{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T06:54:25Z","timestamp":1763621665132,"version":"3.40.3"},"publisher-location":"Cham","reference-count":63,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031601064"},{"type":"electronic","value":"9783031601071"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-60107-1_6","type":"book-chapter","created":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T01:02:20Z","timestamp":1717203740000},"page":"60-80","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Multimodal Design for\u00a0Interactive Collaborative Problem-Solving Support"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3234-6797","authenticated-orcid":false,"given":"Hannah","family":"VanderHoeven","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2162-3307","authenticated-orcid":false,"given":"Mariah","family":"Bradford","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2232-4300","authenticated-orcid":false,"given":"Changsoo","family":"Jung","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4374-7263","authenticated-orcid":false,"given":"Ibrahim","family":"Khebour","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2870-7019","authenticated-orcid":false,"given":"Kenneth","family":"Lai","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2233-9761","authenticated-orcid":false,"given":"James","family":"Pustejovsky","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7878-7227","authenticated-orcid":false,"given":"Nikhil","family":"Krishnaswamy","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2653-0873","authenticated-orcid":false,"given":"Nathaniel","family":"Blanchard","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,6,1]]},"reference":[{"key":"6_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chb.2018.10.025","volume":"104","author":"J Andrews-Todd","year":"2020","unstructured":"Andrews-Todd, J., Forsyth, C.M.: Exploring social and cognitive dimensions of collaborative problem solving in an open online simulation-based task. Comput. Hum. Behav. 104, 105759 (2020). https:\/\/doi.org\/10.1016\/j.chb.2018.10.025","journal-title":"Comput. Hum. Behav."},{"issue":"4","key":"6_CR2","first-page":"358","volume":"27","author":"R Arnheim","year":"1994","unstructured":"Arnheim, R.: Hand and mind: what gestures reveal about thought by David McNeill. Leonardo 27(4), 358 (1994)","journal-title":"Leonardo"},{"unstructured":"Banarescu, L., et al.: Abstract meaning representation for sembanking. In: Proceedings of the 7th Linguistic Annotation Workshop and Interoperability with Discourse, pp. 178\u2013186 (2013)","key":"6_CR3"},{"issue":"3","key":"6_CR4","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1207\/S15327809JLS1203_1","volume":"12","author":"B Barron","year":"2003","unstructured":"Barron, B.: When smart groups fail. J. Learn. Sci. 12(3), 307\u2013359 (2003)","journal-title":"J. Learn. Sci."},{"doi-asserted-by":"crossref","unstructured":"Bradford, M., Khebour, I., Blanchard, N., Krishnaswamy, N.: Automatic detection of collaborative states in small groups using multimodal features. In: AIED (2023)","key":"6_CR5","DOI":"10.1007\/978-3-031-36272-9_69"},{"unstructured":"Brutti, R., Donatelli, L., Lai, K., Pustejovsky, J.: Abstract meaning representation for gesture, pp. 1576\u20131583, June 2022. https:\/\/aclanthology.org\/2022.lrec-1.169","key":"6_CR6"},{"unstructured":"Castillon, I., Venkatesha, V., VanderHoeven, H., Bradford, M., Krishnaswamy, N., Blanchard, N.: Multimodal features for group dynamic-aware agents. In: Interdisciplinary Approaches to Getting AI Experts and Education Stakeholders Talking Workshop at AIEd. International AIEd Society (2022)","key":"6_CR7"},{"doi-asserted-by":"publisher","unstructured":"Chejara, P., Prieto, L.P., Rodriguez-Triana, M.J., Kasepalu, R., Ruiz-Calleja, A., Shankar, S.K.: How to build more generalizable models for collaboration quality? Lessons learned from exploring multi-context audio-log datasets using multimodal learning analytics. In: LAK2023, pp. 111\u2013121. Association for Computing Machinery, New York, NY, USA, March 2023. https:\/\/doi.org\/10.1145\/3576050.3576144","key":"6_CR8","DOI":"10.1145\/3576050.3576144"},{"doi-asserted-by":"publisher","unstructured":"Cunico, F., Carletti, M., Cristani, M., Masci, F., Conigliaro, D.: 6D pose estimation for industrial applications, pp. 374\u2013384, September 2019. https:\/\/doi.org\/10.1007\/978-3-030-30754-7_37","key":"6_CR9","DOI":"10.1007\/978-3-030-30754-7_37"},{"doi-asserted-by":"crossref","unstructured":"Dey, I., et al.: The NICE framework: analyzing students\u2019 nonverbal interactions during collaborative learning. In: Pre-Conference Workshop on Collaboration Analytics at LAK 2023. SOLAR (2023)","key":"6_CR10","DOI":"10.22318\/cscl2023.218179"},{"issue":"2","key":"6_CR11","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/j.learninstruc.2011.10.001","volume":"22","author":"S D\u2019Mello","year":"2012","unstructured":"D\u2019Mello, S., Graesser, A.: Dynamics of affective states during complex learning. Learn. Instr. 22(2), 145\u2013157 (2012)","journal-title":"Learn. Instr."},{"issue":"2","key":"6_CR12","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1109\/TAFFC.2015.2457417","volume":"7","author":"F Eyben","year":"2016","unstructured":"Eyben, F., et al.: The Geneva minimalistic acoustic parameter set (GeMAPS) for voice research and affective computing. IEEE Trans. Affect. Comput. 7(2), 190\u2013202 (2016). https:\/\/doi.org\/10.1109\/TAFFC.2015.2457417","journal-title":"IEEE Trans. Affect. Comput."},{"doi-asserted-by":"publisher","unstructured":"Eyben, F., W\u00f6llmer, M., Schuller, B.: OpenSMILE: the Munich versatile and fast open-source audio feature extractor. In: Proceedings of the 18th ACM International Conference on Multimedia, pp. 1459\u20131462. Association for Computing Machinery, New York, NY, USA, October 2010. https:\/\/doi.org\/10.1145\/1873951.1874246","key":"6_CR13","DOI":"10.1145\/1873951.1874246"},{"doi-asserted-by":"crossref","unstructured":"Fan, H., et al.: Multiscale vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6824\u20136835 (2021)","key":"6_CR14","DOI":"10.1109\/ICCV48922.2021.00675"},{"issue":"2","key":"6_CR15","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1177\/1529100618808244","volume":"19","author":"AC Graesser","year":"2018","unstructured":"Graesser, A.C., Fiore, S.M., Greiff, S., Andrews-Todd, J., Foltz, P.W., Hesse, F.W.: Advancing the science of collaborative problem solving. Psychol. Sci. Pub. Interest 19(2), 59\u201392 (2018). https:\/\/doi.org\/10.1177\/1529100618808244","journal-title":"Psychol. Sci. Pub. Interest"},{"issue":"12","key":"6_CR16","doi-asserted-by":"publisher","first-page":"77","DOI":"10.3390\/mti5120077","volume":"5","author":"M de Haas","year":"2021","unstructured":"de Haas, M., Vogt, P., Krahmer, E.: When preschoolers interact with an educational robot, does robot feedback influence engagement? Multimodal Technol. Interact. 5(12), 77 (2021)","journal-title":"Multimodal Technol. Interact."},{"doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., Satoh, Y.: Can spatiotemporal 3D CNNs retrace the history of 2D CNNs and ImageNet? In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6546\u20136555 (2018)","key":"6_CR17","DOI":"10.1109\/CVPR.2018.00685"},{"key":"6_CR18","series-title":"Educational Assessment in an Information Age","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1007\/978-94-017-9395-7_2","volume-title":"Assessment and Teaching of 21st Century Skills","author":"F Hesse","year":"2015","unstructured":"Hesse, F., Care, E., Buder, J., Sassenberg, K., Griffin, P.: A framework for teachable collaborative problem solving skills. In: Griffin, P., Care, E. (eds.) Assessment and Teaching of 21st Century Skills. EAIA, pp. 37\u201356. Springer, Dordrecht (2015). https:\/\/doi.org\/10.1007\/978-94-017-9395-7_2"},{"doi-asserted-by":"crossref","unstructured":"Hu, Y., Fua, P., Wang, W., Salzmann, M.: Single-stage 6D object pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020","key":"6_CR19","DOI":"10.1109\/CVPR42600.2020.00300"},{"doi-asserted-by":"publisher","unstructured":"Kandoi, C., et al.: Intentional microgesture recognition for extended human-computer interaction. In: Kurosu, M., Hashizume, A. (eds.) HCII 2023. LNCS, vol. 14011, pp. 499\u2013518. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-35596-7_32","key":"6_CR20","DOI":"10.1007\/978-3-031-35596-7_32"},{"doi-asserted-by":"crossref","unstructured":"Kendon, A.: Gesticulation and speech: two aspects of the process of utterance. In: The Relationship of Verbal and Nonverbal Communication, vol. 25, pp. 207\u2013227 (1980)","key":"6_CR21","DOI":"10.1515\/9783110813098.207"},{"doi-asserted-by":"crossref","unstructured":"Kendon, A.: Gesture: Visible Action as Utterance. Cambridge University Press (2004)","key":"6_CR22","DOI":"10.1017\/CBO9780511807572"},{"doi-asserted-by":"crossref","unstructured":"Khebour, I., et\u00a0al.: When text and speech are not enough: a multimodal dataset of collaboration in a situated task (2024)","key":"6_CR23","DOI":"10.5334\/johd.168"},{"doi-asserted-by":"crossref","unstructured":"Kita, S.: Pointing: a foundational building block of human communication. In: Pointing: Where Language, Culture, and Cognition Meet, pp.\u00a01\u20138 (2003)","key":"6_CR24","DOI":"10.4324\/9781410607744"},{"key":"6_CR25","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1007\/s10919-014-0200-6","volume":"39","author":"APH Kong","year":"2015","unstructured":"Kong, A.P.H., Law, S.P., Kwan, C.C.Y., Lai, C., Lam, V.: A coding system with independent annotations of gesture forms and functions during verbal communication: development of a database of speech and gesture (dosage). J. Nonverbal Behav. 39, 93\u2013111 (2015)","journal-title":"J. Nonverbal Behav."},{"doi-asserted-by":"crossref","unstructured":"Krishnaswamy, N., et al.: Diana\u2019s world: a situated multimodal interactive agent. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 13618\u201313619 (2020)","key":"6_CR26","DOI":"10.1609\/aaai.v34i09.7096"},{"unstructured":"Krishnaswamy, N., et al.: Communicating and acting: understanding gesture in simulation semantics. In: IWCS 2017-12th International Conference on Computational Semantics-Short papers (2017)","key":"6_CR27"},{"doi-asserted-by":"crossref","unstructured":"Krishnaswamy, N., Pustejovsky, J.: Generating a novel dataset of multimodal referring expressions. In: Proceedings of the 13th International Conference on Computational Semantics-Short Papers, pp. 44\u201351 (2019)","key":"6_CR28","DOI":"10.18653\/v1\/W19-0507"},{"key":"6_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"574","DOI":"10.1007\/978-3-030-58520-4_34","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Labb\u00e9","year":"2020","unstructured":"Labb\u00e9, Y., Carpentier, J., Aubry, M., Sivic, J.: CosyPose: consistent multi-view multi-object 6D pose estimation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12362, pp. 574\u2013591. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58520-4_34"},{"unstructured":"Lai, K., et al.: Modeling theory of mind in multimodal HCI. In: Digital Human Modeling and Applications in Health, Safety, Ergonomics and Risk Management. Springer (2024)","key":"6_CR30"},{"issue":"4","key":"6_CR31","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1093\/jos\/ffp004","volume":"26","author":"A Lascarides","year":"2009","unstructured":"Lascarides, A., Stone, M.: A formal semantic analysis of gesture. J. Semant. 26(4), 393\u2013449 (2009)","journal-title":"J. Semant."},{"doi-asserted-by":"publisher","unstructured":"Li, J., Jin, K., Zhou, D., Kubota, N., Ju, Z.: Attention mechanism-based CNN for facial expression recognition. Neurocomputing 411, 340\u2013350 (2020). https:\/\/doi.org\/10.1016\/j.neucom.2020.06.014","key":"6_CR32","DOI":"10.1016\/j.neucom.2020.06.014"},{"issue":"3","key":"6_CR33","doi-asserted-by":"publisher","first-page":"1195","DOI":"10.1109\/TAFFC.2020.2981446","volume":"13","author":"S Li","year":"2022","unstructured":"Li, S., Deng, W.: Deep facial expression recognition: a survey. IEEE Trans. Affect. Comput. 13(3), 1195\u20131215 (2022). https:\/\/doi.org\/10.1109\/TAFFC.2020.2981446","journal-title":"IEEE Trans. Affect. Comput."},{"unstructured":"Mather, S.M.: Ethnographic research on the use of visually based regulators for teachers and interpreters. In: Attitudes, Innuendo, and Regulators, pp. 136\u2013161 (2005)","key":"6_CR34"},{"unstructured":"McNeill, D.: Hand and mind. In: Advances in Visual Semiotics, vol. 351 (1992)","key":"6_CR35"},{"doi-asserted-by":"crossref","unstructured":"Narayana, P., Beveridge, R., Draper, B.A.: Gesture recognition: locus on the hands. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5235\u20135244 (2018)","key":"6_CR36","DOI":"10.1109\/CVPR.2018.00549"},{"doi-asserted-by":"publisher","unstructured":"Oertel, C., Salvi, G.: A gaze-based method for relating group involvement to individual engagement in multimodal multiparty dialogue. In: Proceedings of the 15th ACM on International Conference on Multimodal Interaction - ICMI 2013, pp. 99\u2013106. ACM Press, Sydney, Australia (2013). https:\/\/doi.org\/10.1145\/2522848.2522865","key":"6_CR37","DOI":"10.1145\/2522848.2522865"},{"issue":"2","key":"6_CR38","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1080\/01411920050000953","volume":"26","author":"L Ogden","year":"2000","unstructured":"Ogden, L.: Collaborative tasks, collaborative children: an analysis of reciprocity during peer interaction at key stage 1. Br. Edu. Res. J. 26(2), 211\u2013226 (2000)","journal-title":"Br. Edu. Res. J."},{"issue":"1","key":"6_CR39","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1162\/0891201053630264","volume":"31","author":"M Palmer","year":"2005","unstructured":"Palmer, M., Gildea, D., Kingsbury, P.: The proposition bank: an annotated corpus of semantic roles. Comput. Linguist. 31(1), 71\u2013106 (2005)","journal-title":"Comput. Linguist."},{"unstructured":"Pustejovsky, J., Krishnaswamy, N.: VoxML: a visualization modeling language. In: Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016), pp. 4606\u20134613. European Language Resources Association (ELRA), Portoro\u017e, Slovenia, May 2016. https:\/\/aclanthology.org\/L16-1730","key":"6_CR40"},{"issue":"3\u20134","key":"6_CR41","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1007\/s13218-021-00727-5","volume":"35","author":"J Pustejovsky","year":"2021","unstructured":"Pustejovsky, J., Krishnaswamy, N.: Embodied human computer interaction. KI-K\u00fcnstliche Intelligenz 35(3\u20134), 307\u2013327 (2021)","journal-title":"KI-K\u00fcnstliche Intelligenz"},{"doi-asserted-by":"publisher","unstructured":"Pustejovsky, J., Krishnaswamy, N.: Multimodal semantics for affordances and actions. In: Kurosu, M. (ed.) HCII 2022. LNCS, vol. 13302, pp. 137\u2013160. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-05311-5_9","key":"6_CR42","DOI":"10.1007\/978-3-031-05311-5_9"},{"unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision (2022)","key":"6_CR43"},{"issue":"2","key":"6_CR44","doi-asserted-by":"publisher","first-page":"1179","DOI":"10.1109\/LRA.2016.2532924","volume":"1","author":"C Rennie","year":"2016","unstructured":"Rennie, C., Shome, R., Bekris, K.E., De Souza, A.F.: A dataset for improved RGBD-based object detection and pose estimation for warehouse pick-and-place. IEEE Rob. Autom. Lett. 1(2), 1179\u20131185 (2016)","journal-title":"IEEE Rob. Autom. Lett."},{"doi-asserted-by":"publisher","unstructured":"Ruan, X., Palansuriya, C., Constantin, A.: Affective dynamic based technique for facial emotion recognition (FER) to support intelligent tutors in education. In: Wang, N., Rebolledo-Mendez, G., Matsuda, N., Santos, O.C., Dimitrova, V. (eds.) AIED, vol. 13916, pp. 774\u2013779. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-36272-9_70","key":"6_CR45","DOI":"10.1007\/978-3-031-36272-9_70"},{"doi-asserted-by":"crossref","unstructured":"Sap, M., LeBras, R., Fried, D., Choi, Y.: Neural theory-of-mind? On the limits of social intelligence in large LMS. arXiv preprint arXiv:2210.13312 (2022)","key":"6_CR46","DOI":"10.18653\/v1\/2022.emnlp-main.248"},{"issue":"2","key":"6_CR47","doi-asserted-by":"publisher","first-page":"107","DOI":"10.18608\/jla.2015.22.9","volume":"2","author":"B Schneider","year":"2015","unstructured":"Schneider, B., Pea, R.: Does seeing one another\u2019s gaze affect group dialogue? A computational approach. J. Learn. Anal. 2(2), 107\u2013133 (2015)","journal-title":"J. Learn. Anal."},{"issue":"4","key":"6_CR48","doi-asserted-by":"publisher","first-page":"713","DOI":"10.1007\/s11257-021-09290-y","volume":"31","author":"AEB Stewart","year":"2021","unstructured":"Stewart, A.E.B., Keirn, Z., D\u2019Mello, S.K.: Multimodal modeling of collaborative problem-solving facets in triads. User Model. User-Adap. Inter. 31(4), 713\u2013751 (2021). https:\/\/doi.org\/10.1007\/s11257-021-09290-y","journal-title":"User Model. User-Adap. Inter."},{"doi-asserted-by":"crossref","unstructured":"Sun, C., Shute, V.J., Stewart, A., Yonehiro, J., Duran, N., D\u2019Mello, S.: Towards a generalized competency model of collaborative problem solving. Comput. Educ. 143, 103672 (2020). https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0360131519302258","key":"6_CR49","DOI":"10.1016\/j.compedu.2019.103672"},{"key":"6_CR50","doi-asserted-by":"publisher","DOI":"10.1016\/j.chb.2021.107120","volume":"128","author":"C Sun","year":"2022","unstructured":"Sun, C., et al.: The relationship between collaborative problem solving behaviors and solution outcomes in a game-based learning environment. Comput. Hum. Behav. 128, 107120 (2022)","journal-title":"Comput. Hum. Behav."},{"unstructured":"Terpstra, C., Khebour, I., Bradford, M., Wisniewski, B., Krishnaswamy, N., Blanchard, N.: How good is automatic segmentation as a multimodal discourse annotation aid? (2023)","key":"6_CR51"},{"unstructured":"Tomasello, M., et al.: Joint attention as social cognition. In: Joint Attention: Its Origins and Role in Development, vol. 103130, pp. 103\u2013130 (1995)","key":"6_CR52"},{"unstructured":"Tong, Z., Song, Y., Wang, J., Wang, L.: VideoMAE: masked autoencoders are data-efficient learners for self-supervised video pre-training. In: Advances in Neural Information Processing Systems, vol. 35, pp. 10078\u201310093 (2022)","key":"6_CR53"},{"issue":"5","key":"6_CR54","doi-asserted-by":"publisher","first-page":"2523","DOI":"10.1007\/s11423-021-10037-0","volume":"69","author":"T T\u00f6rm\u00e4nen","year":"2021","unstructured":"T\u00f6rm\u00e4nen, T., J\u00e4rvenoja, H., M\u00e4nty, K.: Exploring groups\u2019 affective states during collaborative learning: what triggers activating affect on a group level? Educ. Tech. Res. Dev. 69(5), 2523\u20132545 (2021)","journal-title":"Educ. Tech. Res. Dev."},{"doi-asserted-by":"crossref","unstructured":"Tyree, S., et al.: 6-DoF pose estimation of household objects for robotic manipulation: an accessible dataset and benchmark. In: IROS (2022)","key":"6_CR55","DOI":"10.1109\/IROS47612.2022.9981838"},{"unstructured":"Ullman, T.: Large language models fail on trivial alterations to theory-of-mind tasks. arXiv preprint arXiv:2302.08399 (2023)","key":"6_CR56"},{"doi-asserted-by":"publisher","unstructured":"VanderHoeven, H., Blanchard, N., Krishnaswamy, N.: Robust motion recognition using gesture phase annotation. In: Duffy, V.G. (ed.) HCII 2023. LNCS, vol. 14028, pp. 592\u2013608. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-35741-1_42","key":"6_CR57","DOI":"10.1007\/978-3-031-35741-1_42"},{"doi-asserted-by":"crossref","unstructured":"VanderHoeven, H., Blanchard, N., Krishnaswamy, N.: Point target detection for multimodal communication. In: Digital Human Modeling and Applications in Health, Safety, Ergonomics and Risk Management. Springer (2024)","key":"6_CR58","DOI":"10.1007\/978-3-031-61060-8_25"},{"doi-asserted-by":"crossref","unstructured":"Velikovich, L., Williams, I., Scheiner, J., Aleksic, P., Moreno, P., Riley, M.: Semantic lattice processing in contextual automatic speech recognition for google assistant, pp. 2222\u20132226 (2018). https:\/\/www.isca-speech.org\/archive\/Interspeech_2018\/pdfs\/2453.pdf","key":"6_CR59","DOI":"10.21437\/Interspeech.2018-2453"},{"doi-asserted-by":"crossref","unstructured":"Wang, G., Manhardt, F., Tombari, F., Ji, X.: GDR-Net: geometry-guided direct regression network for monocular 6D object pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16611\u201316621, June 2021","key":"6_CR60","DOI":"10.1109\/CVPR46437.2021.01634"},{"key":"6_CR61","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1007\/978-3-642-23774-4_45","volume-title":"Human-Computer Interaction \u2013 INTERACT 2011","author":"K Wolf","year":"2011","unstructured":"Wolf, K., Naumann, A., Rohs, M., M\u00fcller, J.: A taxonomy of microinteractions: defining microgestures based on ergonomic and scenario-dependent requirements. In: Campos, P., Graham, N., Jorge, J., Nunes, N., Palanque, P., Winckler, M. (eds.) INTERACT 2011. LNCS, vol. 6946, pp. 559\u2013575. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-23774-4_45"},{"unstructured":"Zhang, F., et al.: MediaPipe hands: on-device real-time hand tracking. arXiv preprint arXiv:2006.10214 (2020)","key":"6_CR62"},{"doi-asserted-by":"crossref","unstructured":"Zoric, G., Smid, K., Pandzic, I.S.: Facial gestures: taxonomy and application of non-verbal, non-emotional facial displays for embodied conversational agents. In: Conversational Informatics: An Engineering Approach, pp. 161\u2013182 (2007)","key":"6_CR63","DOI":"10.1002\/9780470512470.ch9"}],"container-title":["Lecture Notes in Computer Science","Human Interface and the Management of Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-60107-1_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T22:18:10Z","timestamp":1732141090000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-60107-1_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031601064","9783031601071"],"references-count":63,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-60107-1_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"1 June 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"HCII","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Human-Computer Interaction","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Washington DC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 June 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 July 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"hcii2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2024.hci.international\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}