{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:07:10Z","timestamp":1788934030888,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":54,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373687","type":"print"},{"value":"9783032373694","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\/978-3-032-37369-4_23","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T05:45:35Z","timestamp":1788932735000},"page":"424-441","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["EgoMAN: Interaction-Structured Reasoning for\u00a0Egocentric 3D Hand Trajectory Prediction"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1378-4549","authenticated-orcid":false,"given":"Mingfei","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8246-2254","authenticated-orcid":false,"given":"Yifan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0868-2141","authenticated-orcid":false,"given":"Zhengqin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5056-8516","authenticated-orcid":false,"given":"Homanga","family":"Bharadhwaj","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3709-6125","authenticated-orcid":false,"given":"Yujin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuan","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9916-0930","authenticated-orcid":false,"given":"Ziyi","family":"Kou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0750-5442","authenticated-orcid":false,"given":"Yuan","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7715-7557","authenticated-orcid":false,"given":"Eric","family":"Whitmire","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rajinder","family":"Sodhi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2059-3558","authenticated-orcid":false,"given":"Hrvoje","family":"Benko","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3136-4531","authenticated-orcid":false,"given":"Eli","family":"Shlizerman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"23_CR1","doi-asserted-by":"crossref","unstructured":"Bahl, S., Mendonca, R., Chen, L., Jain, U., Pathak, D.: Affordances from human videos as a versatile representation for robotics. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01324"},{"key":"23_CR2","unstructured":"Bai, S., et\u00a0al.: Qwen2.5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"23_CR3","unstructured":"Banerjee, P., et al.: Introducing hot3d: an egocentric dataset for 3d hand and object tracking. arXiv preprint arXiv:2406.09598 (2024)"},{"key":"23_CR4","unstructured":"Bao, C., Xu, J., Wang, X., Gupta, A., Bharadhwaj, H.: Handsonvlm: vision-language models for hand-object interaction prediction. Trans. Mach. Learn. Res. (2025)"},{"key":"23_CR5","doi-asserted-by":"crossref","unstructured":"Bao, W., et al.: Uncertainty-aware state space transformer for egocentric 3d hand trajectory forecasting. In: International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.01260"},{"key":"23_CR6","unstructured":"Bharadhwaj, H., et al.: Gen2act: human video generation in novel scenarios enables generalizable robot manipulation. In: Conference on Robot Learning (2025)"},{"key":"23_CR7","doi-asserted-by":"crossref","unstructured":"Bharadhwaj, H., Gupta, A., Kumar, V., Tulsiani, S.: Towards generalizable zero-shot manipulation via translating human interaction plans. In: 2024 IEEE International Conference on Robotics and Automation (ICRA), pp. 6904\u20136911. IEEE (2024)","DOI":"10.1109\/ICRA57147.2024.10610288"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Bharadhwaj, H., Mottaghi, R., Gupta, A., Tulsiani, S.: Track2act: predicting point tracks from internet videos enables generalizable robot manipulation. In: ECCV (2024)","DOI":"10.1007\/978-3-031-73116-7_18"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Black, K., et al.: $$\\pi _0$$: A vision-language-action flow model for general robot control. Robot. Sci. Syst. XXI (2025)","DOI":"10.15607\/RSS.2025.XXI.010"},{"key":"23_CR10","doi-asserted-by":"crossref","unstructured":"Chen, H., Sun, B., Zhang, A., Pollefeys, M., Leutenegger, S.: VidBot: learning generalizable 3d actions from in-the-wild 2d human videos for zero-shot robotic manipulation. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.02576"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Chen, Z., et\u00a0al.: Internvl: scaling up vision foundation models and aligning for generic visual-linguistic tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24185\u201324198 (2024)","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"23_CR12","unstructured":"Driess, D., et al.: Palm-e: an embodied multimodal language model. In: Proceedings of the 40th International Conference on Machine Learning. ICML 2023, JMLR.org (2023)"},{"key":"23_CR13","unstructured":"Engel, J., et al.: Project aria: a new tool for egocentric multi-modal ai research. arXiv preprint arXiv:2308.13561 (2023)"},{"key":"23_CR14","unstructured":"Grattafiori, A.: The llama 3 herd of models (2024)"},{"key":"23_CR15","unstructured":"Grauman, K., et al.: Ego-exo4d: Understanding skilled human activity from first-and third-person perspectives. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19383\u201319400 (2024)"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Guo, C., Zuo, X., Wang, S., Cheng, L.: Tm2t: stochastic and tokenized modeling for the reciprocal generation of 3d human motions and texts. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19833-5_34"},{"key":"23_CR17","doi-asserted-by":"crossref","unstructured":"Hatano, M., Hachiuma, R., Saito, H.: Emag: ego-motion aware and generalizable 2d hand forecasting from egocentric videos. In: European Conference on Computer Vision Workshops (ECCVW) (2024)","DOI":"10.1007\/978-3-031-91578-9_7"},{"key":"23_CR18","unstructured":"Hatano, M., Zhu, Z., Saito, H., Damen, D.: The invisible egohand: 3d hand forecasting through egobody pose estimation. arXiv preprint arXiv:2504.08654 (2025)"},{"key":"23_CR19","unstructured":"Hoque, R., Huang, P., Yoon, D.J., Sivapurapu, M., Zhang, J.: Egodex: learning dexterous manipulation from large-scale egocentric video. arXiv preprint arXiv:2505.11709 (2025)"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"Hu, M., et al.: Metric3d v2: a versatile monocular geometric foundation model for zero-shot metric depth and surface normal estimation. IEEE Trans. Pattern Anal. Mach. Intell. (2024)","DOI":"10.1109\/TPAMI.2024.3444912"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Kareer, S., et al.: Egomimic: scaling imitation learning via egocentric video. In: 2025 IEEE International Conference on Robotics and Automation (ICRA), pp. 13226\u201313233. IEEE (2025)","DOI":"10.1109\/ICRA55743.2025.11127989"},{"key":"23_CR22","unstructured":"Kim, M., et al.: Openvla: an open-source vision-language-action model. arXiv preprint arXiv:2406.09246 (2024)"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Kwon, T., Tekin, B., St\u00fchmer, J., Bogo, F., Pollefeys, M.: H2o: Two hands manipulating objects for first person interaction recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 10138\u201310148 (2021)","DOI":"10.1109\/ICCV48922.2021.00998"},{"key":"23_CR24","doi-asserted-by":"crossref","unstructured":"Lai, X., et al.: Lisa: reasoning segmentation via large language model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 9579\u20139589 (2024)","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"23_CR25","unstructured":"Lee, J., et\u00a0al.: Molmoact: action reasoning models that can reason in space. arXiv preprint arXiv:2508.07917 (2025)"},{"key":"23_CR26","unstructured":"Li, Q., et\u00a0al.: Scalable vision-language-action model pretraining for robotic manipulation with real-life human activity videos. arXiv preprint arXiv:2510.21571 (2025)"},{"key":"23_CR27","unstructured":"Li, Y., et\u00a0al.: Hamster: hierarchical action models for open-world robot manipulation. arXiv preprint arXiv:2502.05485 (2025)"},{"key":"23_CR28","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Egocentric prediction of action target in 3d. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.02033"},{"key":"23_CR29","unstructured":"Lipman, Y., Chen, R.T.Q., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. In: The Eleventh International Conference on Learning Representations (2023)"},{"key":"23_CR30","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems, p. 36 (2024)","DOI":"10.52202\/075280-1516"},{"key":"23_CR31","doi-asserted-by":"crossref","unstructured":"Liu, M., Tang, S., Li, Y., Rehg, J.M.: Forecasting human-object interaction: joint prediction of motor attention and actions in first person video. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, 23\u201328 August 2020, Proceedings, Part I, vol. 16, pp. 704\u2013721. Springer (2020)","DOI":"10.1007\/978-3-030-58452-8_41"},{"key":"23_CR32","doi-asserted-by":"crossref","unstructured":"Liu, S., Tripathi, S., Majumdar, S., Wang, X.: Joint hand motion and interaction hotspots prediction from egocentric videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00328"},{"key":"23_CR33","unstructured":"Luo, H., et al.: Being-h0: vision-language-action pretraining from large-scale human videos. arXiv preprint arXiv:2507.15597 (2025)"},{"key":"23_CR34","doi-asserted-by":"crossref","unstructured":"Ma, J., Bao, W., Xu, J., Sun, G., Chen, X., Wang, H.: Novel diffusion models for multimodal 3d hand trajectory prediction. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 2408\u20132415 (2025)","DOI":"10.1109\/IROS60139.2025.11246803"},{"key":"23_CR35","unstructured":"Ma, J., Chen, X., Bao, W., Xu, J., Wang, H.: Madiff: motion-aware mamba diffusion models for hand trajectory prediction on egocentric videos (2024)"},{"key":"23_CR36","doi-asserted-by":"crossref","unstructured":"Ma, J., Xu, J., Chen, X., Wang, H.: Diff-ip2d: diffusion-based hand-object interaction prediction on egocentric videos. In: 2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4291\u20134298 (2024)","DOI":"10.1109\/IROS60139.2025.11247704"},{"key":"23_CR37","doi-asserted-by":"crossref","unstructured":"Ma, L., et al.: Nymeria: a massive collection of multimodal egocentric daily motion in the wild. In: the 18th European Conference on Computer Vision (ECCV) (2024)","DOI":"10.1007\/978-3-031-72691-0_25"},{"key":"23_CR38","doi-asserted-by":"crossref","unstructured":"Maaz, M., Rasheed, H., Khan, S., Khan, F.S.: Video-chatgpt: towards detailed video understanding via large vision and language models. arXiv preprint arXiv:2306.05424 (2023)","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"23_CR39","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"23_CR40","unstructured":"OpenAI, et\u00a0al.: Gpt-4 technical report (2024)"},{"key":"23_CR41","doi-asserted-by":"crossref","unstructured":"Pertsch, K., et al.: Fast: efficient action tokenization for vision-language-action models. arXiv preprint arXiv:2501.09747 (2025)","DOI":"10.15607\/RSS.2025.XXI.012"},{"key":"23_CR42","unstructured":"Physical Intelligence, Black, K., et\u00a0al.: $$\\pi _{0.5}$$: a vision\u2013language\u2013action model with open-world generalization. arXiv preprint arXiv:2504.16054 (2025)"},{"key":"23_CR43","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":"23_CR44","doi-asserted-by":"crossref","unstructured":"Rasheed, H., et al.: Glamm: pixel grounding large multimodal model. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2024)","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"23_CR45","unstructured":"Sim\u00e9oni, O., et al.: DINOv3 (2025)"},{"key":"23_CR46","unstructured":"Team, G.: Gemma 3 technical report (2025)"},{"key":"23_CR47","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Holoassist: an egocentric human interaction dataset for interactive ai assistants in the real world. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 20270\u201320281 (2023)","DOI":"10.1109\/ICCV51070.2023.01854"},{"key":"23_CR48","unstructured":"Wen, J., Zhu, Y., Li, J., Tang, Z., Shen, C., Feng, F.: Dexvla: vision-language model with plug-in diffusion expert for general robot control. arXiv preprint arXiv:2502.05855 (2025)"},{"key":"23_CR49","unstructured":"Yang, R., et\u00a0al.: Egovla: learning vision-language-action models from egocentric human videos. arXiv preprint arXiv:2507.12440 (2025)"},{"key":"23_CR50","unstructured":"Yuan, C., Wen, C., Zhang, T., Gao, Y.: General flow as foundation affordance for scalable robot learning. arXiv preprint arXiv:2401.11439 (2024)"},{"key":"23_CR51","doi-asserted-by":"publisher","unstructured":"Zhang, H., et al.: A survey of physical ai: a history from chatgpt to world models and embodied agents. Preprints (2026). https:\/\/doi.org\/10.20944\/preprints202606.0173.v1","DOI":"10.20944\/preprints202606.0173.v1"},{"key":"23_CR52","unstructured":"Zhang, W., et al.: Embodied-reasoner: synergizing visual search, reasoning, and action for embodied interactive tasks. arXiv preprint arXiv:2503.21696 (2025)"},{"key":"23_CR53","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Barnes, C., Lu, J., Yang, J., Li, H.: On the continuity of rotation representations in neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5745\u20135753 (2019)","DOI":"10.1109\/CVPR.2019.00589"},{"key":"23_CR54","unstructured":"Zitkovich, B., et\u00a0al.: Rt-2: vision-language-action models transfer web knowledge to robotic control. In: Conference on Robot Learning, pp. 2165\u20132183. PMLR (2023)"}],"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\/978-3-032-37369-4_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T05:45:48Z","timestamp":1788932748000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37369-4_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373687","9783032373694"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37369-4_23","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":"10 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"}}]}}