{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:40:18Z","timestamp":1735198818467,"version":"3.32.0"},"reference-count":58,"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\/iros58592.2024.10802596","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"9549-9556","source":"Crossref","is-referenced-by-count":0,"title":["Object Segmentation from Open-Vocabulary Manipulation Instructions Based on Optimal Transport Polygon Matching with Multimodal Foundation Models"],"prefix":"10.1109","author":[{"given":"Takayuki","family":"Nishimura","sequence":"first","affiliation":[{"name":"Keio University,Kanagawa,Japan,223-8522"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Katsuyuki","family":"Kuyo","sequence":"additional","affiliation":[{"name":"Keio University,Kanagawa,Japan,223-8522"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Motonari","family":"Kambara","sequence":"additional","affiliation":[{"name":"Keio University,Kanagawa,Japan,223-8522"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Komei","family":"Sugiura","sequence":"additional","affiliation":[{"name":"Keio University,Kanagawa,Japan,223-8522"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/iros55552.2023.10341402"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00856"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00039"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01789"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.07.009"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1369-5"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.524"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3413013"},{"article-title":"GPT-4 Technical Report","year":"2023","author":"Achiam","key":"ref14"},{"key":"ref15","article-title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","author":"Dai","year":"2023","journal-title":"NeurIPS"},{"article-title":"PaLM-E: An Embodied Multimodal Language Model","volume-title":"ICML","author":"Driess","key":"ref16"},{"key":"ref17","first-page":"287","article-title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","volume-title":"CoRL","author":"Brohan"},{"key":"ref18","first-page":"20","article-title":"ChatGPT for Robotics: Design Principles and Model Abilities","volume":"2","author":"Vemprala","year":"2023","journal-title":"Microsoft Auton. Syst. Robot. Res"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref20","article-title":"Survey on Multimodal Transformers for Robots","author":"Miyazawa","year":"2023","journal-title":"Authorea Preprints"},{"article-title":"Robot Learning in the Era of Foundation Models: A Survey","year":"2023","author":"Xiao","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2024.2408593"},{"article-title":"Large Language Models for Robotics: A Survey","year":"2023","author":"Zeng","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01471"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01050"},{"key":"ref31","article-title":"Segment Everything Everywhere All at Once","author":"Zou","year":"2023","journal-title":"NeurIPS"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_35"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3352363"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342165"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.032"},{"key":"ref37","first-page":"1","article-title":"Interactive Language: Talking to Robots in Real Time","author":"Lynch","year":"2023","journal-title":"IEEE RA-L"},{"key":"ref38","first-page":"1761","article-title":"PolarNet: 3D Point Clouds for Language-Guided Robotic Manipulation","author":"Chen","year":"2023","journal-title":"CoRL"},{"key":"ref39","article-title":"Home-Robot: Open-Vocabulary Mobile Manipulation","author":"Yenamandra","year":"2023","journal-title":"ALOE"},{"key":"ref40","first-page":"3571","article-title":"SLAP: Spatial-Language Attention Policies","volume-title":"CoRL","author":"Parashar"},{"key":"ref41","first-page":"6840","article-title":"Denoising Diffusion Probabilistic Models","volume-title":"NeurIPS","author":"Ho"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460699"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"ref48","article-title":"GPT3-5Turbo"},{"key":"ref49","article-title":"text-embedding-ada-002"},{"key":"ref50","first-page":"770","article-title":"Deep Residual Learning for Image Recognition","volume-title":"CVPR","author":"He"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref52","first-page":"8748","article-title":"Learning Transferable Visual Models From Natural Language Supervision","volume-title":"ICML","author":"Radford"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref54","first-page":"12 888","article-title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","volume-title":"ICML","author":"Li"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01283"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref57","first-page":"2292","article-title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transport","volume-title":"NIPS","author":"Cuturi"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"}],"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\/10802596.pdf?arnumber=10802596","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:01:38Z","timestamp":1735196498000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10802596\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10802596","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}