{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T19:05:21Z","timestamp":1777921521466,"version":"3.51.4"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100017691","name":"Guangxi Key Research and Development Program","doi-asserted-by":"crossref","award":["AA21077015"],"award-info":[{"award-number":["AA21077015"]}],"id":[{"id":"10.13039\/501100017691","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12162005"],"award-info":[{"award-number":["12162005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Innovation Project of Guangxi Graduate Education","award":["YCSW2025221"],"award-info":[{"award-number":["YCSW2025221"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/lra.2026.3686670","type":"journal-article","created":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:51:49Z","timestamp":1776887509000},"page":"7316-7323","source":"Crossref","is-referenced-by-count":0,"title":["VLAD-Grasp: Vision-Language Adaptive Depth Grasping for Part-Specific Manipulation"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1188-5451","authenticated-orcid":false,"given":"Meng","family":"Liu","sequence":"first","affiliation":[{"name":"Guangxi Key Laboratory of Brain-Inspired Computing and Intelligent Chips, School of Electronics and Information Engineering, Guangxi Normal University, Guilin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5793-8065","authenticated-orcid":false,"given":"Yanli","family":"Zou","sequence":"additional","affiliation":[{"name":"Guangxi Key Laboratory of Brain-Inspired Computing and Intelligent Chips, School of Electronics and Information Engineering, Guangxi Normal University, Guilin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Wang","sequence":"additional","affiliation":[{"name":"Guangxi Key Laboratory of Brain-Inspired Computing and Intelligent Chips, School of Electronics and Information Engineering, Guangxi Normal University, Guilin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1371-6356","authenticated-orcid":false,"given":"Shiquan","family":"Qiu","sequence":"additional","affiliation":[{"name":"Guangxi Key Laboratory of Brain-Inspired Computing and Intelligent Chips, School of Electronics and Information Engineering, Guangxi Normal University, Guilin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0102-133X","authenticated-orcid":false,"given":"Fan","family":"Lei","sequence":"additional","affiliation":[{"name":"Guangxi Key Laboratory of Brain-Inspired Computing and Intelligent Chips, School of Electronics and Information Engineering, Guangxi Normal University, Guilin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.2986921"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2975706"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5649406"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801993"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.028"},{"key":"ref6","first-page":"178","article-title":"Language embedded radiance fields for zero-shot task-oriented grasping","volume-title":"Proc. 7th Annu. Conf. Robot Learn., Proc. Mach. Learn. Res.","volume":"229","author":"Rashid","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802654"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01566"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2011.07.016"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2000.844081"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3281153"},{"key":"ref12","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":"ref13","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Gu","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"ref16","first-page":"19769","article-title":"Segment everything everywhere all at once","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Zou","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01417"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73226-3_27"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341379"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342268"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3320012"},{"key":"ref23","article-title":"Lan-grasp: Using large language models for semantic object grasping","author":"Mirjalili","year":"2023"},{"key":"ref24","first-page":"3568","article-title":"ThinkGrasp: A vision-language system for strategic part grasping in clutter","volume-title":"Proc. 8th Conf. Robot Learn., Proc. Mach. Learn. Res.","volume":"270","author":"Qian","year":"2025"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.5204\/thesis.eprints.253403"},{"key":"ref26","article-title":"Glover: Generalizable open-vocabulary affordance reasoning for task-oriented grasping","author":"Ma","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IROS60139.2025.11245995"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2025.105210"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341672"},{"key":"ref30","first-page":"1540","article-title":"Same object, different grasps: Data and semantic knowledge for task-oriented grasping","volume-title":"Proc. Conf. Robot Learn.","author":"Murali","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00229"},{"key":"ref32","article-title":"Qwen2-VL: Enhancing vision-language models perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref33","first-page":"894","article-title":"CLIPort: What and where pathways for robotic manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Shridhar","year":"2022"},{"key":"ref34","article-title":"OV-DINO: Unified open-vocabulary detection with language-aware selective fusion","author":"Wang"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01817"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref40","article-title":"Kosmos-2: Grounding multimodal large language models to the world","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Peng","year":"2024"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11481819\/11489501.pdf?arnumber=11489501","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T19:55:41Z","timestamp":1777665341000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11489501\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":40,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3686670","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}