{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T01:47:22Z","timestamp":1777945642678,"version":"3.51.4"},"reference-count":29,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"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-017"},{"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"},{"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-012"},{"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-004"}],"funder":[{"DOI":"10.13039\/501100003465","name":"Haldia Institute of Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003465","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011381","name":"State Key Laboratory of Robotics and System","doi-asserted-by":"publisher","award":["SKLRS-2025-KF-18"],"award-info":[{"award-number":["SKLRS-2025-KF-18"]}],"id":[{"id":"10.13039\/501100011381","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition Letters"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.patrec.2026.03.011","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T09:25:23Z","timestamp":1773825923000},"page":"15-20","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["TGDF: Task-oriented grasping through dense detection and foundation models"],"prefix":"10.1016","volume":"204","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4002-7904","authenticated-orcid":false,"given":"Hanwen","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9253-5350","authenticated-orcid":false,"given":"Yike","family":"Wen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6980-4555","authenticated-orcid":false,"given":"Ying","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.patrec.2026.03.011_bib0001","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"15964","article-title":"Graspness discovery in clutters for fast and accurate grasp detection","author":"Wang","year":"2021"},{"key":"10.1016\/j.patrec.2026.03.011_bib0002","series-title":"Conference on Robot Learning","first-page":"2004","article-title":"Towards scale balanced 6-dof grasp detection in cluttered scenes","author":"Ma","year":"2023"},{"key":"10.1016\/j.patrec.2026.03.011_bib0003","series-title":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"3000","article-title":"6-DoF grasp detection in clutter with enhanced receptive field and graspable balance sampling","author":"Wang","year":"2024"},{"key":"10.1016\/j.patrec.2026.03.011_bib0004","unstructured":"M.J. Kim, K. Pertsch, S. Karamcheti, T. Xiao, A. Balakrishna, S. Nair, R. Rafailov, E. Foster, G. Lam, P. Sanketi, et al., OpenVLA: An Open-Source Vision-Language-Action Model, (2024). arXiv: 2406.09246."},{"key":"10.1016\/j.patrec.2026.03.011_bib0005","doi-asserted-by":"crossref","DOI":"10.1109\/LRA.2023.3320012","article-title":"Graspgpt: leveraging semantic knowledge from a large language model for task-oriented grasping","author":"Tang","year":"2023","journal-title":"IEEE Rob. Autom. Lett."},{"key":"10.1016\/j.patrec.2026.03.011_bib0006","article-title":"Foundationgrasp: generalizable task-oriented grasping with foundation models","author":"Tang","year":"2025","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"10.1016\/j.patrec.2026.03.011_bib0007","doi-asserted-by":"crossref","unstructured":"H. Huang, F. Lin, Y. Hu, S. Wang, Y. Gao, Copa: General robotic manipulation through spatial constraints of parts with foundation models, (2024). arXiv: 2403.08248.","DOI":"10.1109\/IROS58592.2024.10801352"},{"key":"10.1016\/j.patrec.2026.03.011_bib0008","series-title":"2011 IEEE International Conference on Robotics and Automation","first-page":"3304","article-title":"Efficient grasping from RGBD images: learning using a new rectangle representation","author":"Jiang","year":"2011"},{"key":"10.1016\/j.patrec.2026.03.011_bib0009","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1016\/j.patrec.2021.08.026","article-title":"Multi-style learning for adaptation of perception intelligence in home service robots","volume":"151","author":"Wang","year":"2021","journal-title":"Pattern Recognit. Lett."},{"issue":"4","key":"10.1016\/j.patrec.2026.03.011_bib0010","doi-asserted-by":"crossref","first-page":"3355","DOI":"10.1109\/LRA.2018.2852777","article-title":"Real-world multiobject, multigrasp detection","volume":"3","author":"Chu","year":"2018","journal-title":"IEEE Rob. Autom. Lett."},{"key":"10.1016\/j.patrec.2026.03.011_bib0011","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"8085","article-title":"Densely supervised grasp detector (DSGD)","volume":"33","author":"Asif","year":"2019"},{"key":"10.1016\/j.patrec.2026.03.011_bib0012","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1016\/j.patrec.2025.02.026","article-title":"Interactive shape estimation for densely cluttered objects","volume":"191","author":"Ran","year":"2025","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.patrec.2026.03.011_bib0013","series-title":"2019 International Conference on Robotics and Automation (ICRA)","first-page":"3629","article-title":"PointNetGPD: detecting grasp configurations from point sets","author":"Liang","year":"2019"},{"key":"10.1016\/j.patrec.2026.03.011_bib0014","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11444","article-title":"Graspnet-1billion: a large-scale benchmark for general object grasping","author":"Fang","year":"2020"},{"key":"10.1016\/j.patrec.2026.03.011_bib0015","series-title":"2021 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"13459","article-title":"RGB matters: learning 7-dof grasp poses on monocular RGBD images","author":"Gou","year":"2021"},{"key":"10.1016\/j.patrec.2026.03.011_bib0016","series-title":"2023 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"1757","article-title":"GraspNerf: multiview-based 6-dof grasp detection for transparent and specular objects using generalizable nerf","author":"Dai","year":"2023"},{"key":"10.1016\/j.patrec.2026.03.011_bib0017","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1016\/j.patrec.2023.09.006","article-title":"Hand-object information embedded dexterous grasping generation","volume":"174","author":"Ren","year":"2023","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.patrec.2026.03.011_bib0018","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"4015","article-title":"Segment anything","author":"Kirillov","year":"2023"},{"issue":"8","key":"10.1016\/j.patrec.2026.03.011_bib0019","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"10.1016\/j.patrec.2026.03.011_bib0020","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","first-page":"4171","article-title":"Bert: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.patrec.2026.03.011_bib0021","unstructured":"H. Touvron, T. Lavril, G. Izacard, X. Martinet, M.-A. Lachaux, T. Lacroix, B. Rozi\u00e8re, N. Goyal, E. Hambro, F. Azhar, et al., Llama: Open and efficient foundation language models, (2023). arXiv: 2302.13971."},{"issue":"240","key":"10.1016\/j.patrec.2026.03.011_bib0022","first-page":"1","article-title":"Palm: scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.patrec.2026.03.011_bib0023","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.patrec.2026.03.011_bib0024","unstructured":"J. Achiam, S. Adler, S. Agarwal, L. Ahmad, I. Akkaya, F.L. Aleman, D. Almeida, J. Altenschmidt, S. Altman, S. Anadkat, et al., Gpt-4 technical report, (2023). arXiv: 2303.08774."},{"issue":"5","key":"10.1016\/j.patrec.2026.03.011_bib0025","doi-asserted-by":"crossref","first-page":"1343","DOI":"10.1109\/TRO.2021.3060341","article-title":"Unseen object instance segmentation for robotic environments","volume":"37","author":"Xie","year":"2021","journal-title":"IEEE Trans. Rob."},{"key":"10.1016\/j.patrec.2026.03.011_bib0026","unstructured":"J. Yang, H. Zhang, F. Li, X. Zou, C. Li, J. Gao, Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V, (2023). arXiv: 2310.11441."},{"key":"10.1016\/j.patrec.2026.03.011_bib0027","unstructured":"F. Li, H. Zhang, P. Sun, X. Zou, S. Liu, J. Yang, C. Li, L. Zhang, J. Gao, Semantic-SAM: Segment and Recognize Anything at Any Granularity, (2023). arXiv: 2307.04767."},{"key":"10.1016\/j.patrec.2026.03.011_bib0028","unstructured":"X. Zhao, W. Ding, Y. An, Y. Du, T. Yu, M. Li, M. Tang, J. Wang, Fast segment anything, (2023). arXiv: 2306.12156."},{"key":"10.1016\/j.patrec.2026.03.011_bib0029","unstructured":"A. Yan, Z. Yang, J. Wu, W. Zhu, J. Yang, L. Li, K. Lin, J. Wang, J. McAuley, J. Gao, et al., List Items One by One: A New Data Source and Learning Paradigm for Multimodal LLMs, (2024). arXiv: 2404.16375."}],"container-title":["Pattern Recognition Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167865526001017?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167865526001017?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T12:40:43Z","timestamp":1777725643000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167865526001017"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":29,"alternative-id":["S0167865526001017"],"URL":"https:\/\/doi.org\/10.1016\/j.patrec.2026.03.011","relation":{},"ISSN":["0167-8655"],"issn-type":[{"value":"0167-8655","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"TGDF: Task-oriented grasping through dense detection and foundation models","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition Letters","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patrec.2026.03.011","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}]}}