{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T13:05:58Z","timestamp":1790773558562,"version":"4.1.0"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2023,2,9]],"date-time":"2023-02-09T00:00:00Z","timestamp":1675900800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,2,9]],"date-time":"2023-02-09T00:00:00Z","timestamp":1675900800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100004410","name":"T\u00fcrkiye Bilimsel ve Teknolojik Ara\u015ftirma Kurumu","doi-asserted-by":"publisher","award":["217E040"],"award-info":[{"award-number":["217E040"]}],"id":[{"id":"10.13039\/501100004410","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Lang Resources & Evaluation"],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1007\/s10579-022-09632-1","type":"journal-article","created":{"date-parts":[[2023,2,10]],"date-time":"2023-02-10T00:00:00Z","timestamp":1675987200000},"page":"985-1009","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["The eHRI database: a multimodal database of engagement in human\u2013robot interactions"],"prefix":"10.1007","volume":"57","author":[{"given":"Ege","family":"Kesim","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tugce","family":"Numanoglu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oyku","family":"Bayramoglu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bekir Berker","family":"Turker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nusrah","family":"Hussain","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Metin","family":"Sezgin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yucel","family":"Yemez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2715-2368","authenticated-orcid":false,"given":"Engin","family":"Erzin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,2,9]]},"reference":[{"key":"9632_CR1","unstructured":"Al\u00a0Moubayed, S., Beskow, J., & Skantze, G. (2013). The Furhat social companion talking head. In Interspeech 2013, 14th annual conference of the international speech communication association (pp. 747\u2013749)"},{"key":"9632_CR2","doi-asserted-by":"crossref","unstructured":"Aubrey, A. J., Marshall, D., Rosin, P. L., Vendeventer, J., Cunningham, D. W., & Wallraven, C. (2013). Cardiff conversation database (CCDb): A database of natural dyadic conversations. In 2013 IEEE conference on computer vision and pattern recognition workshops (pp. 277\u2013282)","DOI":"10.1109\/CVPRW.2013.48"},{"key":"9632_CR3","doi-asserted-by":"crossref","unstructured":"Baltrusaitis, T., Zadeh, A., Lim, Y. C., & Morency, L. P. (2018). OpenFace 2.0: Facial behavior analysis toolkit. In 13th IEEE international conference on automatic face gesture recognition (FG 2018) (pp. 59\u201366)","DOI":"10.1109\/FG.2018.00019"},{"key":"9632_CR4","doi-asserted-by":"crossref","unstructured":"Ben-Youssef, A., Clavel, C., Essid, S., Bilac, M., Chamoux, M., & Lim, A. (2017). UE-HRI: A new dataset for the study of user engagement in spontaneous human\u2013robot interactions. In ICMI 2017, 19th ACM international conference on multimodal interaction (pp. 464\u2013472)","DOI":"10.1145\/3136755.3136814"},{"issue":"5","key":"9632_CR5","doi-asserted-by":"publisher","first-page":"815","DOI":"10.1007\/s12369-019-00591-2","volume":"11","author":"A Ben Youssef","year":"2019","unstructured":"Ben Youssef, A., Varni, G., Essid, S., & Clavel, C. (2019). On-the-fly detection of user engagement decrease in spontaneous human\u2013robot interaction. International Journal of Social Robotics, 11(5), 815\u2013828.","journal-title":"International Journal of Social Robotics"},{"issue":"4","key":"9632_CR6","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","volume":"42","author":"C Busso","year":"2008","unstructured":"Busso, C., Bulut, M., Lee, C. C., Kazemzadeh, A., Mower, E., Kim, S., Chang, J. N., Lee, S., & Narayanan, S. S. (2008). IEMOCAP: Interactive emotional dyadic motion capture database. Language Resources and Evaluation, 42(4), 335.","journal-title":"Language Resources and Evaluation"},{"key":"9632_CR7","doi-asserted-by":"crossref","unstructured":"Cafaro, A., Wagner, J., Baur, T., Dermouche, S., Torres\u00a0Torres, M., Pelachaud, C., Andr\u00e9, E., & Valstar, M. (2017). The NoXi database: Multimodal recordings of mediated novice-expert interactions. In ICMI 2017, 19th ACM international conference on multimodal interaction (pp. 350\u2013359)","DOI":"10.1145\/3136755.3136780"},{"key":"9632_CR8","doi-asserted-by":"crossref","unstructured":"Castellano, G., Leite, I., Pereira, A., Martinho, C., Paiva, A., & McOwan, P. W. (2012). Detecting engagement in HRI: An exploration of social and task-based context. In 2012 international conference on privacy, security, risk and trust and 2012 international conference on social computing (pp. 421\u2013428)","DOI":"10.1109\/SocialCom-PASSAT.2012.51"},{"issue":"4","key":"9632_CR9","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1109\/TAFFC.2017.2737019","volume":"10","author":"O Celiktutan","year":"2019","unstructured":"Celiktutan, O., Skordos, E., & Gunes, H. (2019). Multimodal human\u2013human\u2013robot interactions (MHHRI) dataset for studying personality and engagement. IEEE Transactions on Affective Computing, 10(4), 484\u2013497.","journal-title":"IEEE Transactions on Affective Computing"},{"key":"9632_CR12","doi-asserted-by":"crossref","unstructured":"Devillers, L., Rosset, S., Duplessis, G. D., Bechade, L., Yemez, Y., Turker, B. B., Sezgin, M., Erzin, E., El\u00a0Haddad, K., Dupont, S., Deleglise, P., Esteve, Y., Lailler, C., Gilmartin, E., Campbell, N. (2018). Multifaceted engagement in social interaction with a machine: The joker project. In FG 2018, 13th IEEE international conference on automatic face & gesture recognition (pp. 697\u2013701)","DOI":"10.1109\/FG.2018.00110"},{"key":"9632_CR10","doi-asserted-by":"crossref","unstructured":"Devillers, L., Rosset, S., Dubuisson, G. D., Sehili, M. A., B\u00e9chade, L., Delaborde, A., Gossart, C., Letard, V., Yang, F., Yemez, Y., T\u00fcrker, B. B., Sezgin, M., El\u00a0Haddad, K., Dupont, S., Luzzati, D., Est\u00e8ve, Y., Gilmartin, E., & Nick, C. (2015). Multimodal data collection of human\u2013robot humorous interactions in the JOKER project. In ACII 2015, international conference on affective computing and intelligent interaction (pp. 348\u2013354)","DOI":"10.1109\/ACII.2015.7344594"},{"key":"9632_CR13","doi-asserted-by":"crossref","unstructured":"Dhall, A., Kaur, A., Goecke, R., & Gedeon, T. (2018). Emotiw 2018: Audio-video, student engagement and group-level affect prediction. In ICMI 2018, 20th ACM international conference on multimodal interaction (pp. 653\u2013656)","DOI":"10.1145\/3242969.3264993"},{"key":"9632_CR14","doi-asserted-by":"crossref","unstructured":"Glas, N., & Pelachaud, C. (2015). Definitions of engagement in human\u2013agent interaction. In ACII 2015, international conference on affective computing and intelligent interaction (pp. 944\u2013949)","DOI":"10.1109\/ACII.2015.7344688"},{"issue":"4","key":"9632_CR15","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1007\/s10489-013-0503-z","volume":"40","author":"D Griol","year":"2014","unstructured":"Griol, D., Molina, J. M., & Callejas, Z. (2014). Modeling the user state for context-aware spoken interaction in ambient assisted living. Applied Intelligence, 40(4), 749\u2013771.","journal-title":"Applied Intelligence"},{"key":"9632_CR16","unstructured":"Gupta, A., D\u2019Cunha, A., Awasthi, K., & Balasubramanian, V. (2016). DAiSEE: Towards user engagement recognition in the wild. arXiv preprint. arXiv:1609.01885"},{"key":"9632_CR17","doi-asserted-by":"crossref","unstructured":"Hussain, N., Erzin, E., Sezgin, T. M., & Yemez, Y. (2019). Speech driven backchannel generation using deep Q-network for enhancing engagement in human\u2013robot interaction. In Interspeech 2019, 19th annual conference of the international speech communication association (pp. 4445\u20134449)","DOI":"10.21437\/Interspeech.2019-2521"},{"key":"9632_CR18","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3190233","author":"N Hussain","year":"2022","unstructured":"Hussain, N., Erzin, E., Sezgin, T. M., & Yemez, Y. (2022). Training socially engaging robots: Modeling backchannel behaviors with batch reinforcement learning. IEEE Transactions on Affective Computing. https:\/\/doi.org\/10.1109\/TAFFC.2022.3190233.","journal-title":"IEEE Transactions on Affective Computing"},{"key":"9632_CR19","doi-asserted-by":"crossref","unstructured":"Jayagopi, D. B., Sheiki, S., Klotz, D., Wienke, J., Odobez, J. M., Wrede, S., Khalidov, V., Nyugen, L., Wrede, B., & Gatica-Perez, D. (2013). The vernissage corpus: A conversational human\u2013robot-interaction dataset. In HRI 2013, 8th ACM\/IEEE international conference on human\u2013robot interaction (pp. 149\u2013150)","DOI":"10.1109\/HRI.2013.6483545"},{"key":"9632_CR20","doi-asserted-by":"crossref","unstructured":"Kantharaju, R. B., Ringeval, F., & Besacier, L. (2018). Automatic recognition of affective laughter in spontaneous dyadic interactions from audiovisual signals. In ICMI 2018, 20th ACM international conference on multimodal interaction (pp. 220\u2013228)","DOI":"10.1145\/3242969.3243012"},{"key":"9632_CR21","doi-asserted-by":"crossref","unstructured":"Kaur, A., Mustafa, A., Mehta, L., & Dhall, A. (2018). Prediction and localization of student engagement in the wild. In DICTA 2018, digital image computing: Techniques and applications (pp. 1\u20138)","DOI":"10.1109\/DICTA.2018.8615851"},{"issue":"10","key":"9632_CR22","doi-asserted-by":"publisher","first-page":"962","DOI":"10.1016\/j.ijhcs.2006.05.002","volume":"64","author":"KM Lee","year":"2006","unstructured":"Lee, K. M., Jung, Y., Kim, J., & Kim, S. R. (2006). Are physically embodied social agents better than disembodied social agents?: The effects of physical embodiment, tactile interaction, and people\u2019s loneliness in human\u2013robot interaction. International Journal of Human\u2013Computer Studies, 64(10), 962\u2013973.","journal-title":"International Journal of Human\u2013Computer Studies"},{"key":"9632_CR23","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1016\/j.ijhcs.2015.01.001","volume":"77","author":"J Li","year":"2015","unstructured":"Li, J. (2015). The benefit of being physically present: A survey of experimental works comparing copresent robots, telepresent robots and virtual agents. International Journal of Human\u2013Computer Studies, 77, 23\u201337.","journal-title":"International Journal of Human\u2013Computer Studies"},{"key":"9632_CR24","doi-asserted-by":"crossref","unstructured":"Malmir, M., Forster, D., Youngstrom, K., Morrison, L., & Movellan, J. (2013). Home alone: Social robots for digital ethnography of toddler behavior. In IEEE international conference on computer vision workshops (pp. 762\u2013768)","DOI":"10.1109\/ICCVW.2013.104"},{"issue":"1","key":"9632_CR25","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1109\/T-AFFC.2011.20","volume":"3","author":"G McKeown","year":"2012","unstructured":"McKeown, G., Valstar, M., Cowie, R., Pantic, M., & Schroder, M. (2012). The SEMAINE database: Annotated multimodal records of emotionally colored conversations between a person and a limited agent. IEEE Transactions on Affective Computing, 3(1), 5\u201317.","journal-title":"IEEE Transactions on Affective Computing"},{"issue":"2","key":"9632_CR26","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1016\/j.imavis.2012.08.018","volume":"31","author":"A Metallinou","year":"2013","unstructured":"Metallinou, A., Katsamanis, A., & Narayanan, S. (2013). Tracking continuous emotional trends of participants during affective dyadic interactions using body language and speech information. Image and Vision Computing, 31(2), 137\u2013152.","journal-title":"Image and Vision Computing"},{"issue":"3","key":"9632_CR27","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1007\/s10579-015-9300-0","volume":"50","author":"A Metallinou","year":"2016","unstructured":"Metallinou, A., Yang, Z., Cc, Lee, Busso, C., Carnicke, S., & Narayanan, S. (2016). The USC CreativeIT database of multimodal dyadic interactions: From speech and full body motion capture to continuous emotional annotations. Language Resources and Evaluation, 50(3), 497\u2013521.","journal-title":"Language Resources and Evaluation"},{"issue":"01","key":"9632_CR28","doi-asserted-by":"publisher","first-page":"1350005","DOI":"10.1142\/S0219843613500059","volume":"10","author":"SA Moubayed","year":"2013","unstructured":"Moubayed, S. A., Skantze, G., & Beskow, J. (2013). The Furhat back-projected humanoid head: Lip reading, gaze and multi-party interaction. International Journal of Humanoid Robotics, 10(01), 1350005.","journal-title":"International Journal of Humanoid Robotics"},{"key":"9632_CR29","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-05204-1_21","volume-title":"Social robotics","author":"O Mubin","year":"2018","unstructured":"Mubin, O., Ahmad, M. I., Kaur, S., Shi, W., & Khan, A. (2018). Social robots in public spaces: A meta-review. In S. S. Ge, J. J. Cabibihan, M. A. Salichs, E. Broadbent, H. He, A. R. Wagner, & \u00c1. Castro-Gonz\u00e1lez (Eds.), Social robotics (pp. 213\u2013220). Springer International Publishing."},{"key":"9632_CR30","doi-asserted-by":"crossref","unstructured":"Rich, C., Ponsler, B., Holroyd, A., & Sidner, C. L. (2010). Recognizing engagement in human\u2013robot interaction. In HRI 2010, 5th ACM\/IEEE international conference on human\u2013robot interaction (pp. 375\u2013382)","DOI":"10.1109\/HRI.2010.5453163"},{"key":"9632_CR31","doi-asserted-by":"crossref","unstructured":"Ringeval, F., Sonderegger, A., Sauer, J., & Lalanne, D. (2013). Introducing the RECOLA multimodal corpus of remote collaborative and affective interactions. In FG 2013, 10th IEEE international conference and workshops on automatic face and gesture recognition (pp. 1\u20138)","DOI":"10.1109\/FG.2013.6553805"},{"key":"9632_CR32","doi-asserted-by":"crossref","unstructured":"Sharma, M., Ahmetovic, D., Jeni, L. A., & Kitani, K. M. (2018). Recognizing visual signatures of spontaneous head gestures. In WACV 2018, IEEE winter conference on applications of computer vision (pp. 400\u2013408)","DOI":"10.1109\/WACV.2018.00050"},{"issue":"1","key":"9632_CR33","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1016\/j.artint.2005.03.005","volume":"166","author":"CL Sidner","year":"2005","unstructured":"Sidner, C. L., Lee, C., Kidd, C. D., Lesh, N., & Rich, C. (2005). Explorations in engagement for humans and robots. Artificial Intelligence, 166(1), 140\u2013164.","journal-title":"Artificial Intelligence"},{"key":"9632_CR34","doi-asserted-by":"crossref","unstructured":"Valstar, M. (2019). The handbook of multimodal-multisensor interfaces: Language processing, software, commercialization, and emerging directions\u2014Volume 3, association for computing machinery and Morgan & Claypool, chap multimodal databases (pp. 393\u2013421)","DOI":"10.1145\/3233795.3233807"},{"key":"9632_CR35","unstructured":"Vandeventer, J., Aubrey, A., Rosin, P. L., & Marshall, A. D. (2015). 4D Cardiff Conversation Database (4D CCDb): A 4D database of natural, dyadic conversations. In FAAVSP 2015, 1st joint conference on facial analysis, animation, and auditory-visual speech processing (pp. 157\u2013162)"},{"key":"9632_CR36","unstructured":"Wittenburg, P., Brugman, H., Russel, A., Klassmann, A., & Sloetjes, H. (2006). ELAN: A professional framework for multimodality research. In LREC 2006, fifth international conference on language resources and evaluation. Max Planck Institute for Psycholinguistics. https:\/\/archive.mpi.nl\/tla\/elan"}],"container-title":["Language Resources and Evaluation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-022-09632-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10579-022-09632-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-022-09632-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,19]],"date-time":"2023-08-19T08:15:15Z","timestamp":1692432915000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10579-022-09632-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,9]]},"references-count":35,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,9]]}},"alternative-id":["9632"],"URL":"https:\/\/doi.org\/10.1007\/s10579-022-09632-1","relation":{},"ISSN":["1574-020X","1574-0218"],"issn-type":[{"value":"1574-020X","type":"print"},{"value":"1574-0218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,9]]},"assertion":[{"value":"13 December 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 February 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}