{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:38:33Z","timestamp":1757608713350,"version":"3.44.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"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":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11128767","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"7291-7297","source":"Crossref","is-referenced-by-count":0,"title":["Parking-SG: Open-Vocabulary Hierarchical 3D Scene Graph Representation for Open Parking Environments"],"prefix":"10.1109","author":[{"given":"Yaowen","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Automation, Beijing Institute of Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Ruan","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miaoxin","family":"Pan","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengyin","family":"Fu","sequence":"additional","affiliation":[{"name":"School of Automation, Nanjing University of Science and Technology,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2020.102935"},{"key":"ref2","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":"ref3","first-page":"12888","article-title":"Blip: Bootstrapping language-image pretraining for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li","year":"2022"},{"journal-title":"Llama: Open and efficient foundation language models","year":"2023","author":"Touvron","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s12239-023-0025-6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s12239-024-00027-5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147934"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2011.5940476"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00045"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3024668"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3064270"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1049\/icp.2024.3273"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3075644"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2014.X.007"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3687762"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340939"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610168"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00576"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610112"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3320088"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.066"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610243"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3445607"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3441495"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.077"},{"journal-title":"Tag2text: Guiding vision-language model via image tagging","year":"2023","author":"Huang","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_19"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC55140.2022.9922031"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11128767.pdf?arnumber=11128767","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:42:32Z","timestamp":1756881752000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128767\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128767","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}