Daichi","family":"Azuma","sequence":"additional","affiliation":[{"name":"Sony Semiconductor Solutions"}]},{"given":"Taiki","family":"Miyanishi","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}]},{"given":"Shuhei","family":"Kurita","sequence":"additional","affiliation":[{"name":"National Institute of Informatics,Tokyo,Japan"}]},{"given":"Motoaki","family":"Kawanabe","sequence":"additional","affiliation":[{"name":"Advanced Telecommunications Research Institute International (ATR),Kyoto,Japan"}]}],"member":"263","reference":[{"article-title":"Sim-to-real transfer for vision-and-language navigation","volume-title":"CoRL","author":"Anderson","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.073"},{"article-title":"Object goal navigation using goal-oriented semantic exploration","volume-title":"NeurIPS","author":"Chaplot","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341827"},{"article-title":"History aware multimodal transformer for vision-and-language navigation","volume-title":"NeurIPS","author":"Chen","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00008"},{"journal-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models","year":"2023","author":"Fu","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02219"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adf6991"},{"article-title":"3d-llm: Injecting the 3d world into large language models","volume-title":"NeurIPS","author":"Hong","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160390"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1086"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"article-title":"Generative language-grounded policy in vision-and-language navigation with bayes\u2019 rule","volume-title":"ICLR","author":"Kurita","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01396"},{"article-title":"BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"ICML","author":"Li","key":"ref20"},{"article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"ICML","author":"Li","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"article-title":"Visual instruction tuning","volume-title":"NeurIPS","author":"Liu","key":"ref23"},{"article-title":"Zson: Zero-shot object-goal navigation using multimodal goal embeddings","volume-title":"NeurIPS","author":"Majumdar","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"journal-title":"Habitat 3.0: A co-habitat for humans, avatars and robots","year":"2023","author":"Puig","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"journal-title":"Learning transferable visual models from natural language supervision","year":"2021","author":"Radford","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01832"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"article-title":"Embodied referring expression for manipulation question answering in interactive environment","year":"2022","author":"Sima","key":"ref32"},{"article-title":"Habitat 2.0: Training home assistants to rearrange their habitat","volume-title":"NeurIPS","author":"Szot","key":"ref33"},{"journal-title":"Knowledge-based embodied question answering","year":"2021","author":"Tan","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00682"},{"journal-title":"Building generalizable agents with a realistic and rich 3d environment","year":"2018","author":"Wu","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/280765.280773"},{"journal-title":"3d question answering","year":"2022","author":"Ye","key":"ref38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00647"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2024,10,14]]},"location":"Abu Dhabi, United Arab Emirates","end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10801314.pdf?arnumber=10801314","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:27:52Z","timestamp":1735198072000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10801314\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10801314","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}