{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T04:27:10Z","timestamp":1787372830104,"version":"build-2736575974"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032093202","type":"print"},{"value":"9783032093219","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T00:00:00Z","timestamp":1762560000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T00:00:00Z","timestamp":1762560000000},"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\/978-3-032-09321-9_34","type":"book-chapter","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T04:58:20Z","timestamp":1762491500000},"page":"495-509","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Collaborative Multimodal Learning for\u00a0Human-Human Interaction Recognition in\u00a0Videos"],"prefix":"10.1007","author":[{"given":"Vo Ngoc Thanh","family":"Huynh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thi Ngoc Ha","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9556-484X","authenticated-orcid":false,"given":"Tien-Dung","family":"Mai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,8]]},"reference":[{"key":"34_CR1","unstructured":"Pruss, S., Alper, M., Averbuch-Elor, H.: Dynamic scene understanding from vision-language representations (2025). arXiv:2501.11653"},{"key":"34_CR2","doi-asserted-by":"crossref","unstructured":"Shaikh, M.B., et al.: From CNNs to transformers in multimodal human action recognition: a survey (2024). arXiv:2405.15813","DOI":"10.1145\/3664815"},{"issue":"1","key":"34_CR3","first-page":"773","volume":"81","author":"V Khean","year":"2024","unstructured":"Khean, V., et al.: Human interaction recognition in surveillance videos using hybrid deep learning and machine learning models. Comput. Mater. Contin. 81(1), 773\u2013787 (2024)","journal-title":"Comput. Mater. Contin."},{"key":"34_CR4","doi-asserted-by":"crossref","unstructured":"Alper, M., Averbuch-Elor, H.: Learning human-human interactions in images from weak textual supervision. In: ICCV, pp. 12345\u201312354. IEEE (2023)","DOI":"10.1109\/ICCV51070.2023.00270"},{"key":"34_CR5","unstructured":"Radford, A., et al.: Robust speech recognition via large-scale weak supervision (2022). arXiv:2212.04356"},{"key":"34_CR6","unstructured":"Gabeur, V.: Multi-modal learning for video understanding. Ph.D. thesis, Universit\u00e9 Grenoble Alpes (2022)"},{"key":"34_CR7","doi-asserted-by":"crossref","unstructured":"Gao, X., et al.: Pairwise emotional relationship recognition in drama videos: dataset and benchmark (2021). arXiv:2109.11243","DOI":"10.1145\/3474085.3475493"},{"key":"34_CR8","doi-asserted-by":"crossref","unstructured":"Arnab, A., et al.: ViViT: a video vision transformer (2021). arXiv:2103.15691","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"34_CR9","doi-asserted-by":"crossref","unstructured":"Brown, A., et al.: Automated video labelling: identifying faces by corroborative evidence. In: MIPR, pp. 175\u2013184. IEEE (2021)","DOI":"10.1109\/MIPR51284.2021.00019"},{"key":"34_CR10","doi-asserted-by":"crossref","unstructured":"Brown, A., et al.: Face, body, voice: video person-clustering with multiple modalities. In: ICCVW, pp. 2698\u20132707. IEEE (2021)","DOI":"10.1109\/ICCVW54120.2021.00357"},{"key":"34_CR11","doi-asserted-by":"crossref","unstructured":"Kalogeiton, V., Zisserman, A.: Constrained video face clustering using 1NN relations. In: BMVC, pp. 1\u201312. BMVA Press (2020)","DOI":"10.5244\/C.34.185"},{"key":"34_CR12","unstructured":"Dosovitskiy, A., et al.: An image is worth 16\u00d716 words: transformers for image recognition at scale (2020). arXiv:2010.11929"},{"key":"34_CR13","doi-asserted-by":"crossref","unstructured":"Kukleva, A., et al.: Learning interactions and relationships between movie characters. In: CVPR, pp. 10189\u201310198. IEEE (2020)","DOI":"10.1109\/CVPR42600.2020.00987"},{"key":"34_CR14","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? In: CVPR, pp. 6299\u20136308. IEEE (2017)"},{"key":"34_CR15","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: AAAI Conference on Artificial Intelligence (AAAI), pp. 7444\u20137452. AAAI Press (2018)","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"34_CR16","unstructured":"Kay, W., et al.: The kinetics human action video dataset (2017). arXiv:1705.06950"},{"issue":"3","key":"34_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2682899","volume":"47","author":"SK D\u2019Mello","year":"2015","unstructured":"D\u2019Mello, S.K., Kory, J.: A Review and Meta-Analysis of Multimodal Affect Detection Systems. ACM Comput. Surv. 47(3), 1\u201336 (2015)","journal-title":"ACM Comput. Surv."},{"issue":"6","key":"34_CR18","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1007\/s00530-010-0182-0","volume":"16","author":"PK Atrey","year":"2010","unstructured":"Atrey, P.K., et al.: Multimodal fusion for multimedia analysis: a survey. Multimed. Syst. 16(6), 345\u2013379 (2010)","journal-title":"Multimed. Syst."},{"key":"34_CR19","doi-asserted-by":"crossref","unstructured":"Castellano, G., et al.: Emotion recognition through multiple modalities: face, body gesture, speech. In: Affect and Emotion in Human-Computer Interaction, pp. 92\u2013103. Springer (2008)","DOI":"10.1007\/978-3-540-85099-1_8"},{"key":"34_CR20","unstructured":"Carreira, J., et al.: A short note on the kinetics-700 human action dataset (2019). arXiv:1907.06987"},{"key":"34_CR21","doi-asserted-by":"crossref","unstructured":"Heilbron, F.C., et al.: ActivityNet: a large-scale video benchmark for human activity understanding. In: CVPR, pp. 961\u2013970. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"34_CR22","doi-asserted-by":"crossref","unstructured":"Zhao, H., et \u00cdal.: HACS: human action clips and segments dataset for recognition and temporal localization. In: ICCV, pp. 8668\u20138678. IEEE (2019)","DOI":"10.1109\/ICCV.2019.00876"},{"key":"34_CR23","unstructured":"Soomro, K., et al.: UCF101: a dataset of 101 human action classes from videos in the wild (2012). arXiv:1212.0402"},{"key":"34_CR24","doi-asserted-by":"crossref","unstructured":"Xiong, Y., et al.: Recognizing complex events from static images by fusing deep channels. In: CVPR, pp. 1600\u20131609. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7298768"},{"key":"34_CR25","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: Zero-shot learning via visual abstraction. In: ECCV, pp. 401\u2013416. Springer (2014)","DOI":"10.1007\/978-3-319-10593-2_27"},{"key":"34_CR26","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization (2017). arXiv:1711.05101"},{"issue":"11","key":"34_CR27","doi-asserted-by":"publisher","first-page":"1473","DOI":"10.1109\/TCSVT.2008.2005594","volume":"18","author":"P Turaga","year":"2008","unstructured":"Turaga, P., et al.: Machine recognition of human activities: a survey. IEEE Trans. Circuits Syst. Video Technol. 18(11), 1473\u20131488 (2008)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"6","key":"34_CR28","doi-asserted-by":"publisher","first-page":"976","DOI":"10.1016\/j.imavis.2009.11.014","volume":"28","author":"R Poppe","year":"2010","unstructured":"Poppe, R.: A survey on vision-based human action recognition. Image Vis. Comput. 28(6), 976\u2013990 (2010)","journal-title":"Image Vis. Comput."},{"issue":"6","key":"34_CR29","doi-asserted-by":"publisher","first-page":"865","DOI":"10.1109\/TSMCC.2011.2178594","volume":"42","author":"OP Popoola","year":"2012","unstructured":"Popoola, O.P., Wang, K.: Video-based abnormal human behavior recognition: a review. IEEE Trans. Syst. Man Cybern. C 42(6), 865\u2013878 (2012)","journal-title":"IEEE Trans. Syst. Man Cybern. C"},{"key":"34_CR30","doi-asserted-by":"publisher","first-page":"28","DOI":"10.3389\/frobt.2015.00028","volume":"2","author":"M Vrigkas","year":"2015","unstructured":"Vrigkas, M., Nikou, C., Kakadiaris, I.A.: A review of human activity recognition methods. Front. Robot. AI 2, 28 (2015)","journal-title":"Front. Robot. AI"},{"key":"34_CR31","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1016\/j.patcog.2015.11.019","volume":"53","author":"L Lo Presti","year":"2016","unstructured":"Lo Presti, L., La Cascia, M.: 3D skeleton-based human action classification. Pattern Recognit. 53, 130\u2013147 (2016)","journal-title":"Pattern Recognit."},{"key":"34_CR32","unstructured":"Vaswani, A., et al.: Attention is all you need (2017). arXiv:1706.03762"},{"key":"34_CR33","unstructured":"Shu, X., Tang, J., Qi, G.J., Liu, W., Yang, J.: Hierarchical long short-term concurrent memory for human interaction recognition (2018). arXiv:1811.00270"}],"container-title":["Lecture Notes in Computer Science","Computational Collective Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-09321-9_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T04:08:38Z","timestamp":1787371718000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-09321-9_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,8]]},"ISBN":["9783032093202","9783032093219"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-09321-9_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,8]]},"assertion":[{"value":"8 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICCCI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Collective Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ho Chi Minh City","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","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":"12 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccci2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iccci.pwr.edu.pl\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}