{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T12:47:11Z","timestamp":1780318031816,"version":"3.54.1"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2023,8,5]],"date-time":"2023-08-05T00:00:00Z","timestamp":1691193600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,8,5]],"date-time":"2023-08-05T00:00:00Z","timestamp":1691193600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"National Key Research and Development Program of the Ministry of Science and Technology","award":["2018YFC0309104"],"award-info":[{"award-number":["2018YFC0309104"]}]},{"name":"Classroom Observation and Analysis of College Basic Courses based on COUPS Scale","award":["ZDJG-1712"],"award-info":[{"award-number":["ZDJG-1712"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-023-16365-y","type":"journal-article","created":{"date-parts":[[2023,8,5]],"date-time":"2023-08-05T02:01:53Z","timestamp":1691200913000},"page":"20953-20973","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Fusion-Mask-RCNN: Visual robotic grasping in cluttered scenes"],"prefix":"10.1007","volume":"83","author":[{"given":"Junyan","family":"Ge","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingbo","family":"Mao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3795-9387","authenticated-orcid":false,"given":"Jinlong","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,8,5]]},"reference":[{"key":"16365_CR1","doi-asserted-by":"publisher","first-page":"101052","DOI":"10.1016\/j.aei.2020.101052","volume":"44","author":"L Bergamini","year":"2020","unstructured":"Bergamini L, Sposato M, Pellicciari M, Peruzzini M, Calderara S, Schmidt J (2020) Deep learning-based method for vision-guided robotic grasping of unknown objects[J]. Adv Eng Inform 44:101052. https:\/\/doi.org\/10.1016\/j.aei.2020.101052","journal-title":"Adv Eng Inform"},{"key":"16365_CR2","doi-asserted-by":"publisher","unstructured":"Bukschat Y, Vetter M. EfficientPose: An efficient, accurate and scalable end-to-end 6D multi object pose estimation approach[J]. https:\/\/doi.org\/10.48550\/arXiv.2011.04307","DOI":"10.48550\/arXiv.2011.04307"},{"key":"16365_CR3","unstructured":"Chemelil P K (2021) Single shot multi box detector approach to autonomous vision-based pick and place robotic arm in the presence of uncertainties[D]. JKUAT-COETEC"},{"key":"16365_CR4","doi-asserted-by":"publisher","unstructured":"Chen W, Jia X, Chang H J, Duan J, Leonardis A (2020) G2l-net: Global to local network for real-time 6d pose estimation with embedding vector features[C]. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 4233\u20134242. https:\/\/doi.org\/10.1109\/cvpr42600.2020.00429","DOI":"10.1109\/cvpr42600.2020.00429"},{"key":"16365_CR5","doi-asserted-by":"publisher","unstructured":"Chen Z, Jia Z, Lin M, et al (2022) Towards generalization an d data efficient learning of deep robotic grasping[C]. 2022 IEEE 17th Conference on Industrial Electronics and Applications (ICIEA). IEEE, 804 809. https:\/\/doi.org\/10.1109\/ICIEA54703.2022.10006045","DOI":"10.1109\/ICIEA54703.2022.10006045"},{"key":"16365_CR6","unstructured":"Denninger M, Sundermeyer M, Winkelbauer D, Zidan Y, Olefir D, Elbadrawy M, Lodhi A, Katam H (2019) Blenderproc[J]. arXiv preprint arXiv:1911.01911"},{"key":"16365_CR7","doi-asserted-by":"publisher","unstructured":"Gupta S, Girshick R, Arbel\u00e1ez P, Malik J (2014) Learning rich features from RGB-D images for object detection and segmentation[C]. European conference on computer vision. Springer, Cham, 345\u2013360. https:\/\/doi.org\/10.1007\/978-3-319-10584-0_23","DOI":"10.1007\/978-3-319-10584-0_23"},{"key":"16365_CR8","doi-asserted-by":"publisher","unstructured":"Hafiz, Abdul Mueed, and Ghulam Mohiuddin Bhat (2020) A survey on instance segmentation: state of the art. International journal of multimedia information retrieval 9.3: 171\u2013189. https:\/\/doi.org\/10.48550\/arXiv.2007.00047","DOI":"10.48550\/arXiv.2007.00047"},{"key":"16365_CR9","doi-asserted-by":"publisher","unstructured":"He K, Gkioxari G, Doll\u00e1r P, Dollar P, Girshick R (2017) Mask r-cnn[C]. Proceedings of the IEEE international conference on computer vision. 2961\u20132969. https:\/\/doi.org\/10.48550\/arXiv.1703.06870","DOI":"10.48550\/arXiv.1703.06870"},{"key":"16365_CR10","doi-asserted-by":"publisher","unstructured":"He Y, Huang H, Fan H, Chen Q, Sun J (2021) FFB6D: A full flow bidirectional fusion network for 6D pose Estimation[C]. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 3003\u20133013. https:\/\/doi.org\/10.1109\/cvpr46437.2021.00302","DOI":"10.1109\/cvpr46437.2021.00302"},{"key":"16365_CR11","doi-asserted-by":"publisher","unstructured":"Hou, Rui, et al (2020) Real-time panoptic segmentation from dense detections. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. https:\/\/doi.org\/10.48550\/arXiv.1912.01202","DOI":"10.48550\/arXiv.1912.01202"},{"key":"16365_CR12","doi-asserted-by":"publisher","first-page":"51","DOI":"10.3389\/fnbot.2020.00051","volume":"14","author":"B Li","year":"2020","unstructured":"Li B, Cao H, Qu Z, Hu Y, Wang Z, Liang Z (2020) Event-based robotic grasping detection with neuromorphic vision sensor and event-grasping dataset[J]. Front Neurorobot 14:51. https:\/\/doi.org\/10.3389\/fnbot.2020.00051","journal-title":"Front Neurorobot"},{"key":"16365_CR13","doi-asserted-by":"publisher","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C, Alexander C (2016) Berg. Ssd: Single shot multibox detector[C]. European conference on computer vision. Springer, Cham, 21\u201337. https:\/\/doi.org\/10.48550\/arXiv.1512.02325","DOI":"10.48550\/arXiv.1512.02325"},{"key":"16365_CR14","doi-asserted-by":"publisher","unstructured":"Lu X, Wang W, Ma C, et al (2019) See more, know more: Unsupervised video object segmentation with co-attention siamese networks[C]. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 3623\u20133632. https:\/\/doi.org\/10.48550\/arXiv.2001.06810","DOI":"10.48550\/arXiv.2001.06810"},{"key":"16365_CR15","doi-asserted-by":"publisher","unstructured":"Lu X, Wang W, Danelljan M, et al (2020) Video object segmentation with episodic graph memory networks[C]. Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part III 16. Springer International Publishing, 661\u2013679. https:\/\/doi.org\/10.48550\/arXiv.2007.07020","DOI":"10.48550\/arXiv.2007.07020"},{"issue":"4","key":"16365_CR16","doi-asserted-by":"publisher","first-page":"2228","DOI":"10.1109\/TPAMI.2020.3040258","volume":"44","author":"X Lu","year":"2020","unstructured":"Lu X, Wang W, Shen J et al (2020) Zero-shot video object segmentation with co-attention siamese networks[J]. IEEE Trans Pattern Anal Mach Intell 44(4):2228\u20132242. https:\/\/doi.org\/10.1109\/TPAMI.2020.3040258","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"11","key":"16365_CR17","doi-asserted-by":"publisher","first-page":"7885","DOI":"10.1109\/TPAMI.2021.3115815","volume":"44","author":"X Lu","year":"2021","unstructured":"Lu X, Wang W, Shen J et al (2021) Segmenting objects from relational visual data[J]. IEEE Trans Pattern Anal Mach Intell 44(11):7885\u20137897. https:\/\/doi.org\/10.1109\/TPAMI.2021.3115815","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"16365_CR18","doi-asserted-by":"publisher","unstructured":"Mahanta GB, Deepak B, Biswal BB (2021) Application of soft computing methods in robotic grasping: A state-of-the-art survey[J]. Proceedings of the Institution of Mechanical Engineers, Part E: Journal of Process Mechanical Engineering, 09544089211039977. https:\/\/doi.org\/10.1177\/09544089211039977","DOI":"10.1177\/09544089211039977"},{"key":"16365_CR19","doi-asserted-by":"publisher","unstructured":"Mahler J, Pokorny FT, Hou B, Roderick M, Laskey M, Aubry M, Kohlhoff K, Kr\u00f6ger T, Kuffner J, Goldberg K (2016) Dex-net 1.0: A cloud-based network of 3d objects for robust grasp planning using a multi-armed bandit model with correlated rewards[C]. 2016 IEEE international conference on robotics and automation (ICRA). IEEE, 1957-1964. https:\/\/doi.org\/10.1109\/icra.2016.7487342","DOI":"10.1109\/icra.2016.7487342"},{"key":"16365_CR20","doi-asserted-by":"publisher","unstructured":"Mahler J, Matl M, Liu X, Li A, Gealy D, Goldberg K (2018) Dex-net 3.0: Computing robust robot vacuum suction grasp targets in point clouds using a new analytic model and deep learning[J]. arXiv preprint;arXiv:1709.06670. https:\/\/doi.org\/10.1109\/icra.2018.8460887","DOI":"10.1109\/icra.2018.8460887"},{"key":"16365_CR21","doi-asserted-by":"publisher","unstructured":"Miao C, Zhong X, Zhong X, et al (2021) Detection and grasping of texture-less objects based on 3d template matching[C]. 2021 40th Chinese Control Conference (CCC). IEEE, 3943\u20133948. https:\/\/doi.org\/10.23919\/ccc52363.2021.9550615","DOI":"10.23919\/ccc52363.2021.9550615"},{"key":"16365_CR22","doi-asserted-by":"publisher","unstructured":"Mohamad, Mustafa, et al (2015) Super generalized 4pcs for 3d registration. 2015 International Conference on 3D Vision. IEEE. https:\/\/doi.org\/10.1109\/3DV.2015.74","DOI":"10.1109\/3DV.2015.74"},{"key":"16365_CR23","doi-asserted-by":"publisher","unstructured":"Morrison D, Corke P, Leitner J (2018) Closing the loop for robotic grasping: A real-time, generative grasp synthesis approach[J]. arXiv preprint;arXiv:1804.05172, https:\/\/doi.org\/10.15607\/rss.2018.xiv.021","DOI":"10.15607\/rss.2018.xiv.021"},{"issue":"5","key":"16365_CR24","doi-asserted-by":"publisher","first-page":"717","DOI":"10.1109\/70.326576","volume":"10","author":"FC Park","year":"1994","unstructured":"Park FC, Martin BJ (1994) Robot sensor calibration: solving AX= XB on the Euclidean group[J]. IEEE Trans Robot Autom 10(5):717\u2013721. https:\/\/doi.org\/10.1109\/70.326576","journal-title":"IEEE Trans Robot Autom"},{"key":"16365_CR25","doi-asserted-by":"publisher","unstructured":"Peng S, Liu Y, Huang Q, Zhou X, Bao H (2019) Pvnet: Pixel-wise voting network for 6dof pose estimation[C]. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 4561\u20134570. https:\/\/doi.org\/10.1109\/cvpr.2019.00469","DOI":"10.1109\/cvpr.2019.00469"},{"issue":"6","key":"16365_CR26","doi-asserted-by":"publisher","first-page":"063025","DOI":"10.1117\/1.jei.30.6.063025","volume":"30","author":"T Ren","year":"2021","unstructured":"Ren T, Dong Z, Qi F et al (2021) Relational reasoning for real-time object searching[J]. Journal of Electronic Imaging 30(6):063025. https:\/\/doi.org\/10.1117\/1.jei.30.6.063025","journal-title":"Journal of Electronic Imaging"},{"issue":"3","key":"16365_CR27","doi-asserted-by":"publisher","first-page":"392","DOI":"10.2307\/2031890","volume":"3","author":"WE Roth","year":"1952","unstructured":"Roth WE (1952) The equations AX-YB= C and AX-XB= c in matrices[J]. Proceed Am Math Soc 3(3):392\u2013396. https:\/\/doi.org\/10.2307\/2031890","journal-title":"Proceed Am Math Soc"},{"key":"16365_CR28","doi-asserted-by":"publisher","unstructured":"Rusu R B, Blodow N, Beetz M (2009) Fast point feature histograms (FPFH) for 3D registration[C]\/\/2009 IEEE international conference on robotics and automation. IEEE,: 3212\u20133217. https:\/\/doi.org\/10.1109\/robot.2009.5152473","DOI":"10.1109\/robot.2009.5152473"},{"key":"16365_CR29","doi-asserted-by":"crossref","unstructured":"Schneider L, Jasch M, Fr\u00f6hlich B, Weber T, Franke U, Pollefeys M, R\u00e4tsch M (2017) Multimodal neural networks: Rgb-d for semantic segmentation and object detection[C]. Scandinavian conference on image analysis. Springer, Cham, 98\u2013109.","DOI":"10.1007\/978-3-319-59126-1_9"},{"key":"16365_CR30","doi-asserted-by":"publisher","unstructured":"Segal, Aleksandr, Dirk Haehnel, and Sebastian Thrun (2009) Generalized-icp. Robotics: science and systems. 2 (4). https:\/\/doi.org\/10.15607\/RSS.2009.V.021","DOI":"10.15607\/RSS.2009.V.021"},{"issue":"1","key":"16365_CR31","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1109\/70.88014","volume":"5","author":"YC Shiu","year":"1989","unstructured":"Shiu YC, Ahmad S (1989) Calibration of wrist-mounted robotic sensors by solving homogeneous transform equations of the form AX= XB[J]. IEEE Trans Robot Autom 5(1):16\u201329. https:\/\/doi.org\/10.1109\/70.88014","journal-title":"IEEE Trans Robot Autom"},{"key":"16365_CR32","doi-asserted-by":"publisher","unstructured":"Wang Y, Wang J, Chen W (2018) Grasp planning based on scene grasp ability in unstructured environment[C]. 2018 IEEE International Conference on Robotics and Biomimetics (ROBIO). IEEE, 1477\u20131482. https:\/\/doi.org\/10.1109\/robio.2018.8665076","DOI":"10.1109\/robio.2018.8665076"},{"key":"16365_CR33","doi-asserted-by":"publisher","unstructured":"Ward, Isaac Ronald, Hamid Laga, and Mohammed Bennamoun (2019) \"RGB-D image-based object detection: from traditional methods to deep learning techniques.\" RGB-D Image Analysis and Processing 169\u2013201. https:\/\/doi.org\/10.48550\/arXiv.1907.09236","DOI":"10.48550\/arXiv.1907.09236"},{"key":"16365_CR34","doi-asserted-by":"publisher","unstructured":"Zhou T, Fan D P, Cheng M M, et al (2021) RGB-D salient object detection: A survey[J]. Computational Visual Media, 7: 37\u201369. https:\/\/doi.org\/10.48550\/arXiv.2008.00230","DOI":"10.48550\/arXiv.2008.00230"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-16365-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-16365-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-16365-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,15]],"date-time":"2024-02-15T10:49:05Z","timestamp":1707994145000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-16365-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,5]]},"references-count":34,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2024,2]]}},"alternative-id":["16365"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-16365-y","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,5]]},"assertion":[{"value":"1 February 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 June 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 July 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 August 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}