{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T04:44:21Z","timestamp":1761972261081,"version":"build-2065373602"},"reference-count":25,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"11","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2025,11,1]]},"DOI":"10.1587\/transinf.2024edp7261","type":"journal-article","created":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T18:06:12Z","timestamp":1745345172000},"page":"1325-1334","source":"Crossref","is-referenced-by-count":0,"title":["A Fine-Aware Vision Transformer for Precision Grasp Pose Detection"],"prefix":"10.1587","volume":"E108.D","author":[{"given":"Trung Minh","family":"BUI","sequence":"first","affiliation":[{"name":"lntelligent Robotics Research Center, Korea Electronics Technology Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jung-Hoon","family":"HWANG","sequence":"additional","affiliation":[{"name":"lntelligent Robotics Research Center, Korea Electronics Technology Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sewoong","family":"JUN","sequence":"additional","affiliation":[{"name":"lntelligent Robotics Research Center, Korea Electronics Technology Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wonha","family":"KIM","sequence":"additional","affiliation":[{"name":"College of Electronics and Information, Kyung Hee University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"DongIn","family":"SHIN","sequence":"additional","affiliation":[{"name":"lntelligent Robotics Research Center, Korea Electronics Technology Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"publisher","unstructured":"[1] P. Raj, L. Behera, and T. Sandhan, \u201cScalable and time-efficient bin-picking for unknown objects in dense clutter,\u201d IEEE Trans. Automation Science and Engineering, vol.21, no.3, pp.2289-2301, 2024. 10.1109\/tase.2023.3324610","DOI":"10.1109\/TASE.2023.3324610"},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] A. Cordeiro, L.F. Rocha, C. Costa, P. Costa, and M.F. Silva, \u201cBin picking approaches based on deep learning techniques: A state-of-the-art survey,\u201d 2022 IEEE Int. Conf. Autonomous Robot Systems and Competitions (ICARSC), pp.110-117, IEEE, 2022. 10.1109\/icarsc55462.2022.9784795","DOI":"10.1109\/ICARSC55462.2022.9784795"},{"key":"3","doi-asserted-by":"publisher","unstructured":"[3] K. Kleeberger, R. Bormann, W. Kraus, and M.F. Huber, \u201cA survey on learning-based robotic grasping,\u201d Current Robotics Reports, vol.1, no.4, pp.239-249, 2020. 10.1007\/s43154-020-00021-6","DOI":"10.1007\/s43154-020-00021-6"},{"key":"4","doi-asserted-by":"publisher","unstructured":"[4] H. Tian, K. Song, S. Li, S. Ma, J. Xu, and Y. Yan, \u201cData-driven robotic visual grasping detection for unknown objects: A problem-oriented review,\u201d Expert Systems with Applications, vol.211, p.118624, 2023. 10.1016\/j.eswa.2022.118624","DOI":"10.1016\/j.eswa.2022.118624"},{"key":"5","doi-asserted-by":"publisher","unstructured":"[5] M. Dong and J. Zhang, \u201cA review of robotic grasp detection technology,\u201d Robotica, vol.41, no.12, pp.3846-3885, 2023. 10.1017\/s0263574723001285","DOI":"10.1017\/S0263574723001285"},{"key":"6","doi-asserted-by":"publisher","unstructured":"[6] R. Newbury, M. Gu, L. Chumbley, A. Mousavian, C. Eppner, J. Leitner, J. Bohg, A. Morales, T. Asfour, D. Kragic, D. Fox, and A. Cosgun, \u201cDeep learning approaches to grasp synthesis: A review,\u201d IEEE Trans. Robotics, vol.39, no.5, pp.3994-4015, 2023. 10.1109\/tro.2023.3280597","DOI":"10.1109\/TRO.2023.3280597"},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] M.A. Rashed, R.N. Farhan, and W.M. Jasim, \u201cRobotic grasping based on deep learning: A survey,\u201d 2023 Second Int. Conf. Advanced Computer Applications (ACA), pp.1-7, IEEE, 2023. 10.1109\/aca57612.2023.10346726","DOI":"10.1109\/ACA57612.2023.10346726"},{"key":"8","doi-asserted-by":"publisher","unstructured":"[8] S.P. Pattar, T. Killus, T. Hirakawa, T. Yamashita, T. Sawanobori, and H. Fujiyoshi, \u201cAutomatic data collection for object detection and grasp-position estimation with mobile robots and invisible markers,\u201d Advanced Robotics, vol.37, no.4, pp.241-256, 2023. 10.1080\/01691864.2022.2136504","DOI":"10.1080\/01691864.2022.2136504"},{"key":"9","doi-asserted-by":"publisher","unstructured":"[9] F.-J. Chu, R. Xu, and P.A. Vela, \u201cReal-world multiobject, multigrasp detection,\u201d IEEE Robotics and Automation Letters, vol.3, no.4, pp.3355-3362, 2018. 10.1109\/lra.2018.2852777","DOI":"10.1109\/LRA.2018.2852777"},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] S. Kumra, S. Joshi, and F. Sahin, \u201cAntipodal robotic grasping using generative residual convolutional neural network,\u201d 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp.9626-9633, 2020. 10.1109\/iros45743.2020.9340777","DOI":"10.1109\/IROS45743.2020.9340777"},{"key":"11","unstructured":"[11] K. Islam, \u201cRecent advances in vision transformer: A survey and outlook of recent work,\u201d arXiv preprint arXiv:2203.01536, 2022."},{"key":"12","doi-asserted-by":"publisher","unstructured":"[12] K. Han, Y. Wang, H. Chen, X. Chen, J. Guo, Z. Liu, Y. Tang, A. Xiao, C. Xu, Y. Xu, Z. Yang, Y. Zhang, and D. Tao, \u201cA survey on vision transformer,\u201d IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.45, no.1, pp.87-110, 2022. 10.1109\/tpami.2022.3152247","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"13","doi-asserted-by":"publisher","unstructured":"[13] S. Khan, M. Naseer, M. Hayat, S.W. Zamir, F.S. Khan, and M. Shah, \u201cTransformers in vision: A survey,\u201d ACM computing surveys (CSUR), vol.54, no.10s, pp.1-41, 2022. 10.1145\/3505244","DOI":"10.1145\/3505244"},{"key":"14","doi-asserted-by":"publisher","unstructured":"[14] Y. Liu, Y. Zhang, Y. Wang, F. Hou, J. Yuan, J. Tian, Y. Zhang, Z. Shi, J. Fan, and Z. He, \u201cA survey of visual transformers,\u201d IEEE Trans. Neural Networks and Learning Systems, vol.35, no.6, pp.7478-7498, 2024. 10.1109\/tnnls.2022.3227717","DOI":"10.1109\/TNNLS.2022.3227717"},{"key":"15","doi-asserted-by":"publisher","unstructured":"[15] S. Wang, Z. Zhou, and Z. Kan, \u201cWhen transformer meets robotic grasping: Exploits context for efficient grasp detection,\u201d IEEE robotics and automation letters, vol.7, no.3, pp.8170-8177, 2022. 10.1109\/lra.2022.3187261","DOI":"10.1109\/LRA.2022.3187261"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] X. Xie, G. Cheng, J. Wang, X. Yao, and J. Han, \u201cOriented R-CNN for object detection,\u201d Proc. IEEE\/CVF international conference on computer vision, pp.3520-3529, 2021. 10.1109\/iccv48922.2021.00350","DOI":"10.1109\/ICCV48922.2021.00350"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] R. Ranftl, A. Bochkovskiy, and V. Koltun, \u201cVision transformers for dense prediction,\u201d Proc. IEEE\/CVF international conference on computer vision, pp.12179-12188, 2021. 10.1109\/iccv48922.2021.01196","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] Y. Jiang, S. Moseson, and A. Saxena, \u201cEfficient grasping from rgbd images: Learning using a new rectangle representation,\u201d 2011 IEEE International conference on robotics and automation, pp.3304-3311, IEEE, 2011.","DOI":"10.1109\/ICRA.2011.5980145"},{"key":"19","doi-asserted-by":"publisher","unstructured":"[19] D. Morrison, P. Corke, and J. Leitner, \u201cLearning robust, real-time, reactive robotic grasping,\u201d The International journal of robotics research, vol.39, no.2-3, pp.183-201, 2020. 10.1177\/0278364919859066","DOI":"10.1177\/0278364919859066"},{"key":"20","doi-asserted-by":"crossref","unstructured":"[20] H. Karaoguz and P. Jensfelt, \u201cObject detection approach for robot grasp detection,\u201d 2019 Int. Conf. Robotics and Automation (ICRA), pp.4953-4959, IEEE, 2019. 10.1109\/icra.2019.8793751","DOI":"10.1109\/ICRA.2019.8793751"},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] S. Ainetter and F. Fraundorfer, \u201cEnd-to-end trainable deep neural network for robotic grasp detection and semantic segmentation from RGB,\u201d 2021 IEEE Int. Conf. Robotics and Automation (ICRA), pp.13452-13458, IEEE, 2021. 10.1109\/icra48506.2021.9561398","DOI":"10.1109\/ICRA48506.2021.9561398"},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] A. Depierre, E. Dellandr\u00e9a, and L. Chen, \u201cJacquard: A large scale dataset for robotic grasp detection,\u201d 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp.3511-3516, 2018. 10.1109\/iros.2018.8593950","DOI":"10.1109\/IROS.2018.8593950"},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] H. Zhang, X. Lan, S. Bai, X. Zhou, Z. Tian, and N. Zheng, \u201cRoi-based robotic grasp detection for object overlapping scenes,\u201d 2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp.4768-4775, IEEE, 2019. 10.1109\/iros40897.2019.8967869","DOI":"10.1109\/IROS40897.2019.8967869"},{"key":"24","doi-asserted-by":"publisher","unstructured":"[24] X. Li, R. Cao, Y. Feng, K. Chen, B. Yang, C.-W. Fu, Y. Li, Q. Dou, Y.-H. Liu, and P.-A. Heng, \u201cA sim-to-real object recognition and localization framework for industrial robotic bin picking,\u201d IEEE Robotics and Automation Letters, vol.7, no.2, pp.3961-3968, 2022. 10.1109\/lra.2022.3149026","DOI":"10.1109\/LRA.2022.3149026"},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] S. Jiang, X. Zhao, Z. Cai, K. Xiang, and Z. Ju, \u201cSingle-grasp detection based on rotational region cnn,\u201d Advances in Computational Intelligence Systems: Contributions Presented at the 19th UK Workshop on Computational Intelligence, Sept. 4-6, 2019, Portsmouth, UK 19, pp.131-141, Springer, 2020. 10.1007\/978-3-030-29933-0_11","DOI":"10.1007\/978-3-030-29933-0_11"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E108.D\/11\/E108.D_2024EDP7261\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T03:36:10Z","timestamp":1761968170000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E108.D\/11\/E108.D_2024EDP7261\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,1]]},"references-count":25,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2024edp7261","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"type":"print","value":"0916-8532"},{"type":"electronic","value":"1745-1361"}],"subject":[],"published":{"date-parts":[[2025,11,1]]},"article-number":"2024EDP7261"}}