{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T11:29:50Z","timestamp":1764588590559,"version":"3.38.0"},"reference-count":67,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T00:00:00Z","timestamp":1734998400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T00:00:00Z","timestamp":1734998400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"the Strategic research and consulting project of Chinese Academy of Engineering","award":["No.2023-HY-14"],"award-info":[{"award-number":["No.2023-HY-14"]}]},{"name":"the 2022 major science and technology project Yuelu \u2022 Multimodal Graph-Text-Sound-Semantic Gesture Big Model Research and Demonstration Application","award":["No.kh2301019"],"award-info":[{"award-number":["No.kh2301019"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1007\/s00530-024-01591-7","type":"journal-article","created":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T07:09:51Z","timestamp":1735024191000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Personalized decision-making for agents in face-to-face interaction in virtual reality"],"prefix":"10.1007","volume":"31","author":[{"given":"Xiaonuo","family":"Dongye","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongdong","family":"Weng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haiyan","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeyu","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yihua","family":"Bao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pukun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,24]]},"reference":[{"key":"1591_CR1","first-page":"27","volume":"1","author":"M Wooldridge","year":"1999","unstructured":"Wooldridge, M.: Intelligent agents. Multiagent systems: A modern approach to distributed artificial intelligence 1, 27\u201373 (1999)","journal-title":"Multiagent systems: A modern approach to distributed artificial intelligence"},{"issue":"1","key":"1591_CR2","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1080\/088395100117142","volume":"14","author":"M Luck","year":"2000","unstructured":"Luck, M., Aylett, R.: Applying artificial intelligence to virtual reality: Intelligent virtual environments. Appl. Artif. Intell. 14(1), 3\u201332 (2000)","journal-title":"Appl. Artif. Intell."},{"key":"1591_CR3","doi-asserted-by":"crossref","unstructured":"Jiang, H., Song, L., Weng, D., Sun, Z., Li, H., Dongye, X., Zhang, Z.: In situ 3D scene synthesis for ubiquitous embodied interfaces. Proceedings of the 32nd ACM International Conference on Multimedia, pp 3666\u20133675 (2024)","DOI":"10.1145\/3664647.3681616"},{"issue":"4\u20132","key":"1591_CR4","doi-asserted-by":"publisher","first-page":"1460","DOI":"10.18517\/ijaseit.8.4-2.6824","volume":"8","author":"M Nizam","year":"2018","unstructured":"Nizam, M., Abidin, R.Z., Hashim, N.C., Lam, M.C., Arshad, H., Majid, N.: A review of multimodal interaction technique in augmented reality environment. Int. J. Adv. Sci. Eng. Inf. Technol 8(4\u20132), 1460 (2018)","journal-title":"Int. J. Adv. Sci. Eng. Inf. Technol"},{"key":"1591_CR5","doi-asserted-by":"crossref","unstructured":"Fotinea, E.-S., Efthimiou, E., Dimou, A.-L., Goulas, T., Karioris, P., Peer, A., Maragos, P., Tzafestas, C., Kokkinos, I., Hauer, K. et al.: Data acquisition towards defining a multimodal interaction model for human\u2013assistive robot communication. In: Universal Access in Human-Computer Interaction. Aging and Assistive Environments: 8th International Conference, UAHCI 2014, Held as Part of HCI International 2014, Heraklion, Crete, Greece, June 22\u201327, 2014, Proceedings, Part III 8, pp. 613\u2013624 (2014). Springer","DOI":"10.1007\/978-3-319-07446-7_59"},{"key":"1591_CR6","doi-asserted-by":"crossref","unstructured":"Heuvel, J., Corral, N., Bruckschen, L., Bennewitz, M.: Learning personalized human-aware robot navigation using virtual reality demonstrations from a user study. In: 2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), pp. 898\u2013905 (2022). IEEE","DOI":"10.1109\/RO-MAN53752.2022.9900554"},{"key":"1591_CR7","first-page":"20","volume":"2","author":"S Vemprala","year":"2023","unstructured":"Vemprala, S., Bonatti, R., Bucker, A., Kapoor, A.: Chatgpt for robotics: design principles and model abilities. Microsoft Auton. Syst. Robot. Res 2, 20 (2023)","journal-title":"Microsoft Auton. Syst. Robot. Res"},{"key":"1591_CR8","doi-asserted-by":"crossref","unstructured":"Shen, Y., Heacock, L., Elias, J., Hentel, K.D., Reig, B., Shih, G., Moy, L.: ChatGPT and other large language models are double-edged swords. Radiological Society of North America (2023)","DOI":"10.1148\/radiol.230163"},{"key":"1591_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.lindif.2023.102274","volume":"103","author":"E Kasneci","year":"2023","unstructured":"Kasneci, E., Se\u00dfler, K., K\u00fcchemann, S., Bannert, M., Dementieva, D., Fischer, F., Gasser, U., Groh, G., G\u00fcnnemann, S., H\u00fcllermeier, E., et al.: Chatgpt for good? on opportunities and challenges of large language models for education. Learn. Individ. Differ. 103, 102274 (2023)","journal-title":"Learn. Individ. Differ."},{"key":"1591_CR10","doi-asserted-by":"crossref","unstructured":"Wang, A., Gao, Z., Lee, L.H., Braud, T., Hui, P.: Decentralized, not dehumanized in the metaverse: Bringing utility to nfts through multimodal interaction. In: Proceedings of the 2022 International Conference on Multimodal Interaction, pp. 662\u2013667 (2022)","DOI":"10.1145\/3536221.3558176"},{"issue":"12","key":"1591_CR11","doi-asserted-by":"publisher","first-page":"15949","DOI":"10.1109\/TPAMI.2023.3311447","volume":"45","author":"J Gao","year":"2023","unstructured":"Gao, J., Chen, M., Xu, C.: Vectorized evidential learning for weakly-supervised temporal action localization. IEEE Trans. Pattern Anal. Mach. Intell. 45(12), 15949\u201315963 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1591_CR12","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1016\/j.patrec.2013.07.003","volume":"36","author":"M Turk","year":"2014","unstructured":"Turk, M.: Multimodal interaction: A review. Pattern Recogn. Lett. 36, 189\u2013195 (2014)","journal-title":"Pattern Recogn. Lett."},{"key":"1591_CR13","doi-asserted-by":"crossref","unstructured":"Kaiser, E., Olwal, A., McGee, D., Benko, H., Corradini, A., Li, X., Cohen, P., Feiner, S.: Mutual disambiguation of 3d multimodal interaction in augmented and virtual reality. In: Proceedings of the 5th International Conference on Multimodal Interfaces, pp. 12\u201319 (2003)","DOI":"10.1145\/958432.958438"},{"key":"1591_CR14","doi-asserted-by":"crossref","unstructured":"Cordeiro, D., Correia, N., Jesus, R.: Arzombie: A mobile augmented reality game with multimodal interaction. In: 2015 7th International Conference on Intelligent Technologies for Interactive Entertainment (INTETAIN), pp. 22\u201331 (2015). IEEE","DOI":"10.4108\/icst.intetain.2015.259743"},{"key":"1591_CR15","doi-asserted-by":"crossref","unstructured":"Ismail, A.W., Billinghurst, M., Sunar, M.S.: Vision-based technique and issues for multimodal interaction in augmented reality. In: Proceedings of the 8th International Symposium on Visual Information Communication and Interaction, pp. 75\u201382 (2015)","DOI":"10.1145\/2801040.2801058"},{"key":"1591_CR16","doi-asserted-by":"crossref","unstructured":"Al-Sada, M., Ishizawa, F., Tsurukawa, J., Nakajima, T.: Input forager: A user-driven interaction adaptation approach for head worn displays. In: Proceedings of the 15th International Conference on Mobile and Ubiquitous Multimedia, pp. 115\u2013122 (2016)","DOI":"10.1145\/3012709.3012719"},{"key":"1591_CR17","doi-asserted-by":"crossref","unstructured":"Sita, E., Studley, M., Dailami, F., Pipe, A., Thomessen, T.: Towards multimodal interactions: robot jogging in mixed reality. In: Proceedings of the 23rd ACM Symposium on Virtual Reality Software and Technology, pp. 1\u20132 (2017)","DOI":"10.1145\/3139131.3141200"},{"key":"1591_CR18","doi-asserted-by":"publisher","first-page":"5410","DOI":"10.1109\/TMM.2023.3333206","volume":"26","author":"Y Hu","year":"2024","unstructured":"Hu, Y., Gao, J., Dong, J., Fan, B., Liu, H.: Exploring rich semantics for open-set action recognition. IEEE Trans. Multimedia 26, 5410\u20135421 (2024)","journal-title":"IEEE Trans. Multimedia"},{"issue":"3","key":"1591_CR19","doi-asserted-by":"publisher","first-page":"1646","DOI":"10.1109\/TCSVT.2021.3075470","volume":"32","author":"J Gao","year":"2022","unstructured":"Gao, J., Xu, C.: Learning video moment retrieval without a single annotated video. IEEE Trans. Circuits Syst. Video Technol. 32(3), 1646\u20131657 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"9","key":"1591_CR20","doi-asserted-by":"publisher","first-page":"1449","DOI":"10.1109\/JPROC.2015.2460697","volume":"103","author":"D Lahat","year":"2015","unstructured":"Lahat, D., Adali, T., Jutten, C.: Multimodal data fusion: an overview of methods, challenges, and prospects. Proc. IEEE 103(9), 1449\u20131477 (2015)","journal-title":"Proc. IEEE"},{"issue":"1","key":"1591_CR21","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1038\/s41597-020-00630-y","volume":"7","author":"CY Park","year":"2020","unstructured":"Park, C.Y., Cha, N., Kang, S., Kim, A., Khandoker, A.H., Hadjileontiadis, L., Oh, A., Jeong, Y., Lee, U.: K-emocon, a multimodal sensor dataset for continuous emotion recognition in naturalistic conversations. Scientific Data 7(1), 293 (2020)","journal-title":"Scientific Data"},{"key":"1591_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2023.101521","volume":"81","author":"CC Bennett","year":"2023","unstructured":"Bennett, C.C., Bae, Y.-H., Yoon, J.H., Chae, Y., Yoon, E., Lee, S., Ryu, U., Kim, S.Y., Weiss, B.: Effects of cross-cultural language differences on social cognition during human-agent interaction in cooperative game environments. Computer Speech & Language 81, 101521 (2023)","journal-title":"Computer Speech & Language"},{"issue":"2","key":"1591_CR23","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1007\/s12559-022-10067-7","volume":"15","author":"L Malandri","year":"2023","unstructured":"Malandri, L., Mercorio, F., Mezzanzanica, M., Nobani, N.: Convxai: a system for multimodal interaction with any black-box explainer. Cogn. Comput. 15(2), 613\u2013644 (2023)","journal-title":"Cogn. Comput."},{"key":"1591_CR24","doi-asserted-by":"crossref","unstructured":"Miech, A., Zhukov, D., Alayrac, J.-B., Tapaswi, M., Laptev, I., Sivic, J.: Howto100m: Learning a text-video embedding by watching hundred million narrated video clips. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2630\u20132640 (2019)","DOI":"10.1109\/ICCV.2019.00272"},{"key":"1591_CR25","doi-asserted-by":"crossref","unstructured":"Sun, P., Kretzschmar, H., Dotiwalla, X., Chouard, A., Patnaik, V., Tsui, P., Guo, J., Zhou, Y., Chai, Y., Caine, B., et al.: Scalability in perception for autonomous driving: Waymo open dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2446\u20132454 (2020)","DOI":"10.1109\/CVPR42600.2020.00252"},{"issue":"1","key":"1591_CR26","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.inffus.2011.08.001","volume":"14","author":"B Khaleghi","year":"2013","unstructured":"Khaleghi, B., Khamis, A., Karray, F.O., Razavi, S.N.: Multisensor data fusion: A review of the state-of-the-art. Information fusion 14(1), 28\u201344 (2013)","journal-title":"Information fusion"},{"issue":"3","key":"1591_CR27","doi-asserted-by":"publisher","first-page":"2198","DOI":"10.1016\/j.neuroimage.2010.09.073","volume":"54","author":"AR Groves","year":"2011","unstructured":"Groves, A.R., Beckmann, C.F., Smith, S.M., Woolrich, M.W.: Linked independent component analysis for multimodal data fusion. Neuroimage 54(3), 2198\u20132217 (2011)","journal-title":"Neuroimage"},{"issue":"5","key":"1591_CR28","doi-asserted-by":"publisher","first-page":"829","DOI":"10.1162\/neco_a_01273","volume":"32","author":"J Gao","year":"2020","unstructured":"Gao, J., Li, P., Chen, Z., Zhang, J.: A survey on deep learning for multimodal data fusion. Neural Comput. 32(5), 829\u2013864 (2020)","journal-title":"Neural Comput."},{"key":"1591_CR29","doi-asserted-by":"crossref","unstructured":"Qi, S., Huang, S., Wei, P., Zhu, S.-C.: Predicting human activities using stochastic grammar. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1164\u20131172 (2017)","DOI":"10.1109\/ICCV.2017.132"},{"key":"1591_CR30","doi-asserted-by":"crossref","unstructured":"Liu, Y., Han, T., Ma, S., Zhang, J., Yang, Y., Tian, J., He, H., Li, A., He, M., Liu, Z., et al.: Summary of chatgpt\/gpt-4 research and perspective towards the future of large language models. (2023) arXiv preprint arXiv:2304.01852","DOI":"10.1016\/j.metrad.2023.100017"},{"key":"1591_CR31","unstructured":"Zhao, W.X., Zhou, K., Li, J., Tang, T., Wang, X., Hou, Y., Min, Y., Zhang, B., Zhang, J., Dong, Z., et al.: A survey of large language models. (2023) arXiv preprint arXiv:2303.18223"},{"key":"1591_CR32","unstructured":"Wei, J., Tay, Y., Bommasani, R., Raffel, C., Zoph, B., Borgeaud, S., Yogatama, D., Bosma, M., Zhou, D., Metzler, D., et al.: Emergent abilities of large language models. (2022) arXiv preprint arXiv:2206.07682"},{"issue":"10","key":"1591_CR33","doi-asserted-by":"publisher","first-page":"3476","DOI":"10.1109\/TPAMI.2020.2985708","volume":"43","author":"J Gao","year":"2021","unstructured":"Gao, J., Zhang, T., Xu, C.: Learning to model relationships for zero-shot video classification. IEEE Trans. Pattern Anal. Mach. Intell. 43(10), 3476\u20133491 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1591_CR34","unstructured":"Wolf, Y., Wies, N., Levine, Y., Shashua, A.: Fundamental limitations of alignment in large language models. (2023) arXiv preprint arXiv:2304.11082"},{"key":"1591_CR35","doi-asserted-by":"crossref","unstructured":"Gao, N., Zhao, Z., Zeng, Z., Zhang, S., Weng, D., Bao, Y.: Gesgpt: Speech gesture synthesis with text parsing from chatgpt. IEEE Robotics and Automation Letters (2024)","DOI":"10.1109\/LRA.2024.3359544"},{"key":"1591_CR36","doi-asserted-by":"crossref","unstructured":"Park, J.S., O\u2019Brien, J.C., Cai, C.J., Morris, M.R., Liang, P., Bernstein, M.S.: Generative agents: Interactive simulacra of human behavior. In: In the 36th Annual ACM Symposium on User Interface Software and Technology (UIST \u201923). UIST \u201923. Association for Computing Machinery, New York, NY, USA (2023)","DOI":"10.1145\/3586183.3606763"},{"key":"1591_CR37","unstructured":"Liang, Y., Zhu, L., Yang, Y.: Tachikuma: Understading complex interactions with multi-character and novel objects by large language models. (2023) arXiv preprint arXiv:2307.12573"},{"key":"1591_CR38","doi-asserted-by":"crossref","unstructured":"Wu, T., Terry, M., Cai, C.J.: Ai chains: Transparent and controllable human-ai interaction by chaining large language model prompts. In: Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems, pp. 1\u201322 (2022)","DOI":"10.1145\/3491102.3517582"},{"key":"1591_CR39","unstructured":"Kaddour, J., Harris, J., Mozes, M., Bradley, H., Raileanu, R., McHardy, R.: Challenges and applications of large language models. (2023) arXiv preprint arXiv:2307.10169"},{"key":"1591_CR40","doi-asserted-by":"crossref","unstructured":"Ziems, C., Held, W., Shaikh, O., Chen, J., Zhang, Z., Yang, D.: Can large language models transform computational social science? (2023) arXiv preprint arXiv:2305.03514","DOI":"10.1162\/coli_a_00502"},{"issue":"3","key":"1591_CR41","doi-asserted-by":"publisher","first-page":"14","DOI":"10.3390\/mti1030014","volume":"1","author":"MI Ahmad","year":"2017","unstructured":"Ahmad, M.I., Mubin, O., Orlando, J.: A systematic review of adaptivity in human-robot interaction. Multimodal Technologies and Interaction 1(3), 14 (2017)","journal-title":"Multimodal Technologies and Interaction"},{"key":"1591_CR42","doi-asserted-by":"crossref","unstructured":"Reig, S., Luria, M., Wang, J.Z., Oltman, D., Carter, E.J., Steinfeld, A., Forlizzi, J., Zimmerman, J.: Not some random agent: Multi-person interaction with a personalizing service robot. In: Proceedings of the 2020 ACM\/IEEE International Conference on Human-robot Interaction, pp. 289\u2013297 (2020)","DOI":"10.1145\/3319502.3374795"},{"key":"1591_CR43","unstructured":"Foster, M.E., Craenen, B., Deshmukh, A., Lemon, O., Bastianelli, E., Dondrup, C., Papaioannou, I., Vanzo, A., Odobez, J.-M., Can\u00e9vet, O., et al.: Mummer: Socially intelligent human-robot interaction in public spaces. (2019) arXiv preprint arXiv:1909.06749"},{"issue":"4","key":"1591_CR44","doi-asserted-by":"publisher","first-page":"120","DOI":"10.3390\/robotics10040120","volume":"10","author":"M Hellou","year":"2021","unstructured":"Hellou, M., Gasteiger, N., Lim, J.Y., Jang, M., Ahn, H.S.: Personalization and localization in human-robot interaction: A review of technical methods. Robotics 10(4), 120 (2021)","journal-title":"Robotics"},{"key":"1591_CR45","doi-asserted-by":"crossref","unstructured":"Koay, K.L., Syrdal, D.S., Ho, W.C., Dautenhahn, K.: Prototyping realistic long-term human-robot interaction for the study of agent migration. In: 2016 25th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN), pp. 809\u2013816 (2016). IEEE","DOI":"10.1109\/ROMAN.2016.7745212"},{"issue":"6","key":"1591_CR46","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1145\/3618320","volume":"42","author":"H Jiang","year":"2023","unstructured":"Jiang, H., Weng, D., Dongye, X., Luo, L., Zhang, Z.:\u00a0Commonsense knowledge-driven joint reasoning approach for object retrieval in virtual reality.\u00a0ACM Trans. Graph.\u00a042(6), 198 (2023)","journal-title":"ACM Trans. Graph"},{"key":"1591_CR47","unstructured":"Abramson, J., Ahuja, A., Carnevale, F., Georgiev, P., Goldin, A., Hung, A., Landon, J., Lhotka, J., Lillicrap, T., Muldal, A., et al.: Improving multimodal interactive agents with reinforcement learning from human feedback. (2022) arXiv preprint arXiv:2211.11602"},{"key":"1591_CR48","doi-asserted-by":"crossref","unstructured":"V\u00f6lkel, S.T., Sch\u00f6del, R., Buschek, D., Stachl, C., Au, Q., Bischl, B., B\u00fchner, M., Hussmann, H.: Opportunities and challenges of utilizing personality traits for personalization in hci. Personalized Human-Computer Interaction 31 (2019)","DOI":"10.1515\/9783110552485-002"},{"issue":"2","key":"1591_CR49","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1109\/TETCI.2022.3141105","volume":"6","author":"J Duan","year":"2022","unstructured":"Duan, J., Yu, S., Tan, H.L., Zhu, H., Tan, C.: A survey of embodied ai: From simulators to research tasks. IEEE Transactions on Emerging Topics in Computational Intelligence 6(2), 230\u2013244 (2022)","journal-title":"IEEE Transactions on Emerging Topics in Computational Intelligence"},{"key":"1591_CR50","unstructured":"Xi, Z., Chen, W., Guo, X., He, W., Ding, Y., Hong, B., Zhang, M., Wang, J., Jin, S., Zhou, E., et al.: The rise and potential of large language model based agents: A survey. (2023) arXiv preprint arXiv:2309.07864"},{"key":"1591_CR51","unstructured":"Penning, L., Garcez, A., Lamb, L.C., Meyer, J.: A neural-symbolic cognitive agent for online learning and reasoning. In: Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence, vol. 2, pp. 1653\u20131658 (2011). International Joint Conferences on Artificial Intelligence"},{"issue":"3","key":"1591_CR52","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1016\/j.eng.2020.01.011","volume":"6","author":"Y Zhu","year":"2020","unstructured":"Zhu, Y., Gao, T., Fan, L., Huang, S., Edmonds, M., Liu, H., Gao, F., Zhang, C., Qi, S., Wu, Y.N., et al.: Dark, beyond deep: A paradigm shift to cognitive ai with humanlike common sense. Engineering 6(3), 310\u2013345 (2020)","journal-title":"Engineering"},{"issue":"9","key":"1591_CR53","doi-asserted-by":"publisher","first-page":"2069","DOI":"10.3390\/electronics12092069","volume":"12","author":"X Dongye","year":"2023","unstructured":"Dongye, X., Weng, D., Jiang, H., Feng, L.: A modular haptic agent system with encountered-type active interaction. Electronics 12(9), 2069 (2023)","journal-title":"Electronics"},{"key":"1591_CR54","unstructured":"Rusu, A.A., Colmenarejo, S.G., Gulcehre, C., Desjardins, G., Kirkpatrick, J., Pascanu, R., Mnih, V., Kavukcuoglu, K., Hadsell, R.: Policy distillation. (2015) arXiv preprint arXiv:1511.06295"},{"issue":"6","key":"1591_CR55","doi-asserted-by":"publisher","first-page":"1071","DOI":"10.3390\/diagnostics11061071","volume":"11","author":"M Odusami","year":"2021","unstructured":"Odusami, M., Maskeli\u016bnas, R., Dama\u0161evi\u010dius, R., Krilavi\u010dius, T.: Analysis of features of alzheimer\u2019s disease: Detection of early stage from functional brain changes in magnetic resonance images using a finetuned resnet18 network. Diagnostics 11(6), 1071 (2021)","journal-title":"Diagnostics"},{"issue":"7","key":"1591_CR56","doi-asserted-by":"publisher","first-page":"1315","DOI":"10.1016\/j.jmb.2019.01.033","volume":"431","author":"M El Beheiry","year":"2019","unstructured":"El Beheiry, M., Doutreligne, S., Caporal, C., Ostertag, C., Dahan, M., Masson, J.-B.: Virtual reality: beyond visualization. J. Mol. Biol. 431(7), 1315\u20131321 (2019)","journal-title":"J. Mol. Biol."},{"key":"1591_CR57","doi-asserted-by":"crossref","unstructured":"Song, C.H., Wu, J., Washington, C., Sadler, B.M., Chao, W.-L., Su, Y.: Llm-planner: Few-shot grounded planning for embodied agents with large language models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2998\u20133009 (2023)","DOI":"10.1109\/ICCV51070.2023.00280"},{"key":"1591_CR58","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10462-012-9356-9","volume":"43","author":"SS Rautaray","year":"2015","unstructured":"Rautaray, S.S., Agrawal, A.: Vision based hand gesture recognition for human computer interaction: a survey. Artif. Intell. Rev. 43, 1\u201354 (2015)","journal-title":"Artif. Intell. Rev."},{"key":"1591_CR59","doi-asserted-by":"crossref","unstructured":"Dongye, X., Weng, D., Jiang, H., Chen, P.: Learning personalized agent for real-time face-to-face interaction in vr. In: 2024 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), pp. 759\u2013760 (2024). IEEE","DOI":"10.1109\/VRW62533.2024.00176"},{"issue":"4","key":"1591_CR60","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1023\/A:1011288000451","volume":"10","author":"A Pinar Saygin","year":"2000","unstructured":"Pinar Saygin, A., Cicekli, I., Akman, V.: Turing test: 50 years later. Mind. Mach. 10(4), 463\u2013518 (2000)","journal-title":"Mind. Mach."},{"key":"1591_CR61","unstructured":"Huang, W., Abbeel, P., Pathak, D., Mordatch, I.: Language models as zero-shot planners: Extracting actionable knowledge for embodied agents. In: International Conference on Machine Learning, pp. 9118\u20139147 (2022). PMLR"},{"key":"1591_CR62","doi-asserted-by":"crossref","unstructured":"Geijtenbeek, T., Steenbrink, F., Otten, B., Even-Zohar, O.: D-flow: immersive virtual reality and real-time feedback for rehabilitation. In: Proceedings of the 10th International Conference on Virtual Reality Continuum and Its Applications in Industry, pp. 201\u2013208 (2011)","DOI":"10.1145\/2087756.2087785"},{"key":"1591_CR63","doi-asserted-by":"crossref","unstructured":"Khundam, C., Vorachart, V., Preeyawongsakul, P., Hosap, W., No\u00ebl, F.: A comparative study of interaction time and usability of using controllers and hand tracking in virtual reality training. In: Informatics, vol. 8, p. 60 (2021). MDPI","DOI":"10.3390\/informatics8030060"},{"key":"1591_CR64","unstructured":"Wang, J., Zhang, C., Li, J., Ma, Y., Niu, L., Han, J., Peng, Y., Zhu, Y., Fan, L.: Evaluating and modeling social intelligence: A comparative study of human and ai capabilities. (2024) arXiv preprint arXiv:2405.11841"},{"key":"1591_CR65","doi-asserted-by":"crossref","unstructured":"Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H., Zhang, J., Chen, Z., Tang, J., Chen, X., Lin, Y., et al.: A survey on large language model based autonomous agents. (2023) arXiv preprint arXiv:2308.11432","DOI":"10.1007\/s11704-024-40231-1"},{"key":"1591_CR66","unstructured":"Lu, P., Peng, B., Cheng, H., Galley, M., Chang, K.-W., Wu, Y.N., Zhu, S.-C., Gao, J.: Chameleon: Plug-and-play compositional reasoning with large language models. (2023) arXiv preprint arXiv:2304.09842"},{"key":"1591_CR67","unstructured":"Naveed, H., Khan, A.U., Qiu, S., Saqib, M., Anwar, S., Usman, M., Barnes, N., Mian, A.: A comprehensive overview of large language models. (2023) arXiv preprint arXiv:2307.06435"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-024-01591-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-024-01591-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-024-01591-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,28]],"date-time":"2025-02-28T11:00:25Z","timestamp":1740740425000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-024-01591-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,24]]},"references-count":67,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["1591"],"URL":"https:\/\/doi.org\/10.1007\/s00530-024-01591-7","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"type":"print","value":"0942-4962"},{"type":"electronic","value":"1432-1882"}],"subject":[],"published":{"date-parts":[[2024,12,24]]},"assertion":[{"value":"23 April 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 November 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 December 2024","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 competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"28"}}