{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T02:44:18Z","timestamp":1775529858139,"version":"3.50.1"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&amp;D Program of China","award":["2021YFB1714800"],"award-info":[{"award-number":["2021YFB1714800"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62173034"],"award-info":[{"award-number":["62173034"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23B2059"],"award-info":[{"award-number":["U23B2059"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62088101"],"award-info":[{"award-number":["62088101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3557685","type":"journal-article","created":{"date-parts":[[2025,4,3]],"date-time":"2025-04-03T19:59:13Z","timestamp":1743710353000},"page":"3057-3068","source":"Crossref","is-referenced-by-count":7,"title":["RoG-SAM: A Language-Driven Framework for Instance-Level Robotic Grasping Detection"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5310-9164","authenticated-orcid":false,"given":"Yunpeng","family":"Mei","sequence":"first","affiliation":[{"name":"State Key Lab of Autonomous Intelligent Unmanned Systems, Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9898-3129","authenticated-orcid":false,"given":"Jian","family":"Sun","sequence":"additional","affiliation":[{"name":"State Key Lab of Autonomous Intelligent Unmanned Systems, Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9430-8652","authenticated-orcid":false,"given":"Zhihong","family":"Peng","sequence":"additional","affiliation":[{"name":"State Key Lab of Autonomous Intelligent Unmanned Systems, Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1111-7285","authenticated-orcid":false,"given":"Fang","family":"Deng","sequence":"additional","affiliation":[{"name":"State Key Lab of Autonomous Intelligent Unmanned Systems, Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7266-2412","authenticated-orcid":false,"given":"Gang","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Lab of Autonomous Intelligent Unmanned Systems, Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2449-9793","authenticated-orcid":false,"given":"Jie","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, Tongji University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10611277"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340777"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593950"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3214196"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2024.3413164"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561398"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01146"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919859066"},{"key":"ref9","article-title":"Segment and track anything","author":"Cheng","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2011.07.016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759657"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202237"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139361"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2025.103547"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02207"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-062122-025215"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980145"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594116"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967869"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01721-6"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_3"},{"key":"ref24","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref25","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref27","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh"},{"key":"ref28","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Den","year":"2017"},{"key":"ref29","article-title":"DINO: DETR with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.2139\/ssrn.5037734","article-title":"Show and grasp: Few-shot semantic segmentation for robot grasping through zero-shot foundation models","author":"Barcellona","year":"2024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00886"},{"key":"ref34","article-title":"Language-guided robot grasping: Clip-based referring grasp synthesis in clutter","author":"Tziafas","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2021.103757"},{"key":"ref36","article-title":"Grounded sam: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024"},{"key":"ref37","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016"},{"key":"ref38","article-title":"Shapenet: An information-rich 3D model repository","author":"Chang","year":"2015"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793917"},{"key":"ref40","article-title":"Orientation attentive robotic grasp synthesis with augmented grasp map representation","author":"Chalvatzaki","year":"2020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2022.3165825"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2020.101963"},{"key":"ref43","article-title":"Optimizing correlated graspability score and grasp regression for better grasp prediction","author":"Depierre","year":"2020"},{"key":"ref44","article-title":"Lightweight convolutional neural network with Gaussian-based grasping representation for robotic grasping detection","author":"Cao","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161149"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2024.3379049"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106059"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3390\/s22166208"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161319"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2852777"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2917034"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2022.3209488"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2022.3224314"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3419180"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.058"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3281153"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3184873"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3080076"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3342697"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10948350.pdf?arnumber=10948350","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T17:30:57Z","timestamp":1748539857000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10948350\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3557685","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}