{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T06:34:38Z","timestamp":1774938878304,"version":"3.50.1"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"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 J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/jstsp.2026.3671182","type":"journal-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T21:00:56Z","timestamp":1772830856000},"page":"202-212","source":"Crossref","is-referenced-by-count":0,"title":["SPGrasp: Spatiotemporal Prompt-Driven Grasp Synthesis in Dynamic Scenes"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5310-9164","authenticated-orcid":false,"given":"Yunpeng","family":"Mei","sequence":"first","affiliation":[{"name":"National Key Lab of Autonomous Intelligent Unmanned Systems and School of Automation, Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5681-0916","authenticated-orcid":false,"given":"Hongjie","family":"Cao","sequence":"additional","affiliation":[{"name":"National Key Lab of Autonomous Intelligent Unmanned Systems and School of Automation, Beijing Institute of Technology, Beijing, China"}]},{"given":"Wei","family":"Xiao","sequence":"additional","affiliation":[{"name":"National Key Lab of Autonomous Intelligent Unmanned Systems and School of Automation, Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5361-4338","authenticated-orcid":false,"given":"Yinqiu","family":"Xia","sequence":"additional","affiliation":[{"name":"National Key Lab of Autonomous Intelligent Unmanned Systems and School of Automation, Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9055-9276","authenticated-orcid":false,"given":"Zhaohan","family":"Feng","sequence":"additional","affiliation":[{"name":"National Key Lab of Autonomous Intelligent Unmanned Systems and School of Automation, 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":"National Key Lab of Autonomous Intelligent Unmanned Systems and School of Automation, 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, Harbin Institute of Technology, Harbin, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340777"},{"issue":"5","key":"ref2","article-title":"Multi-agent embodied AI: Advances and future directions","volume":"69","author":"Feng","year":"2026","journal-title":"Sci. China Inf. Sci."},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.xinn.2025.100948"},{"key":"ref4","article-title":"SAM 2: Segment anything in images and videos","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ravi","year":"2025"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3557563"},{"key":"ref6","first-page":"111000","article-title":"Motion consistency model: Accelerating video diffusion with disentangled motion-appearance distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Zhai","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1182"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2955824"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2011.07.016"},{"key":"ref10","article-title":"Universal visuo-tactile video understanding for embodied interaction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xie","year":"2025"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS60139.2025.11246564"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981670"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3504792"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00852"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3281153"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73254-6_26"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3557685"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01146"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636057"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3026970"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2014.2382476"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01217"},{"key":"ref25","article-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018"},{"key":"ref26","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":"ref27","first-page":"1450","article-title":"Language-guided robot grasping: CLIP-based referring grasp synthesis in clutter","volume-title":"Proc. Conf. Robot Learn.","volume":"229","author":"Tziafas","year":"2023"},{"key":"ref28","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":"ref29","article-title":"DINO: DETR with improved denoising anchor boxes for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2917034"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561398"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593950"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161149"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967869"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2852777"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919859066"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106059"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3390\/s22166208"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2025.103547"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"ref41","first-page":"1246","article-title":"BEHAVIOR Robot Suite: Streamlining real-world whole-body manipulation for everyday household activities","volume-title":"Proc. Conf. Robot Learn.","volume":"305","author":"Jiang","year":"2025"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4200690\/11458039\/11422883.pdf?arnumber=11422883","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T05:07:00Z","timestamp":1774933620000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11422883\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":41,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2026.3671182","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}