{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T09:17:19Z","timestamp":1767777439894,"version":"3.41.0"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031939648","type":"print"},{"value":"9783031939655","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-93965-5_19","type":"book-chapter","created":{"date-parts":[[2025,6,5]],"date-time":"2025-06-05T14:53:24Z","timestamp":1749135204000},"page":"265-281","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Feature Contributions to\u00a0Multimodal Interpretation of\u00a0Common Ground"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4374-7263","authenticated-orcid":false,"given":"Ibrahim","family":"Khebour","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2232-4300","authenticated-orcid":false,"given":"Changsoo","family":"Jung","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5604-7920","authenticated-orcid":false,"given":"Jack","family":"Fitzgerald","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1097-4821","authenticated-orcid":false,"given":"Huma","family":"Jamil","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7878-7227","authenticated-orcid":false,"given":"Nikhil","family":"Krishnaswamy","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,6,6]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Ai, W., Zhang, F., Meng, T., Shou, Y., Shao, H., Li, K.: A two-stage multimodal emotion recognition model based on graph contrastive learning. In: 2023 IEEE 29th International Conference on Parallel and Distributed Systems (ICPADS), pp. 397\u2013404. IEEE (2023)","DOI":"10.1109\/ICPADS60453.2023.00067"},{"key":"19_CR2","doi-asserted-by":"publisher","unstructured":"Bradford, M., Khebour, I., Blanchard, N., Krishnaswamy, N.: Automatic detection of collaborative states in small groups using multimodal features. In: In: Wang, N., Rebolledo-Mendez, G., Matsuda, N., Santos, O.C., Dimitrova, V. (eds.) International Conference on Artificial Intelligence in Education, pp. 767\u2013773. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-36272-9_69","DOI":"10.1007\/978-3-031-36272-9_69"},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Bradford, M., Khebour, I., VanderHoeven, H., Blanchard, N., Krishnaswamy, N.: Modeling individual beliefs in co-situated groups. In: International Conference on Human-Computer Interaction (HCII). Springer (2025)","DOI":"10.1007\/978-3-031-93412-4_8"},{"key":"19_CR4","unstructured":"Brutti, R., Donatelli, L., Lai, K., Pustejovsky, J.: Abstract meaning representation for gesture. In: Proceedings of the Thirteenth Language Resources and Evaluation Conference (2022)"},{"key":"19_CR5","doi-asserted-by":"crossref","unstructured":"Budzianowski, P., et al.: Multiwoz\u2013A large-scale multi-domain wizard-of-oz dataset for task-oriented dialogue modelling. arXiv preprint arXiv:1810.00278 (2018)","DOI":"10.18653\/v1\/D18-1547"},{"key":"19_CR6","doi-asserted-by":"publisher","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009). https:\/\/doi.org\/10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"19_CR7","doi-asserted-by":"crossref","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 (2010)","DOI":"10.1145\/1873951.1874246"},{"key":"19_CR8","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"19_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"727","DOI":"10.1007\/978-3-319-46484-8_44","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Jabri","year":"2016","unstructured":"Jabri, A., Joulin, A., van der Maaten, L.: Revisiting visual question answering baselines. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 727\u2013739. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_44"},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"Jacqmin, L., Rojas-Barahona, L.M., Favre, B.: \u201cdo you follow me?\u201d: a survey of recent approaches in dialogue state tracking. arXiv preprint arXiv:2207.14627 (2022)","DOI":"10.18653\/v1\/2022.sigdial-1.33"},{"key":"19_CR11","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. J. Open Humanit. Data 10(1) (2024)","DOI":"10.5334\/johd.168"},{"key":"19_CR12","unstructured":"Khebour, I., et\u00a0al.: Common ground tracking in multimodal dialogue. arXiv preprint arXiv:2403.17284 (2024)"},{"key":"19_CR13","doi-asserted-by":"publisher","first-page":"557","DOI":"10.1162\/tacl_a_00384","volume":"9","author":"L Liao","year":"2021","unstructured":"Liao, L., Long, L.H., Ma, Y., Lei, W., Chua, T.S.: Dialogue state tracking with incremental reasoning. Trans. Assoc. Comput. Linguist. 9, 557\u2013569 (2021)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"19_CR14","unstructured":"Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., Ng, A.Y., et al.: Multimodal deep learning. In: ICML, vol. 11, pp. 689\u2013696 (2011)"},{"issue":"6","key":"19_CR15","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2016","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"19_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.compedu.2019.103672","volume":"143","author":"C Sun","year":"2020","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)","journal-title":"Comput. Educ."},{"key":"19_CR17","doi-asserted-by":"publisher","first-page":"1479905","DOI":"10.3389\/frai.2024.1479905","volume":"7","author":"J Tu","year":"2024","unstructured":"Tu, J., Rim, K., Ye, B., Lai, K., Pustejovsky, J.: Dense paraphrasing for multimodal dialogue interpretation. Front. Artif. Intell. 7, 1479905 (2024)","journal-title":"Front. Artif. Intell."},{"key":"19_CR18","doi-asserted-by":"publisher","unstructured":"VanderHoeven, H., Blanchard, N., Krishnaswamy, N.: Robust motion recognition using gesture phase annotation. In: In: Duffy, V.G. (eds.) International Conference on Human-Computer Interaction, pp. 592\u2013608. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-35741-1_42","DOI":"10.1007\/978-3-031-35741-1_42"},{"key":"19_CR19","doi-asserted-by":"publisher","unstructured":"VanderHoeven, H., Blanchard, N., Krishnaswamy, N.: Point target detection for multimodal communication. In: In: Duffy, V.G. (eds.) International Conference on Human-Computer Interaction, pp. 356\u2013373. Springer (2024). https:\/\/doi.org\/10.1007\/978-3-031-61060-8_25","DOI":"10.1007\/978-3-031-61060-8_25"},{"key":"19_CR20","unstructured":"Venkatesha, V., et al.: Propositional extraction from natural speech in small group collaborative tasks. In: Proceedings of the 17th International Conference on Educational Data Mining, pp. 169\u2013180 (2024)"},{"key":"19_CR21","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1016\/j.neuroimage.2013.11.007","volume":"102","author":"GK Verma","year":"2014","unstructured":"Verma, G.K., Tiwary, U.S.: Multimodal fusion framework: a multiresolution approach for emotion classification and recognition from physiological signals. Neuroimage 102, 162\u2013172 (2014)","journal-title":"Neuroimage"},{"key":"19_CR22","doi-asserted-by":"publisher","first-page":"12360","DOI":"10.1109\/TCSVT.2024.3435561","volume":"12","author":"D Yang","year":"2024","unstructured":"Yang, D., et al.: Asynchronous multimodal video sequence fusion via learning modality-exclusive and-agnostic representations. IEEE Trans. Circ. Syst. Video Technol. 12, 12360\u201312375 (2024)","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"19_CR23","unstructured":"Yang, Z., Yuan, Y., Wu, Y., Cohen, W.W., Salakhutdinov, R.R.: Review networks for caption generation. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"19_CR24","doi-asserted-by":"publisher","unstructured":"Zhang, Z., Ji, H.: Abstract meaning representation guided graph encoding and decoding for joint information extraction. In: Toutanova, K., Rumshisky, A., Zettlemoyer, L., Hakkani-Tur, D., Beltagy, I., Bethard, S., Cotterell, R., Chakraborty, T., Zhou, Y. (eds.) Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 39\u201349. Association for Computational Linguistics, Online (2021). https:\/\/doi.org\/10.18653\/v1\/2021.naacl-main.4, https:\/\/aclanthology.org\/2021.naacl-main.4\/","DOI":"10.18653\/v1\/2021.naacl-main.4"}],"container-title":["Lecture Notes in Computer Science","Human-Computer Interaction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-93965-5_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,5]],"date-time":"2025-06-05T14:53:28Z","timestamp":1749135208000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-93965-5_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031939648","9783031939655"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-93965-5_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"6 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to disclose.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"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":"Gothenburg","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"hcii2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2025.hci.international\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}