{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T15:42:57Z","timestamp":1792856577641,"version":"4.5.0"},"publisher-location":"Cham","reference-count":92,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032375490","type":"print"},{"value":"9783032375506","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\/978-3-032-37550-6_29","type":"book-chapter","created":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T17:23:12Z","timestamp":1789233792000},"page":"502-523","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["CoMind: Understanding Collaborative Human Activity from\u00a0Multiple Minds and\u00a0Views"],"prefix":"10.1007","author":[{"given":"Alexey","family":"Gavryushin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dingxi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhao","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexandros","family":"Delitzas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaqi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ben","family":"Ellis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cedric","family":"Z\u00f6llner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manthan","family":"Patel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manuel","family":"Kaufmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marc","family":"Pollefeys","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,13]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"Farha, A., Richard, Y., Gall, A., J.: When will you do what?-Anticipating temporal occurrences of activities. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5343\u20135352 (2018)","DOI":"10.1109\/CVPR.2018.00560"},{"issue":"3","key":"29_CR2","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1177\/0963721417706392","volume":"26","author":"RB Adams Jr","year":"2017","unstructured":"Adams, R.B., Jr., Albohn, D.N., Kveraga, K.: Social vision: applying a social-functional approach to face and expression perception. Curr. Dir. Psychol. Sci. 26(3), 243\u2013248 (2017)","journal-title":"Curr. Dir. Psychol. Sci."},{"key":"29_CR3","unstructured":"Anthropic: Claude opus 4.5 system card. System card (2025). https:\/\/www.anthropic.com\/claude-opus-4-5-system-card. Accessed 04 Mar 2026"},{"key":"29_CR4","unstructured":"Anthropic: Introducing claude opus 4.6. Anthropic News (2026). https:\/\/www.anthropic.com\/news\/claude-opus-4-6. Accessed 04 Mar 2026"},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Apperly, I.: Mindreaders: the cognitive basis of \u201ctheory of mind\". Psychology Press (2010)","DOI":"10.4324\/9780203833926"},{"key":"29_CR6","unstructured":"Artec 3D: Artec leo: Wireless professional 3d scanner (2024). https:\/\/www.artec3d.com\/portable-3d-scanners\/artec-leo. Accessed 04 Mar 2026"},{"key":"29_CR7","unstructured":"Bai, S., et\u00a0al.: Qwen3-vl technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"Bain, M., Huh, J., Han, T., Zisserman, A.: Whisperx: time-accurate speech transcription of long-form audio (2023). https:\/\/arxiv.org\/abs\/2303.00747","DOI":"10.21437\/Interspeech.2023-78"},{"key":"29_CR9","doi-asserted-by":"crossref","unstructured":"Banerjee, P., et\u00a0al.: Hot3d: hand and object tracking in 3d from egocentric multi-view videos. arXiv preprint arXiv:2411.19167 (2024)","DOI":"10.1109\/CVPR52734.2025.00662"},{"key":"29_CR10","unstructured":"de\u00a0Belen, R.A., Mohammadi, G., Sowmya, A.: Temporal understanding of gaze communication with gazetransformer. In: NeuRIPS Workshop on Gaze Meets ML (2023)"},{"key":"29_CR11","unstructured":"Bonnetto, A., et al.: Epfl-smart-kitchen-30: densely annotated cooking dataset with 3d kinematics to challenge video and language models. arXiv preprint arXiv:2506.01608 (2025)"},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Cakmak, M., Srinivasa, S.S., Lee, M.K., Forlizzi, J., Kiesler, S.: Human preferences for robot-human hand-over configurations. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 1986\u20131993. IEEE (2011)","DOI":"10.1109\/IROS.2011.6094735"},{"key":"29_CR13","unstructured":"Chang, M., et al.: Partnr: a benchmark for planning and reasoning in embodied multi-agent tasks. arXiv preprint arXiv:2411.00081 (2024)"},{"key":"29_CR14","doi-asserted-by":"crossref","unstructured":"Chavan, V., et al.: Indego: a dataset of industrial scenarios and collaborative work for egocentric assistants. In: Advances in Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track (2025)","DOI":"10.52202\/085713-3301"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"Chen, J., Mittal, G., Yu, Y., Kong, Y., Chen, M.: Gatehub: gated history unit with background suppression for online action detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19925\u201319934 (2022)","DOI":"10.1109\/CVPR52688.2022.01930"},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Chen, Z., et\u00a0al.: Tombench: benchmarking theory of mind in large language models. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics, vol. 1: Long Papers, pp. 15959\u201315983 (2024)","DOI":"10.18653\/v1\/2024.acl-long.847"},{"key":"29_CR17","doi-asserted-by":"crossref","unstructured":"Chong, E., Wang, Y., Ruiz, N., Rehg, J.M.: Detecting attended visual targets in video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5396\u20135406 (2020)","DOI":"10.1109\/CVPR42600.2020.00544"},{"issue":"4","key":"29_CR18","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1016\/j.tics.2009.01.005","volume":"13","author":"G Csibra","year":"2009","unstructured":"Csibra, G., Gergely, G.: Natural pedagogy. Trends Cogn. Sci. 13(4), 148\u2013153 (2009)","journal-title":"Trends Cogn. Sci."},{"key":"29_CR19","doi-asserted-by":"crossref","unstructured":"Damen, D., et al.: Scaling egocentric vision: the epic-kitchens dataset. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 720\u2013736 (2018)","DOI":"10.1007\/978-3-030-01225-0_44"},{"key":"29_CR20","doi-asserted-by":"publisher","unstructured":"Damen, D., et al.: Rescaling egocentric vision: collection, pipeline and challenges for epic-kitchens-100. Int. J. Comput. Vision (IJCV) 130, 33\u201355 (2022). https:\/\/doi.org\/10.1007\/s11263-021-01531-2","DOI":"10.1007\/s11263-021-01531-2"},{"key":"29_CR21","unstructured":"DeepMind, G.: Gemma 4 (2026). https:\/\/deepmind.google\/models\/gemma\/gemma-4\/. Accessed July 2026"},{"key":"29_CR22","unstructured":"Doshi, T., the Gemini\u00a0Team: Gemini 3 flash: Frontier intelligence built for speed (2025). https:\/\/blog.google\/products-and-platforms\/products\/gemini\/gemini-3-flash\/, google Blog"},{"key":"29_CR23","doi-asserted-by":"crossref","unstructured":"Dutta, A., Zisserman, A.: The VIA annotation software for images, audio and video. In: Proceedings of the 27th ACM International Conference on Multimedia. MM \u201919. ACM, New York (2019)","DOI":"10.1145\/3343031.3350535"},{"key":"29_CR24","unstructured":"Engel, J., et al.: Project aria: a new tool for egocentric multi-modal ai research. arXiv preprint arXiv:2308.13561 (2023)"},{"key":"29_CR25","doi-asserted-by":"crossref","unstructured":"Fan, L., Wang, W., Huang, S., Tang, X., Zhu, S.C.: Understanding human gaze communication by spatio-temporal graph reasoning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 5724\u20135733 (2019)","DOI":"10.1109\/ICCV.2019.00582"},{"key":"29_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1007\/978-3-642-33718-5_23","volume-title":"Computer Vision \u2013 ECCV 2012","author":"A Fathi","year":"2012","unstructured":"Fathi, A., Li, Y., Rehg, J.M.: Learning to recognize daily actions using gaze. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7572, pp. 314\u2013327. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33718-5_23"},{"key":"29_CR27","doi-asserted-by":"crossref","unstructured":"Fu, R., et al.: Gigahands: a massive annotated dataset of bimanual hand activities. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 17461\u201317474 (2025)","DOI":"10.1109\/CVPR52734.2025.01627"},{"issue":"11","key":"29_CR28","doi-asserted-by":"publisher","first-page":"4021","DOI":"10.1109\/TPAMI.2020.2992889","volume":"43","author":"A Furnari","year":"2020","unstructured":"Furnari, A., Farinella, G.M.: Rolling-unrolling lstms for action anticipation from first-person video. IEEE Trans. Pattern Anal. Mach. Intell. 43(11), 4021\u20134036 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"29_CR29","doi-asserted-by":"crossref","unstructured":"Furnari, A., Farinella, G.M.: Towards streaming egocentric action anticipation. In: 2022 26th International Conference on Pattern Recognition (ICPR), pp. 1250\u20131257. IEEE (2022)","DOI":"10.1109\/ICPR56361.2022.9956090"},{"key":"29_CR30","doi-asserted-by":"crossref","unstructured":"Gao, J., Yang, Z., Nevatia, R.: Red: reinforced encoder-decoder networks for action anticipation. arXiv preprint arXiv:1707.04818 (2017)","DOI":"10.5244\/C.31.92"},{"key":"29_CR31","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Grauman, K.: Anticipative video transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13505\u201313515 (2021)","DOI":"10.1109\/ICCV48922.2021.01325"},{"key":"29_CR32","unstructured":"Grauman, K., et\u00a0al.: Ego4d: around the world in 3,000 hours of egocentric video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18995\u201319012 (2022)"},{"key":"29_CR33","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)"},{"issue":"2","key":"29_CR34","doi-asserted-by":"publisher","first-page":"2007","DOI":"10.1007\/s00521-022-07826-w","volume":"35","author":"Z Guo","year":"2023","unstructured":"Guo, Z., Hou, Y., Wang, P., Gao, Z., Xu, M., Li, W.: Ft-hid: a large-scale rgb-d dataset for first-and third-person human interaction analysis. Neural Comput. Appl. 35(2), 2007\u20132024 (2023)","journal-title":"Neural Comput. Appl."},{"key":"29_CR35","unstructured":"Huang, D., Hilliges, O., Van Gool, L., Wang, X.: Palm: predicting actions through language models@ ego4d long-term action anticipation challenge 2023. arXiv preprint arXiv:2306.16545 (2023)"},{"issue":"4","key":"29_CR36","doi-asserted-by":"publisher","first-page":"306","DOI":"10.1109\/THMS.2020.2965429","volume":"50","author":"Y Huang","year":"2020","unstructured":"Huang, Y., Cai, M., Sato, Y.: An ego-vision system for discovering human joint attention. IEEE Trans. Hum.-Mach. Syst. 50(4), 306\u2013316 (2020)","journal-title":"IEEE Trans. Hum.-Mach. Syst."},{"key":"29_CR37","doi-asserted-by":"crossref","unstructured":"Huang, Y., et al.: Egoexolearn: a dataset for bridging asynchronous ego- and exo-centric view of procedural activities in real world. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2024)","DOI":"10.1109\/CVPR52733.2024.02084"},{"key":"29_CR38","doi-asserted-by":"crossref","unstructured":"Jang, Y., Sullivan, B., Ludwig, C., Gilchrist, I., Damen, D., Mayol-Cuevas, W.: Epic-tent: an egocentric video dataset for camping tent assembly. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops (2019)","DOI":"10.1109\/ICCVW.2019.00547"},{"key":"29_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"767","DOI":"10.1007\/978-3-030-58574-7_46","volume-title":"Computer Vision \u2013 ECCV 2020","author":"B Jia","year":"2020","unstructured":"Jia, B., Chen, Y., Huang, S., Zhu, Y., Zhu, S.-C.: Lemma: A multi-view dataset for le arning m ulti-agent m ulti-task a ctivities. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12371, pp. 767\u2013786. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58574-7_46"},{"key":"29_CR40","doi-asserted-by":"crossref","unstructured":"Khirodkar, R., Bansal, A., Ma, L., Newcombe, R., Vo, M., Kitani, K.: Egohumans: an egocentric 3d multi-human benchmark. arXiv preprint arXiv:2305.16487 (2023)","DOI":"10.1109\/ICCV51070.2023.01814"},{"key":"29_CR41","unstructured":"Li, Y., Veerabadran, V., Iuzzolino, M.L., Roads, B.D., Celikyilmaz, A., Ridgeway, K.: Egotom: benchmarking theory of mind reasoning from egocentric videos. arXiv preprint arXiv:2503.22152 (2025)"},{"key":"29_CR42","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, pp. 3282\u20133292 (2022)","DOI":"10.1109\/CVPR52688.2022.00328"},{"key":"29_CR43","doi-asserted-by":"crossref","unstructured":"Liu, Y., Zhang, C., Xing, R., Tang, B., Yang, B., Yi, L.: Core4d: a 4d human-object-human interaction dataset for collaborative object rearrangement. arXiv preprint arXiv:2406.19353 (2024)","DOI":"10.1109\/CVPR52734.2025.00172"},{"key":"29_CR44","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1007\/s11263-013-0655-7","volume":"106","author":"MJ Marin-Jimenez","year":"2014","unstructured":"Marin-Jimenez, M.J., Zisserman, A., Eichner, M., Ferrari, V.: Detecting people looking at each other in videos. Int. J. Comput. Vision (IJCV) 106, 282\u2013296 (2014)","journal-title":"Int. J. Comput. Vision (IJCV)"},{"key":"29_CR45","doi-asserted-by":"crossref","unstructured":"Mascar\u00f3, E.V., Ahn, H., Lee, D.: Intention-conditioned long-term human egocentric action anticipation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 6048\u20136057 (2023)","DOI":"10.1109\/WACV56688.2023.00599"},{"key":"29_CR46","unstructured":"McLean, C., et al.: Embody 3d: a large-scale multimodal motion and behavior dataset. Technical report. arXiv preprint https:\/\/arxiv.org\/pdf\/2510.16258 (2025)"},{"key":"29_CR47","unstructured":"Medina, M.J.M.K.V.: Su\u00e1rez p zisserman a laeo-net++: revisiting people looking at each other in videos. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 10 (2021)"},{"key":"29_CR48","unstructured":"Meta Reality Labs Research: Project aria machine perception services (mps) (2024). https:\/\/facebookresearch.github.io\/projectaria_tools\/docs\/ARK\/mps. Accessed 04 Mar 2026"},{"key":"29_CR49","doi-asserted-by":"publisher","first-page":"23765","DOI":"10.52202\/068431-1726","volume":"35","author":"H Mittal","year":"2022","unstructured":"Mittal, H., Morgado, P., Jain, U., Gupta, A.: Learning state-aware visual representations from audible interactions. Adv. Neural. Inf. Process. Syst. 35, 23765\u201323779 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR50","unstructured":"OpenAI: Gpt-4o system card. System card (2024). https:\/\/openai.com\/index\/gpt-4o-system-card\/. Accessed 04 Mar 2026"},{"key":"29_CR51","unstructured":"OpenAI: Gpt-5.1 instant and gpt-5.1 thinking system card addendum. System card addendum (2025). https:\/\/openai.com\/index\/gpt-5-system-card-addendum-gpt-5-1\/. Accessed 04 Mar 2026"},{"key":"29_CR52","unstructured":"OpenAI: Introducing gpt-5.2. OpenAI Index (2025). https:\/\/openai.com\/index\/introducing-gpt-5-2\/. Accessed 04 Mar 2026"},{"issue":"6","key":"29_CR53","doi-asserted-by":"publisher","first-page":"1855","DOI":"10.1109\/TRO.2021.3075365","volume":"37","author":"V Ortenzi","year":"2021","unstructured":"Ortenzi, V., Cosgun, A., Pardi, T., Chan, W.P., Croft, E., Kuli\u0107, D.: Object handovers: a review for robotics. IEEE Trans. Rob. 37(6), 1855\u20131873 (2021)","journal-title":"IEEE Trans. Rob."},{"key":"29_CR54","doi-asserted-by":"crossref","unstructured":"Osman, N., Camporese, G., Coscia, P., Ballan, L.: Slowfast rolling-unrolling lstms for action anticipation in egocentric videos. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3437\u20133445 (2021)","DOI":"10.1109\/ICCVW54120.2021.00383"},{"key":"29_CR55","doi-asserted-by":"crossref","unstructured":"Pasca, R., et al.: Summarize the past to predict the future: Natural language descriptions of context boost multimodal object interaction anticipation. In: Conference on Computer Vision and Pattern Recognition 2024 (2024). https:\/\/eth-ait.github.io\/transfusion-proj\/","DOI":"10.1109\/CVPR52733.2024.01731"},{"key":"29_CR56","doi-asserted-by":"crossref","unstructured":"Perrett, T., et al.: Hd-epic: a highly-detailed egocentric video dataset. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 23901\u201323913 (2025)","DOI":"10.1109\/CVPR52734.2025.02226"},{"key":"29_CR57","doi-asserted-by":"crossref","unstructured":"Premack, D., Woodruff, G.: Does a chimpanzee have a theory of mind. Behav. Brain Sci. 1, 515 \u2013 526 (1978)","DOI":"10.1017\/S0140525X00076512"},{"key":"29_CR58","doi-asserted-by":"crossref","unstructured":"Puig, X., et al.: Virtualhome: simulating household activities via programs (2018)","DOI":"10.1109\/CVPR.2018.00886"},{"key":"29_CR59","unstructured":"Puig, X., et al.: Watch-and-help: a challenge for social perception and human-ai collaboration. arXiv preprint arXiv:2010.09890 (2020)"},{"key":"29_CR60","unstructured":"Qi, Z., Wang, S., Su, C., Su, L., Huang, Q., Tian, Q.: Self-regulated learning for egocentric video activity anticipation. IEEE Trans. Pattern Anal. Mach. Intell. (2021)"},{"key":"29_CR61","unstructured":"Qiu, H., Shi, Z., Wang, L., Xiong, H., Li, X., Li, H.: Egome: a new dataset and challenge for following me via egocentric view in real world. arXiv preprint arXiv:2501.19061 (2025)"},{"key":"29_CR62","unstructured":"Rabinowitz, N., Perbet, F., Song, F., Zhang, C., Eslami, S.A., Botvinick, M.: Machine theory of mind. In: International Conference on Machine Learning, pp. 4218\u20134227. PMLR (2018)"},{"key":"29_CR63","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. In: International Conference on Machine Learning, pp. 28492\u201328518. PMLR (2023)"},{"key":"29_CR64","unstructured":"Recasens, A., Khosla, A., Vondrick, C., Torralba, A.: Where are they looking? In: NeurIPS (2015)"},{"key":"29_CR65","doi-asserted-by":"crossref","unstructured":"Reddy, V.: Understanding attention to self joint attention: communication and other minds: issues in philosophy and psychology, p. 85 (2005)","DOI":"10.1093\/acprof:oso\/9780199245635.003.0005"},{"key":"29_CR66","doi-asserted-by":"crossref","unstructured":"Rizve, M.N., et al.: Pivotal: prior-driven supervision for weakly-supervised temporal action localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22992\u201323002 (2023)","DOI":"10.1109\/CVPR52729.2023.02202"},{"key":"29_CR67","doi-asserted-by":"publisher","unstructured":"Rodin, I., Furnari, A., Mavroeidis, D., Farinella, G.M.: Untrimmed action anticipation. In: International Conference on Image Analysis and Processing, pp. 337\u2013348. Springer, Heidelberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-06433-3_29","DOI":"10.1007\/978-3-031-06433-3_29"},{"key":"29_CR68","doi-asserted-by":"crossref","unstructured":"Rusinkiewicz, S., Levoy, M.: Efficient variants of the icp algorithm. In: Proceedings Third International Conference on 3-D Digital Imaging and Modeling, pp. 145\u2013152. IEEE (2001)","DOI":"10.1109\/IM.2001.924423"},{"key":"29_CR69","doi-asserted-by":"crossref","unstructured":"Sarlin, P.E., Cadena, C., Siegwart, R., Dymczyk, M.: From coarse to fine: robust hierarchical localization at large scale. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01300"},{"key":"29_CR70","doi-asserted-by":"crossref","unstructured":"Sarlin, P.E., DeTone, D., Malisiewicz, T., Rabinovich, A.: SuperGlue: learning feature matching with graph neural networks. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00499"},{"issue":"4","key":"29_CR71","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1017\/S0140525X12000660","volume":"36","author":"L Schilbach","year":"2013","unstructured":"Schilbach, L., et al.: Toward a second-person neuroscience. Behav. Brain Sci. 36(4), 393\u2013414 (2013)","journal-title":"Behav. Brain Sci."},{"issue":"2","key":"29_CR72","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.tics.2005.12.009","volume":"10","author":"N Sebanz","year":"2006","unstructured":"Sebanz, N., Bekkering, H., Knoblich, G.: Joint action: bodies and minds moving together. Trends Cogn. Sci. 10(2), 70\u201376 (2006)","journal-title":"Trends Cogn. Sci."},{"key":"29_CR73","doi-asserted-by":"crossref","unstructured":"Sener, F., et al.: Assembly101: a large-scale multi-view video dataset for understanding procedural activities. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21096\u201321106 (2022)","DOI":"10.1109\/CVPR52688.2022.02042"},{"key":"29_CR74","doi-asserted-by":"crossref","unstructured":"Shi, H., et al.: Muma-tom: multi-modal multi-agent theory of mind. In: Proceedings of the AAAI Conference on Artificial Intelligence (2025)","DOI":"10.1609\/aaai.v39i2.32142"},{"key":"29_CR75","doi-asserted-by":"crossref","unstructured":"Shi, Y., Fernando, B., Hartley, R.: Action anticipation with rbf kernelized feature mapping rnn. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 301\u2013317 (2018)","DOI":"10.1007\/978-3-030-01249-6_19"},{"key":"29_CR76","doi-asserted-by":"crossref","unstructured":"Shridhar, M., et al.: Alfred: a benchmark for interpreting grounded instructions for everyday tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10740\u201310749 (2020)","DOI":"10.1109\/CVPR42600.2020.01075"},{"issue":"3","key":"29_CR77","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1007\/s12193-015-0196-1","volume":"9","author":"J Six","year":"2015","unstructured":"Six, J., Leman, M.: Synchronizing multimodal recordings using audio-to-audio alignment. J. Multimodal User Interfaces 9(3), 223\u2013229 (2015). https:\/\/doi.org\/10.1007\/s12193-015-0196-1","journal-title":"J. Multimodal User Interfaces"},{"issue":"1","key":"29_CR78","doi-asserted-by":"publisher","first-page":"112","DOI":"10.5898\/JHRI.2.1.Strabala","volume":"2","author":"KW Strabala","year":"2013","unstructured":"Strabala, K.W., et al.: Towards seamless human-robot handovers. J. Hum.-Rob. Interact. 2(1), 112\u2013132 (2013)","journal-title":"J. Hum.-Rob. Interact."},{"key":"29_CR79","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1007\/978-3-030-58548-8_34","volume-title":"Computer Vision \u2013 ECCV 2020","author":"O Taheri","year":"2020","unstructured":"Taheri, O., Ghorbani, N., Black, M.J., Tzionas, D.: GRAB: a dataset of whole-body human grasping of objects. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 581\u2013600. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_34"},{"key":"29_CR80","doi-asserted-by":"crossref","unstructured":"Tomasello, M., Carpenter, M., Call, J., Behne, T., Moll, H.: Understanding and sharing intentions: the origins of cultural cognition. Behav. Brain Sci. 28, 675\u2013735 (2005)","DOI":"10.1017\/S0140525X05000129"},{"key":"29_CR81","doi-asserted-by":"crossref","unstructured":"Villa-Cueva, E., et al.: Moments: a comprehensive multimodal benchmark for theory of mind. arXiv preprint arXiv:2507.04415 (2025)","DOI":"10.18653\/v1\/2025.findings-emnlp.1230"},{"key":"29_CR82","doi-asserted-by":"crossref","unstructured":"Vondrick, C., Pirsiavash, H., Torralba, A.: Anticipating visual representations from unlabeled video. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 98\u2013106 (2016)","DOI":"10.1109\/CVPR.2016.18"},{"key":"29_CR83","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, pp. 20270\u201320281 (2023)","DOI":"10.1109\/ICCV51070.2023.01854"},{"key":"29_CR84","unstructured":"Wang, Z., et al.: Himemformer: hierarchical memory-aware transformer for multi-agent action anticipation. arXiv preprint arXiv:2411.01455 (2024)"},{"key":"29_CR85","doi-asserted-by":"publisher","first-page":"68736","DOI":"10.52202\/075280-3007","volume":"36","author":"N Wiederhold","year":"2023","unstructured":"Wiederhold, N., Megyeri, A., Paris, D., Banerjee, S., Banerjee, N.: Hoh: markerless multimodal human-object-human handover dataset with large object count. Adv. Neural. Inf. Process. Syst. 36, 68736\u201368748 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR86","doi-asserted-by":"crossref","unstructured":"Yang, J., et\u00a0al.: Egolife: towards egocentric life assistant. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 28885\u201328900 (2025)","DOI":"10.1109\/CVPR52734.2025.02690"},{"key":"29_CR87","doi-asserted-by":"crossref","unstructured":"Ye, Z., Li, Y., Liu, Y., Bridges, C., Rozga, A., Rehg, J.M.: Detecting bids for eye contact using a wearable camera. In: IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG), vol.\u00a01, pp.\u00a01\u20138. IEEE (2015)","DOI":"10.1109\/FG.2015.7163095"},{"key":"29_CR88","doi-asserted-by":"crossref","unstructured":"Zhang, C., et al.: Object-centric video representation for long-term action anticipation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 6751\u20136761 (2024)","DOI":"10.1109\/WACV57701.2024.00661"},{"key":"29_CR89","unstructured":"Zhang, H., et al.: Building cooperative embodied agents modularly with large language models. arXiv preprint arXiv:2307.02485 (2023)"},{"key":"29_CR90","doi-asserted-by":"publisher","unstructured":"Zhang, S., et al.: Egobody: human body shape and motion of interacting people from head-mounted devices. In: European Conference on Computer Vision, pp. 180\u2013200. Springer, Heidelberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-20068-7_11","DOI":"10.1007\/978-3-031-20068-7_11"},{"key":"29_CR91","doi-asserted-by":"crossref","unstructured":"Zhang, X., Chen, Y., Yeh, S., Li, S.: Metamind: modeling human social thoughts with metacognitive multi-agent systems. arXiv preprint arXiv:2505.18943 (2025)","DOI":"10.52202\/085713-0881"},{"key":"29_CR92","unstructured":"Zhao, Q., et al.: AntGPT: can large language models help long-term action anticipation from videos? In: The Twelfth International Conference on Learning Representations (2024)"}],"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\/978-3-032-37550-6_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T17:23:28Z","timestamp":1789233808000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37550-6_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032375490","9783032375506"],"references-count":92,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37550-6_29","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":"13 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"}}]}}