{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T20:07:25Z","timestamp":1789157245656,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032374288","type":"print"},{"value":"9783032374295","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-37429-5_8","type":"book-chapter","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T19:13:42Z","timestamp":1789154022000},"page":"112-130","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["RoboGesture: Real-Time Semantic-Aligned Co-speech Gestures Generation for Humanoid Interaction"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3987-722X","authenticated-orcid":false,"given":"Zifan","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9099-5334","authenticated-orcid":false,"given":"Ziang","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0379-5648","authenticated-orcid":false,"given":"Pengyang","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8982-3376","authenticated-orcid":false,"given":"Zirui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0207-8431","authenticated-orcid":false,"given":"Chenghuai","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1428-7641","authenticated-orcid":false,"given":"Tianze","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2554-5141","authenticated-orcid":false,"given":"Zekun","family":"Qi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2310-211X","authenticated-orcid":false,"given":"Liangliang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3365-4620","authenticated-orcid":false,"given":"He","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9319-0354","authenticated-orcid":false,"given":"Li","family":"Yi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"issue":"4","key":"8_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592458","volume":"42","author":"S Alexanderson","year":"2023","unstructured":"Alexanderson, S., Nagy, R., Beskow, J., Henter, G.E.: Listen, denoise, action! audio-driven motion synthesis with diffusion models. ACM Trans. Graph. (TOG) 42(4), 1\u201320 (2023)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"8_CR2","doi-asserted-by":"publisher","unstructured":"Ao, T., Zhang, Z., Liu, L.: GestureDiffuCLIP: gesture diffusion model with clip latents. ACM Trans. Graph. https:\/\/doi.org\/10.1145\/3592097","DOI":"10.1145\/3592097"},{"key":"8_CR3","unstructured":"Araujo, J.P., Ze, Y., Xu, P., Wu, J., Liu, C.K.: Retargeting matters: general motion retargeting for humanoid motion tracking. arXiv preprint arXiv:2510.02252 (2025)"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Bettosi, C., Baillie, L., Ross, M.K., Broz, F.: A systematic approach to modeling structured behavior in social robots. In: Proceedings of the 2024 International Symposium on Technological Advances in Human-Robot Interaction, pp. 29\u201337 (2024)","DOI":"10.1145\/3648536.3648540"},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"Cai, Z., et al.: Digital life project: autonomous 3D characters with social intelligence. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 582\u2013592 (2024)","DOI":"10.1109\/CVPR52733.2024.00062"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Cao, C., Zhang, Y., Wu, Y., Lu, H., Cheng, J.: Egocentric gesture recognition using recurrent 3D convolutional neural networks with spatiotemporal transformer modules. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3763\u20133771 (2017)","DOI":"10.1109\/ICCV.2017.406"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Cao, L.: AI robots and humanoid AI: review, perspectives and directions. arXiv preprint arXiv:2405.15775 (2024)","DOI":"10.2139\/ssrn.4897361"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Chen, J., Liu, Y., Wang, J., Zeng, A., Li, Y., Chen, Q.: DiffSHEG: a diffusion-based approach for real-time speech-driven holistic 3D expression and gesture generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7352\u20137361 (2024)","DOI":"10.1109\/CVPR52733.2024.00702"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Huang, S.: HoleGest: decoupled diffusion and motion priors for generating holisticly expressive co-speech gestures. In: 2025 International Conference on 3D Vision (3DV), pp. 748\u2013757. IEEE (2025)","DOI":"10.1109\/3DV66043.2025.00074"},{"key":"8_CR10","unstructured":"Comanici, G., et al.: Gemini 2.5: pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. arXiv preprint arXiv:2507.06261 (2025)"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Dafarra, S., et al.: iCub3 avatar system: enabling remote fully immersive embodiment of humanoid robots. Sci. Robot. 9(86), eadh3834 (2024)","DOI":"10.1126\/scirobotics.adh3834"},{"key":"8_CR12","unstructured":"D\u00e9fossez, A., et al.: Moshi: a speech-text foundation model for real-time dialogue. Tech. rep. arXiv:2410.00037 (2024)"},{"key":"8_CR13","doi-asserted-by":"publisher","first-page":"1581024","DOI":"10.3389\/frobt.2025.1581024","volume":"12","author":"A Galatolo","year":"2025","unstructured":"Galatolo, A., Winkle, K.: Simultaneous text and gesture generation for social robots with small language models. Front. Robot. AI 12, 1581024 (2025)","journal-title":"Front. Robot. AI"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Ghorbani, S., Ferstl, Y., Holden, D., Troje, N.F., Carbonneau, M.A.: ZeroEGGS: zero-shot example-based gesture generation from speech. In: Computer Graphics Forum, vol. 42, pp. 206\u2013216. Wiley Online Library (2023)","DOI":"10.1111\/cgf.14734"},{"issue":"1\u20132","key":"8_CR15","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1016\/j.cognition.2002.06.001","volume":"92","author":"P Indefrey","year":"2004","unstructured":"Indefrey, P., Levelt, W.J.: The spatial and temporal signatures of word production components. Cognition 92(1\u20132), 101\u2013144 (2004)","journal-title":"Cognition"},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Jiang, J., et al.: SOLAMI: social vision-language-action modeling for immersive interaction with 3D autonomous characters. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 26887\u201326898 (2025)","DOI":"10.1109\/CVPR52734.2025.02504"},{"key":"8_CR17","unstructured":"Kipp, M.: Gesture Generation by Imitation: From Human Behavior to Computer Character Animation. Universal-Publishers (2005)"},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"Levine, S., Kr\u00e4henb\u00fchl, P., Thrun, S., Koltun, V.: Gesture controllers. In: ACM SIGGRAPH 2010 Papers, pp. 1\u201311 (2010)","DOI":"10.1145\/1833349.1778861"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Li, J., et al.: Audio2Gestures: generating diverse gestures from speech audio with conditional variational autoencoders. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11293\u201311302 (2021)","DOI":"10.1109\/ICCV48922.2021.01110"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Li, R., Yang, S., Ross, D.A., Kanazawa, A.: AI choreographer: music conditioned 3D dance generation with AIST (2021)","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"8_CR21","unstructured":"Lipman, Y., Chen, R.T.Q., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. arXiv:2210.02747 (2023)"},{"key":"8_CR22","doi-asserted-by":"publisher","unstructured":"Liu, H., et al.: BEAT: a large-scale semantic and emotional multi-modal dataset for conversational gestures synthesis. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) European Conference on Computer Vision, pp. 612\u2013630. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20071-7_36","DOI":"10.1007\/978-3-031-20071-7_36"},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Liu, L., Ghaleb, E., Ozyurek, A., Yumak, Z.: SemGes: semantics-aware co-speech gesture generation using semantic coherence and relevance learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13963\u201313973 (2025)","DOI":"10.1109\/ICCV51701.2025.01296"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Mascaro, E.V., Yan, Y., Lee, D.: Robot interaction behavior generation based on social motion forecasting for human-robot interaction. In: 2024 IEEE International Conference on Robotics and Automation (ICRA), pp. 17264\u201317271. IEEE (2024)","DOI":"10.1109\/ICRA57147.2024.10610682"},{"issue":"3","key":"8_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3729539","volume":"14","author":"K Matheus","year":"2025","unstructured":"Matheus, K., Ramnauth, R., Scassellati, B., Salomons, N.: Long-term interactions with social robots: trends, insights, and recommendations. ACM Trans. Hum.-Robot Interact. 14(3), 1\u201342 (2025)","journal-title":"ACM Trans. Hum.-Robot Interact."},{"key":"8_CR26","unstructured":"McNeill, D.: Hand and Mind: What Gestures Reveal About Thought. University of Chicago Press (1992)"},{"key":"8_CR27","unstructured":"OpenAI: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"8_CR28","first-page":"356","volume":"91","author":"E Parizet","year":"2005","unstructured":"Parizet, E., Hamzaoui, N., Sabatie, G.: Comparison of some listening test methods: a case study. Acta Acust. Acust. 91, 356\u2013364 (2005)","journal-title":"Acta Acust. Acust."},{"key":"8_CR29","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4195\u20134205 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"8_CR30","doi-asserted-by":"crossref","unstructured":"Perez, E., Strub, F., De Vries, H., Dumoulin, V., Courville, A.: Film: visual reasoning with a general conditioning layer. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"8_CR31","doi-asserted-by":"crossref","unstructured":"Qin, Y., et al.: AnyTeleop: a general vision-based dexterous robot arm-hand teleoperation system. Robot. Sci. Syst. (2023)","DOI":"10.15607\/RSS.2023.XIX.015"},{"key":"8_CR32","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"8_CR33","doi-asserted-by":"crossref","unstructured":"Scherf, L., Fr\u00f6hlich, K., Koert, D.: Learning action conditions for automatic behavior tree generation from human demonstrations. In: Companion of the 2024 ACM\/IEEE International Conference on Human-Robot Interaction, pp. 950\u2013954 (2024)","DOI":"10.1145\/3610978.3640673"},{"key":"8_CR34","doi-asserted-by":"crossref","unstructured":"Tagliamonte, C., Maccaline, D., LeMasurier, G., Yanco, H.A.: A generalizable architecture for explaining robot failures using behavior trees and large language models. In: Companion of the 2024 ACM\/IEEE International Conference on Human-Robot Interaction, pp. 1038\u20131042 (2024)","DOI":"10.1145\/3610978.3640551"},{"key":"8_CR35","doi-asserted-by":"crossref","unstructured":"Valls Mascaro, E., Lee, D.: Robot behavior generation for social human-robot interaction. Int. J. Soc. Robot. 1\u201320 (2025)","DOI":"10.1007\/s12369-025-01333-3"},{"key":"8_CR36","doi-asserted-by":"crossref","unstructured":"Wang, Z., Chen, J., Chen, Z., Xie, P., Chen, R., Yi, L.: GenH2R: learning generalizable human-to-robot handover via scalable simulation demonstration and imitation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16362\u201316372 (2024)","DOI":"10.1109\/CVPR52733.2024.01548"},{"key":"8_CR37","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: MobileH2R: learning generalizable human to mobile robot handover exclusively from scalable and diverse synthetic data. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 17315\u201317325 (2025)","DOI":"10.1109\/CVPR52734.2025.01614"},{"key":"8_CR38","unstructured":"Yang, L., et al.: OmniRetarget: interaction-preserving data generation for humanoid whole-body loco-manipulation and scene interaction. arXiv preprint arXiv:2509.26633 (2025)"},{"key":"8_CR39","doi-asserted-by":"publisher","unstructured":"Yang, S., et al.: DiffuseStyleGesture: stylized audio-driven co-speech gesture generation with diffusion models. In: Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI-23, pp. 5860\u20135868. International Joint Conferences on Artificial Intelligence Organization (2023). https:\/\/doi.org\/10.24963\/ijcai.2023\/650","DOI":"10.24963\/ijcai.2023\/650"},{"issue":"6","key":"8_CR40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3414685.3417838","volume":"39","author":"Y Yoon","year":"2020","unstructured":"Yoon, Y., et al.: Speech gesture generation from the trimodal context of text, audio, and speaker identity. ACM Trans. Graph. (TOG) 39(6), 1\u201316 (2020)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"8_CR41","doi-asserted-by":"crossref","unstructured":"Yoon, Y., Ko, W.R., Jang, M., Lee, J., Kim, J., Lee, G.: Robots learn social skills: end-to-end learning of co-speech gesture generation for humanoid robots. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 4303\u20134309. IEEE (2019)","DOI":"10.1109\/ICRA.2019.8793720"},{"key":"8_CR42","unstructured":"Ze, Y., Ara\u00fajo, J.P., Wu, J., Liu, C.K.: GMR: general motion retargeting (2025). https:\/\/github.com\/YanjieZe\/GMR, gitHub repository"},{"key":"8_CR43","unstructured":"Zhang, X., et al.: PersonaGesture: single-reference co-speech gesture personalization for unseen speakers. arXiv preprint arXiv:2605.06064 (2026)"},{"key":"8_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, X., Li, J., Ren, J., Zhang, J.: Mitigating error accumulation in co-speech motion generation via global rotation diffusion and multi-level constraints. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 40, pp. 12834\u201312842 (2026)","DOI":"10.1609\/aaai.v40i15.38281"},{"key":"8_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, X., et al.: SemTalk: holistic co-speech motion generation with frame-level semantic emphasis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13761\u201313771 (2025)","DOI":"10.1109\/ICCV51701.2025.01277"},{"key":"8_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, X., Li, J., Zhang, J., Ren, J., Bo, L., Tu, Z.: EchoMask: speech-queried attention-based mask modeling for holistic co-speech motion generation. In: Proceedings of the 33rd ACM International Conference on Multimedia, pp. 10827\u201310836 (2025)","DOI":"10.1145\/3746027.3754847"},{"issue":"5","key":"8_CR47","doi-asserted-by":"publisher","first-page":"1038","DOI":"10.1109\/TMM.2018.2808769","volume":"20","author":"Y Zhang","year":"2018","unstructured":"Zhang, Y., Cao, C., Cheng, J., Lu, H.: EgoGesture: a new dataset and benchmark for egocentric hand gesture recognition. IEEE Trans. Multimedia 20(5), 1038\u20131050 (2018)","journal-title":"IEEE Trans. Multimedia"},{"issue":"4","key":"8_CR48","first-page":"1","volume":"43","author":"Z Zhang","year":"2024","unstructured":"Zhang, Z., et al.: Semantic gesticulator: semantics-aware co-speech gesture synthesis. ACM Trans. Graph. (TOG) 43(4), 1\u201317 (2024)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"8_CR49","doi-asserted-by":"crossref","unstructured":"Zhi, Y., et al.: LivelySpeaker: towards semantic-aware co-speech gesture generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 20807\u201320817 (2023)","DOI":"10.1109\/ICCV51070.2023.01902"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37429-5_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T19:13:53Z","timestamp":1789154033000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37429-5_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032374288","9783032374295"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37429-5_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"12 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}