{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T02:04:01Z","timestamp":1791165841093,"version":"4.1.0"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:00:00Z","timestamp":1760313600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:00:00Z","timestamp":1760313600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376014"],"award-info":[{"award-number":["62376014"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172022"],"award-info":[{"award-number":["62172022"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Foundation for China University Industry-University-Research Innovation","award":["No.2021JQR023"],"award-info":[{"award-number":["No.2021JQR023"]}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["No.2021ZD0111902"],"award-info":[{"award-number":["No.2021ZD0111902"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s00530-025-02005-y","type":"journal-article","created":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T05:41:50Z","timestamp":1760334110000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Bcgn: BLIP-based cross-modal grasping network for language-conditioned robotic grasping"],"prefix":"10.1007","volume":"31","author":[{"given":"Kai","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lichun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianjia","family":"Xin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baocai","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,13]]},"reference":[{"key":"2005_CR1","doi-asserted-by":"crossref","unstructured":"Lamon, E., Leonori, M., Kim, W., Ajoudani, A.: Towards an intelligent collaborative robotic system for mixed case palletizing. In: Proc. ICRA, pp. 9128\u20139134 (2020)","DOI":"10.1109\/ICRA40945.2020.9196850"},{"key":"2005_CR2","first-page":"100006","volume":"2","author":"E Adamopoulou","year":"2020","unstructured":"Adamopoulou, E., Moussiades, L.: Chatbots: history, technology, and applications. Machine Learning Appl 2, 100006 (2020)","journal-title":"Machine Learning Appl"},{"key":"2005_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127475","volume":"581","author":"H Zhang","year":"2024","unstructured":"Zhang, H., Wang, L., Li, S., Xu, K., Yin, B.: Area-keywords cross-modal alignment for referring image segmentation. Neurocomputing 581, 127475 (2024)","journal-title":"Neurocomputing"},{"issue":"5","key":"2005_CR4","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1007\/s00530-024-01470-1","volume":"30","author":"Y Zhang","year":"2024","unstructured":"Zhang, Y., Song, Z., Hu, Z.: Exploring coherence from heterogeneous representations for ocr image captioning. Multimedia Syst. 30(5), 262 (2024)","journal-title":"Multimedia Syst."},{"issue":"4","key":"2005_CR5","doi-asserted-by":"publisher","first-page":"2073","DOI":"10.1007\/s00530-023-01097-8","volume":"29","author":"X Xu","year":"2023","unstructured":"Xu, X., Lv, G., Sun, Y., Hu, Y., Nian, F.: Hierarchical cross-modal contextual attention network for visual grounding. Multimedia Syst. 29(4), 2073\u20132083 (2023)","journal-title":"Multimedia Syst."},{"key":"2005_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y., Xu, R., Lin, Y., Vela, P.A.: A joint network for grasp detection conditioned on natural language commands. In: Proc. ICRA, pp. 4576\u20134582 (2021)","DOI":"10.1109\/ICRA48506.2021.9561994"},{"key":"2005_CR7","doi-asserted-by":"crossref","unstructured":"Kang, G.-C., Kim, J., Kim, J., Zhang, B.-T.: Prograsp: Pragmatic human-robot communication for object grasping. In: Proc. ICRA, pp. 3304\u20133310 (2024)","DOI":"10.1109\/ICRA57147.2024.10610543"},{"key":"2005_CR8","unstructured":"Tziafas, G., Xu, Y., Goel, A., Kasaei, M., Li, Z., Kasaei, H.: Language-guided robot grasping: Clip-based referring grasp synthesis in clutter. arXiv preprint arXiv:2311.05779 (2023)"},{"key":"2005_CR9","doi-asserted-by":"crossref","unstructured":"Vuong, A.D., Vu, M.N., Le, H., Huang, B., Huynh, B., Vo, T., Kugi, A., Nguyen, A.: Grasp-anything: Large-scale grasp dataset from foundation models. In: Proc. ICRA, pp. 14030\u201314037 (2024)","DOI":"10.1109\/ICRA57147.2024.10611277"},{"key":"2005_CR10","doi-asserted-by":"crossref","unstructured":"Lu, Y., Fan, Y., Deng, B., Liu, F., Li, Y., Wang, S.: Vl-grasp: a 6-dof interactive grasp policy for language-oriented objects in cluttered indoor scenes. In: Proc. IROS, pp. 976\u2013983 (2023). IEEE","DOI":"10.1109\/IROS55552.2023.10341379"},{"key":"2005_CR11","doi-asserted-by":"crossref","unstructured":"Depierre, A., Dellandr\u00e9a, E., Chen, L.: Jacquard: A large scale dataset for robotic grasp detection. In: Proc. IROS, pp. 3511\u20133516 (2018)","DOI":"10.1109\/IROS.2018.8593950"},{"key":"2005_CR12","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: Proc. CVPR, pp. 11444\u201311453 (2020)","DOI":"10.1109\/CVPR42600.2020.01146"},{"key":"2005_CR13","unstructured":"Jiang, Y., Moseson, S., Saxena, A.: Efficient grasping from rgbd images: Learning using a new rectangle representation. In: Proc. ICRA, pp. 3304\u20133311 (2011)"},{"key":"2005_CR14","doi-asserted-by":"crossref","unstructured":"Mahler, J., Liang, J., Niyaz, S., Laskey, M., Doan, R., Liu, X., Ojea, J.A., Goldberg, K.: Dex-net 2.0: Deep learning to plan robust grasps with synthetic point clouds and analytic grasp metrics. arXiv preprint arXiv:1703.09312 (2017)","DOI":"10.15607\/RSS.2017.XIII.058"},{"key":"2005_CR15","doi-asserted-by":"crossref","unstructured":"Zhang, H., Lan, X., Bai, S., Zhou, X., Tian, Z., Zheng, N.: Roi-based robotic grasp detection for object overlapping scenes. In: Proc. IROS, pp. 4768\u20134775 (2019)","DOI":"10.1109\/IROS40897.2019.8967869"},{"key":"2005_CR16","doi-asserted-by":"publisher","first-page":"705","DOI":"10.1177\/0278364914549607","volume":"34","author":"I Lenz","year":"2015","unstructured":"Lenz, I., Lee, H., Saxena, A.: Deep learning for detecting robotic grasps. Int J Robotics Res 34, 705\u2013724 (2015)","journal-title":"Int J Robotics Res"},{"key":"2005_CR17","doi-asserted-by":"crossref","unstructured":"Ainetter, S., Fraundorfer, F.: End-to-end trainable deep neural network for robotic grasp detection and semantic segmentation from rgb. In: Proc. ICRA, pp. 13452\u201313458 (2021)","DOI":"10.1109\/ICRA48506.2021.9561398"},{"key":"2005_CR18","doi-asserted-by":"crossref","unstructured":"Redmon, J., Angelova, A.: Real-time grasp detection using convolutional neural networks. In: Proc. ICRA, pp. 1316\u20131322 (2015)","DOI":"10.1109\/ICRA.2015.7139361"},{"key":"2005_CR19","doi-asserted-by":"crossref","unstructured":"Kumra, S., Kanan, C.: Robotic grasp detection using deep convolutional neural networks. In: Proc. IROS, pp. 769\u2013776 (2017)","DOI":"10.1109\/IROS.2017.8202237"},{"key":"2005_CR20","doi-asserted-by":"crossref","unstructured":"Kumra, S., Joshi, S., Sahin, F.: Antipodal robotic grasping using generative residual convolutional neural network. In: Proc. IROS, pp. 9626\u20139633 (2020)","DOI":"10.1109\/IROS45743.2020.9340777"},{"issue":"8","key":"2005_CR21","doi-asserted-by":"publisher","first-page":"4002","DOI":"10.1109\/TCSVT.2023.3237866","volume":"33","author":"G Ren","year":"2023","unstructured":"Ren, G., Geng, W., Guan, P., Cao, Z., Yu, J.: Pixel-wise grasp detection via twin deconvolution and multi-dimensional attention. IEEE Trans. Circuits Syst. Video Technol. 33(8), 4002\u20134010 (2023)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"2005_CR22","doi-asserted-by":"crossref","unstructured":"Morrison, D., Corke, P., Leitner, J.: Closing the loop for robotic grasping: A real-time, generative grasp synthesis approach. arXiv preprint arXiv:1804.05172 (2018)","DOI":"10.15607\/RSS.2018.XIV.021"},{"key":"2005_CR23","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In: Proc. ICML, pp. 12888\u201312900 (2022)"},{"key":"2005_CR24","unstructured":"Li, D., Li, J., Hoi, S.: Blip-diffusion: Pre-trained subject representation for controllable text-to-image generation and editing. NeurIPS 36 (2024)"},{"key":"2005_CR25","doi-asserted-by":"crossref","unstructured":"Wattasseril, J.I., Shekhar, S., D\u00f6llner, J., Trapp, M.: Zero-shot video moment retrieval using blip-based models. In: Proc. ISVC, pp. 160\u2013171 (2023)","DOI":"10.1007\/978-3-031-47969-4_13"},{"key":"2005_CR26","doi-asserted-by":"crossref","unstructured":"Wang, Z., Lu, Y., Li, Q., Tao, X., Guo, Y., Gong, M., Liu, T.: Cris: Clip-driven referring image segmentation. In: Proc. CVPR, pp. 11686\u201311695 (2022)","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"2005_CR27","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. NeurIPS 30 (2017)"},{"key":"2005_CR28","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"2005_CR29","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proc. CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"2005_CR30","unstructured":"Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F.L., Almeida, D., Altenschmidt, J., Altman, S., Anadkat, S., et al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"2005_CR31","unstructured":"Bai, J., Bai, S., Yang, S., Wang, S., Tan, S., Wang, P., Lin, J., Zhou, C., Zhou, J.: Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond. arXiv preprint arXiv:2308.12966 (2023)"},{"key":"2005_CR32","doi-asserted-by":"crossref","unstructured":"Yu, L., Poirson, P., Yang, S., Berg, A.C., Berg, T.L.: Modeling context in referring expressions. In: Proc. ECCV, pp. 69\u201385 (2016)","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"2005_CR33","doi-asserted-by":"crossref","unstructured":"Xu, Z., Chen, Z., Zhang, Y., Song, Y., Wan, X., Li, G.: Bridging vision and language encoders: Parameter-efficient tuning for referring image segmentation. In: Proc. ICCV, pp. 17503\u201317512 (2023)","DOI":"10.1109\/ICCV51070.2023.01605"},{"key":"2005_CR34","doi-asserted-by":"crossref","unstructured":"Yadollahi, E., Romeo, M., Dogan, F.I., Johal, W., De\u00a0Graaf, M., Levy-Tzedek, S., Leite, I.: Explainability for human-robot collaboration. In: Companion of the 2024 ACM\/IEEE International Conference on Human-Robot Interaction, pp. 1364\u20131366 (2024)","DOI":"10.1145\/3610978.3638154"},{"key":"2005_CR35","unstructured":"Cambria, E., Malandri, L., Mercorio, F., Nobani, N., Seveso, A.: Xai meets llms: A survey of the relation between explainable ai and large language models. arXiv preprint arXiv:2407.15248 (2024)"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-02005-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-025-02005-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-02005-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T06:58:30Z","timestamp":1766127510000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-025-02005-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,13]]},"references-count":35,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["2005"],"URL":"https:\/\/doi.org\/10.1007\/s00530-025-02005-y","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,13]]},"assertion":[{"value":"23 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 August 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 October 2025","order":3,"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 no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"433"}}