{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T22:04:25Z","timestamp":1778537065175,"version":"3.51.4"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10611647","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"6620-6626","source":"Crossref","is-referenced-by-count":5,"title":["CLIPUNetr: Assisting Human-robot Interface for Uncalibrated Visual Servoing Control with CLIP-driven Referring Expression Segmentation"],"prefix":"10.1109","author":[{"given":"Chen","family":"Jiang","sequence":"first","affiliation":[{"name":"University of Alberta,Department of Computing Science,Edmonton AB,Canada,T6G 2E8"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchen","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Alberta,Department of Computing Science,Edmonton AB,Canada,T6G 2E8"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin","family":"Jagersand","sequence":"additional","affiliation":[{"name":"University of Alberta,Department of Computing Science,Edmonton AB,Canada,T6G 2E8"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487521"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139369"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460902"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093335"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3062560"},{"key":"ref6","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00766"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107404"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_3"},{"key":"ref11","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"ref13","article-title":"Language-driven semantic segmentation","author":"Li","year":"2022"},{"key":"ref14","first-page":"4971","article-title":"Segvit: Semantic segmentation with plain vision transformers","volume":"35","author":"Zhang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.487"},{"key":"ref17","article-title":"Recognizing object affordances to support scene reasoning for manipulation tasks","author":"Chu","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3286074"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-95459-8_9"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3062315"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460857"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968278"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3248324"},{"key":"ref24","article-title":"Unsupervised learning of object key-points for perception and control","volume":"32","author":"Kulkarni","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref25","first-page":"894","article-title":"Cliport: What and where pathways for robotic manipulation","volume-title":"Conference on Robot Learning.","author":"Shridhar","year":"2022"},{"key":"ref26","first-page":"785","article-title":"Perceiver-actor: A multi-task transformer for robotic manipulation","volume-title":"Conference on Robot Learning.","author":"Shridhar","year":"2023"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.23915\/distill.00011","article-title":"Feature-wise transformations","volume-title":"Distill","author":"Dumoulin","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1997.606723"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01023"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10611647.pdf?arnumber=10611647","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T04:19:48Z","timestamp":1723349988000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611647\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10611647","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}