{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T05:10:23Z","timestamp":1780377023474,"version":"3.54.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T00:00:00Z","timestamp":1781049600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T00:00:00Z","timestamp":1781049600000},"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":[[2026,6,10]]},"DOI":"10.1109\/arso68304.2026.11536136","type":"proceedings-article","created":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T19:33:46Z","timestamp":1780342426000},"page":"163-168","source":"Crossref","is-referenced-by-count":0,"title":["UNCOM: Zero-Shot Context-Aware Command Understanding for Tabletop Scenarios"],"prefix":"10.1109","author":[{"given":"Antonio Galiza Cerdeira","family":"Gonzalez","sequence":"first","affiliation":[{"name":"Jagiellonian University,Krakow,Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pawe\u0142","family":"Gajewski","sequence":"additional","affiliation":[{"name":"Jagiellonian University,Krakow,Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bipin","family":"Indurkhya","sequence":"additional","affiliation":[{"name":"Jagiellonian University,Krakow,Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"issue":"12","key":"ref1","doi-asserted-by":"crossref","DOI":"10.3390\/electronics14122346","article-title":"An empirical study on pointing gestures used in communication in household settings","volume":"14","author":"Kukier","year":"2025","journal-title":"Electronics"},{"key":"ref2","author":"Kim","year":"2024","journal-title":"Openvla: An open-source vision-language-action model"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793590"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/s22166156"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2016.1277554"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3146552"},{"key":"ref7","first-page":"3057","article-title":"Explainable robotics in human-robot interactions","volume-title":"Procedia Computer Science","volume":"176","author":"Setchi"},{"key":"ref8","first-page":"262","article-title":"\u201cput-that-there\u201d voice and gesture at the graphics interface","volume-title":"Proceedings of the 7th annual conference on Computer graphics and interactive techniques","author":"Bolt"},{"key":"ref9","author":"Kumar","year":"2021","journal-title":"Sharing cognition: Human gesture and natural language grounding based planning and navigation for indoor robots"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3643834.3661542"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487507"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v28i1.9051"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3174227"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2852786"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3382507.3418863"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1177\/0278364918760992"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v25i1.7979"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2021.626380"},{"key":"ref19","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning. PMLR","author":"Radford"},{"key":"ref20","author":"Abdin","year":"2024","journal-title":"Phi-4 technical report"},{"key":"ref21","article-title":"Mediapipe: A framework for perceiving and processing reality","volume":"2019","author":"Lugaresi","year":"2019","journal-title":"in Third workshop on computer vision for AR\/VR at IEEE computer vision and pattern recognition (CVPR)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/RAP.2026.3676940"}],"event":{"name":"2026 IEEE International Conference on Advanced Robotics and its Social Impacts (ARSO)","location":"Vienna, Austria","start":{"date-parts":[[2026,6,10]]},"end":{"date-parts":[[2026,6,12]]}},"container-title":["2026 IEEE International Conference on Advanced Robotics and its Social Impacts (ARSO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11535952\/11536109\/11536136.pdf?arnumber=11536136","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T04:59:50Z","timestamp":1780376390000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11536136\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,10]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/arso68304.2026.11536136","relation":{},"subject":[],"published":{"date-parts":[[2026,6,10]]}}}