{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T13:07:42Z","timestamp":1784725662498,"version":"3.55.0"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T00:00:00Z","timestamp":1780704000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T00:00:00Z","timestamp":1780704000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1007\/s00530-026-02379-7","type":"journal-article","created":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T07:34:14Z","timestamp":1780731254000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning complementary features via cross-modal attention for robust 6-DoF grasping"],"prefix":"10.1007","volume":"32","author":[{"given":"Xujian","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baiyang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Fang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongjun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hua","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,6]]},"reference":[{"issue":"4\u20135","key":"2379_CR1","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1177\/0278364917710318","volume":"37","author":"S Levine","year":"2018","unstructured":"Levine, S., Pastor, P., Krizhevsky, A., Ibarz, J., Quillen, D.: Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection. Int. J. Robot. Res. 37(4\u20135), 421\u2013436 (2018)","journal-title":"Int. J. Robot. Res."},{"key":"2379_CR2","doi-asserted-by":"crossref","unstructured":"Fang, H.-S., Wang, C., Gou, M., Lu, C.: Graspnet-1billion: A large-scale benchmark for general object grasping. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11444\u201311453 (2020)","DOI":"10.1109\/CVPR42600.2020.01146"},{"key":"2379_CR3","doi-asserted-by":"crossref","unstructured":"Bicchi, A., Kumar, V.: Robotic grasping and contact: a review. In: Proc. Millennium Conf., IEEE Int. Conf. Robot. Automat., Symposia, vol. 1, pp. 348\u2013353 (2000)","DOI":"10.1109\/ROBOT.2000.844081"},{"issue":"2","key":"2379_CR4","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1109\/TRO.2013.2289018","volume":"30","author":"J Bohg","year":"2014","unstructured":"Bohg, J., Morales, A., Asfour, T., Kragic, D.: Data-driven grasp synthesis\u2014a survey. IEEE Trans. Robot. 30(2), 289\u2013309 (2014)","journal-title":"IEEE Trans. Robot."},{"key":"2379_CR5","first-page":"1","volume":"73","author":"J Wu","year":"2024","unstructured":"Wu, J., Ru, X., Lu, S., Xiong, R., Wang, Y.: Recurrent volume-based 3-D feature fusion for real-time multiview object pose estimation. IEEE Trans. Instrum. Meas. 73, 1\u201313 (2024)","journal-title":"IEEE Trans. Instrum. Meas."},{"issue":"13\u201314","key":"2379_CR6","first-page":"1455","volume":"36","author":"AT Pas","year":"2017","unstructured":"Pas, A.T., Gualtieri, M., Saenko, K., Platt, R.: Grasp pose detection in point clouds. Int. J. Robot. Res. 36(13\u201314), 1455\u20131473 (2017)","journal-title":"Int. J. Robot. Res."},{"key":"2379_CR7","doi-asserted-by":"crossref","unstructured":"Mahler, J., et al.: Dex-Net 2.0: Deep learning to plan robust grasps with synthetic point clouds and analytic grasp metrics. In: Proc. Robot., Sci. Syst. (RSS) (2017). https:\/\/www.roboticsproceedings.org\/rss13\/p58.html","DOI":"10.15607\/RSS.2017.XIII.058"},{"key":"2379_CR8","unstructured":"Qin, Y., Chen, R., Zhu, H., Song, M., Xu, J., Su, H.: S4G: Amodal single-view single-shot SE (3) grasp detection in cluttered scenes. In: Proc. Conf. Robot Learn., pp. 53\u201365 (2020)"},{"key":"2379_CR9","doi-asserted-by":"crossref","unstructured":"Wang, C., Fang, H.-S., Gou, M., Fang, H., Gao, J., Lu, C.: Graspness discovery in clutters for fast and accurate grasp detection. In: Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV), pp. 15944\u201315953 (2021)","DOI":"10.1109\/ICCV48922.2021.01566"},{"key":"2379_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102227","volume":"105","author":"JX Hong","year":"2024","unstructured":"Hong, J.X., Zhang, H.B., Liu, J.H., et al.: A Transformer-based multi-modal fusion network for 6D pose estimation. Inf. Fusion 105, 102227 (2024)","journal-title":"Inf. Fusion"},{"key":"2379_CR11","doi-asserted-by":"crossref","unstructured":"Chen, Y., Lin, Y., Xu, R., Vela, P.A.: Keypoint-graspnet: keypoint-based 6-dof grasp generation from the monocular RGB-D input. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 7988\u20137995. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10161284"},{"key":"2379_CR12","unstructured":"Breyer, M., Chung, J.J., Ott, L., Siegwart, R., Nieto, J.: Volumetric grasping network: Real-time 6 dof grasp detection in clutter. In: Conference on Robot Learning. PMLR, pp. 1602\u20131611 (2021)"},{"key":"2379_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.111318","volume":"161","author":"H Gui","year":"2025","unstructured":"Gui, H., Pang, S., He, X., et al.: GraspFast: multi-stage lightweight 6-DoF grasp pose fast detection with RGB-D image. Pattern Recogn. 161, 111318 (2025)","journal-title":"Pattern Recogn."},{"key":"2379_CR14","unstructured":"Ma, H., Huang, D.: Towards scale balanced 6-dof grasp detection in cluttered scenes. In: Conference on Robot Learning. PMLR, pp. 2004\u20132013 (2023)"},{"issue":"4","key":"2379_CR15","doi-asserted-by":"publisher","first-page":"6899","DOI":"10.1109\/LRA.2021.3096239","volume":"6","author":"J Lundell","year":"2021","unstructured":"Lundell, J., Verdoja, F., Kyrki, V.: DDGC: generative deep dexterous grasping in clutter. IEEE Robot. Autom. Lett. 6(4), 6899\u20136906 (2021)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"2379_CR16","first-page":"1","volume":"70","author":"J Cheng","year":"2021","unstructured":"Cheng, J., Liu, P., Zhang, Q., Ma, H., Wang, F., Zhang, J.: Real-time and efficient 6-D pose estimation from a single RGB image. IEEE Trans. Instrum. Meas. 70, 1\u201314 (2021)","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"2379_CR17","doi-asserted-by":"crossref","unstructured":"Varley, J., Weisz, J., Weiss, J., Allen, P., Generating multi-fingered robotic grasps via deep learning. In: IEEE\/RSJ international conference on intelligent robots and systems (IROS), vol. 2015, pp. 4415\u20134420. IEEE (2015)","DOI":"10.1109\/IROS.2015.7354004"},{"key":"2379_CR18","doi-asserted-by":"crossref","unstructured":"Kappler, D., Bohg, J., Schaal, S., Leveraging big data for grasp planning. In: IEEE international conference on robotics and automation (ICRA), pp. 4304\u20134311. IEEE (2015)","DOI":"10.1109\/ICRA.2015.7139793"},{"key":"2379_CR19","doi-asserted-by":"crossref","unstructured":"Gualtieri, M., Ten Pas, A., Saenko, K., Platt, R.: High precision grasp pose detection in dense clutter. In: 2016 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 598\u2013605. IEEE (2016)","DOI":"10.1109\/IROS.2016.7759114"},{"issue":"13\u201314","key":"2379_CR20","doi-asserted-by":"crossref","first-page":"1455","DOI":"10.1177\/0278364917735594","volume":"36","author":"A Ten Pas","year":"2017","unstructured":"Ten Pas, A., Gualtieri, M., Saenko, K., Platt, R.: Grasp pose detection in point clouds. Int. J. Robot. Res. 36(13\u201314), 1455\u20131473 (2017)","journal-title":"Int. J. Robot. Res."},{"key":"2379_CR21","doi-asserted-by":"crossref","unstructured":"Liang, H., Ma,X., Li, S., G\u00f6rner, M., Tang, S., Fang, B., Sun, F., Zhang, J.: Pointnetgpd: detecting grasp configurations from point sets. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 3629\u20133635. IEEE (2019)","DOI":"10.1109\/ICRA.2019.8794435"},{"key":"2379_CR22","unstructured":"Zhou, Y., Hauser, K.: 6dof grasp planning by optimizing a deep learning scoring function. In Robotics: Science and systems (RSS) Workshop on Revisiting Contact-Turning a Problem into a Solution, vol. 2, p. 6 (2017)"},{"key":"2379_CR23","doi-asserted-by":"crossref","unstructured":"Murali, A., Mousavian, A., Eppner, C., Paxton, C., Fox, D.: 6-dof grasping for target-driven object manipulation in clutter. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 6232\u20136238. IEEE (2020)","DOI":"10.1109\/ICRA40945.2020.9197318"},{"key":"2379_CR24","doi-asserted-by":"crossref","unstructured":"Liang, H., et al.: PointNetGPD: Detecting grasp configurations from point sets. In: Proc. Int. Conf. Robot. Autom. (ICRA), pp. 3629\u20133635 (2019)","DOI":"10.1109\/ICRA.2019.8794435"},{"key":"2379_CR25","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation. In: Proc. IEEE Conf.Comput. Vis. Pattern Recognit. (CVPR), pp. 652\u2013660 (2017)"},{"key":"2379_CR26","doi-asserted-by":"crossref","unstructured":"Lou, X., Yang, Y., Choi, C.: Learning object relations with graph neural networks for target-driven grasping in dense clutter. In: Proc. Int. Conf. Robot. Autom. (ICRA), pp. 742\u2013748 (2022)","DOI":"10.1109\/ICRA46639.2022.9811601"},{"key":"2379_CR27","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1007\/s00530-026-02224-x","volume":"32","author":"B Wang","year":"2026","unstructured":"Wang, B., Fang, M., Wang, N., et al.: Mamba and wavelet-enhanced dual-modal domain adaptation for grasp detection. Multimedia Syst. 32, 163 (2026). https:\/\/doi.org\/10.1007\/s00530-026-02224-x","journal-title":"Multimedia Syst."},{"issue":"131744","key":"2379_CR28","first-page":"0957","volume":"314","author":"B Wang","year":"2026","unstructured":"Wang, B., Wang, X., Fang, M., Li, H., Wang, H.: Eye-to-action: real-time robotic grasping via lightweight gaze estimation. Expert Syst. Appl. 314(131744), 0957\u20134174 (2026)","journal-title":"Expert Syst. Appl."},{"key":"2379_CR29","doi-asserted-by":"crossref","unstructured":"Lu, Y., Deng, B., Wang, Z., Zhi, P., Li, Y., Wang, S.: Hybrid physical metric for 6-DoF grasp pose detection. In: Proc. Int. Conf. Robot. Autom., pp. 8238\u20138244 (2022)","DOI":"10.1109\/ICRA46639.2022.9811961"},{"key":"2379_CR30","doi-asserted-by":"crossref","unstructured":"Dai, Q., Zhu, Y., Geng, Y., Ruan, C., Zhang, J., Wang, H.: Graspnerf: multiview-based 6-dof grasp detection for transparent and specular objects using generalizable nerf. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 1757\u20131763. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10160842"},{"key":"2379_CR31","doi-asserted-by":"crossref","unstructured":"Gou, M., Fang, H.-S., Zhu, Z., Xu, S., Wang, C., Lu, C.: RGB matters: Learning 7-DoF grasp poses on monocular RGBD images. In: Proc. IEEE Int. Conf. Robot. Autom. (ICRA), pp. 13459\u201313466 (2021)","DOI":"10.1109\/ICRA48506.2021.9561409"},{"key":"2379_CR32","doi-asserted-by":"crossref","unstructured":"Hoang, D.-C., Stork, J.A., Stoyanov, T.: Context-aware grasp generation in cluttered scenes. In: Proc. Int. Conf. Robot. Autom. (ICRA), pp. 1492\u20131498 (2022)","DOI":"10.1109\/ICRA46639.2022.9811371"},{"key":"2379_CR33","doi-asserted-by":"crossref","unstructured":"Wang, H., Niu, W., Zhuang, C.: GraNet: a multi-level graph network for 6-DoF grasp pose generation in cluttered scenes. In: Proc. IEEE\/RSJ Int. Conf. Intell. Robots Syst. (IROS), pp. 937\u2013943 (2023)","DOI":"10.1109\/IROS55552.2023.10341549"},{"key":"2379_CR34","doi-asserted-by":"crossref","unstructured":"Duanmu, H., An, K., Zhang, H., Liu, X.: 7-DoF grasping pose estimation based on advanced feature aggregation mechanism. In: Proc. 7th Int. Conf. Electron. Technol. (ICET), pp. 667\u2013673 (2024)","DOI":"10.1109\/ICET61945.2024.10673130"},{"key":"2379_CR35","doi-asserted-by":"publisher","unstructured":"Wang, L., Zhang, Y., Zhu, S., et al.: Improving grasp pose detection by implicitly utilizing geometric information and spatial relations of objects in clutter. IEEE Trans. Instrum. Meas. (2025). https:\/\/doi.org\/10.1109\/TIM.2025.3550952","DOI":"10.1109\/TIM.2025.3550952"},{"key":"2379_CR36","doi-asserted-by":"crossref","unstructured":"Wang, H., Zhang, Y., Wang, Y., et al.: 6-DoF grasp detection in clutter with enhanced receptive field and graspable balance sampling. In: 2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3000\u20133007. IEEE (2024)","DOI":"10.1109\/IROS58592.2024.10802025"},{"key":"2379_CR37","unstructured":"Lin Z., et al.: A structured self-attentive sentence embedding. arXiv Preprint (2017). arXiv:1703.03130"},{"key":"2379_CR38","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proc. Adv. Neural Inf. Process. Syst., vol. 30, June 2017, pp. 5998\u20136008 (2017)"},{"issue":"2","key":"2379_CR39","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1007\/s41095-021-0229-5","volume":"7","author":"M-H Guo","year":"2021","unstructured":"Guo, M.-H., Cai, J.-X., Liu, Z.-N., Mu, T.-J., Martin, R.R., Hu, S.-M.: PCT: point cloud transformer. Comput. Vis. Media 7(2), 187\u2013199 (2021)","journal-title":"Comput. Vis. Media"},{"key":"2379_CR40","doi-asserted-by":"crossref","unstructured":"Yan, X., Zheng, C., Li, Z., Wang, S., Cui, S.: PointASNL: Robust point clouds processing using nonlocal neural networks with adaptive sampling. In: Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), pp. 5589\u20135598 (2020)","DOI":"10.1109\/CVPR42600.2020.00563"},{"key":"2379_CR41","doi-asserted-by":"crossref","unstructured":"Liu, Z., Chen, Z., Xie, S., Zheng, W.: TransGrasp: a multi-scale hierarchical point transformer for 7-DoF grasp detection. In: Proc. Int. Conf. Robot. Autom. (ICRA), pp. 1533\u20131539 (2022)","DOI":"10.1109\/ICRA46639.2022.9812001"},{"key":"2379_CR42","doi-asserted-by":"crossref","unstructured":"Chen, C.-F.R., Fan, Q., Panda, R.: Crossvit: Cross-attention multi-scale vision transformer for image classification. Proceedings of the IEEE\/CVF international conference on computer vision. (2021)","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"2379_CR43","doi-asserted-by":"crossref","unstructured":"Lin, H., et al.: Cat: Cross attention in vision transformer. In: 2022 IEEE International Conference on Multimedia and Expo (ICME). IEEE (2022)","DOI":"10.1109\/ICME52920.2022.9859720"},{"key":"2379_CR44","doi-asserted-by":"crossref","unstructured":"Choy, C., Gwak, J., Savarese, S.: 4D spatio-temporal ConvNets: Minkowski convolutional neural networks. In: Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), pp. 3075\u20133084 (2019)","DOI":"10.1109\/CVPR.2019.00319"},{"key":"2379_CR45","doi-asserted-by":"crossref","unstructured":"YU, S., ZHAI, Di.-Hua., XIA, Y.: MTGrasp: multiscale 6-DoF robotic grasp detection. IEEE\/ASME Trans. Mechatron. 30(1), 156\u2013167 (2024)","DOI":"10.1109\/TMECH.2024.3391917"},{"key":"2379_CR46","doi-asserted-by":"crossref","unstructured":"Morrison, D., Leitner, J., Corke, P.: Closing the loop for robotic grasping: a real-time, generative grasp synthesis approach. In: Proc. Robot., Sci. Syst. (RSS) (2018). https:\/\/www.roboticsproceedings.org\/rss14\/p21.html","DOI":"10.15607\/RSS.2018.XIV.021"},{"issue":"4","key":"2379_CR47","doi-asserted-by":"publisher","first-page":"3355","DOI":"10.1109\/LRA.2018.2852777","volume":"3","author":"F-J Chu","year":"2018","unstructured":"Chu, F.-J., Xu, R., Vela, P.A.: Real-world multiobject, multigrasp detection. IEEE Robot. Autom. Lett. 3(4), 3355\u20133362 (2018)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"2379_CR48","doi-asserted-by":"crossref","unstructured":"Li, Y., Kong, T., Chu, R., Li, Y., Wang, P., Li, L.: Simultaneous semantic and collision learning for 6-DoF grasp pose estimation. In: Proc. IEEE\/RSJ Int. Conf. Intell. Robots Syst. (IROS), pp. 3571\u20133578 (2021)","DOI":"10.1109\/IROS51168.2021.9636012"},{"key":"2379_CR49","doi-asserted-by":"crossref","unstructured":"Zhuang, C., Wang, H., Niu, W., Ding, H.: A parallel graph network for generating 7-DoF model-free grasps in unstructured scenes using point cloud. In: Robot. Comput.-Integr. Manuf., vol. 92, p. 102879 (2025)","DOI":"10.1016\/j.rcim.2024.102879"},{"key":"2379_CR50","doi-asserted-by":"crossref","unstructured":"Woo, S., et al.: CBAM: convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01234-2_1"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02379-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-026-02379-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02379-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T12:55:21Z","timestamp":1784724921000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-026-02379-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,6]]},"references-count":50,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["2379"],"URL":"https:\/\/doi.org\/10.1007\/s00530-026-02379-7","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,6]]},"assertion":[{"value":"13 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no conflict of interest.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"329"}}