{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:40:51Z","timestamp":1765309251006,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276242"],"award-info":[{"award-number":["62276242"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Aviation Science Foundation","award":["2022Z071078001"],"award-info":[{"award-number":["2022Z071078001"]}]},{"name":"Hefei Municipal Natural Science Foundation","award":["HZR2431"],"award-info":[{"award-number":["HZR2431"]}]},{"name":"Dreams Foundation of Jianghuai Advance Technology Center","award":["2023-ZM01Z001"],"award-info":[{"award-number":["2023-ZM01Z001"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3762078","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:54:17Z","timestamp":1761375257000},"page":"14163-14169","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Heterogeneous Encoder Fusion with KAN Decoder for Group Engagement Modeling via 8\u00d7 Sliding Pipelines"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-6651-6067","authenticated-orcid":false,"given":"Yuefeng","family":"Zou","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6157-6769","authenticated-orcid":false,"given":"Hui","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3197-8103","authenticated-orcid":false,"given":"Jun","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8974-3813","authenticated-orcid":false,"given":"Keda","family":"Lu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6860-2772","authenticated-orcid":false,"given":"Linsi","family":"Zhu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1164-0551","authenticated-orcid":false,"given":"Fengzhao","family":"Sun","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2964-4621","authenticated-orcid":false,"given":"Bo","family":"Wang","sequence":"additional","affiliation":[{"name":"Unisound AI Technology Co., Ltd., Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3400-9222","authenticated-orcid":false,"given":"Kun","family":"Yao","sequence":"additional","affiliation":[{"name":"Unisound AI Technology Co., Ltd., Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3598-8564","authenticated-orcid":false,"given":"Jianqing","family":"Sun","sequence":"additional","affiliation":[{"name":"Unisound AI Technology Co., Ltd., Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8309-1301","authenticated-orcid":false,"given":"Jiaen","family":"Liang","sequence":"additional","affiliation":[{"name":"Unisound AI Technology Co., Ltd., Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548363"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3136780"},{"key":"e_1_3_2_1_3_1","unstructured":"Junsong Chen et al. 2023. Pixart-\u03b1: fast training of diffusion transformer for photorealistic text-to-image synthesis. arXiv preprint arXiv:2310.00426."},{"key":"e_1_3_2_1_4_1","unstructured":"Lev Evtodienko. 2021. Multimodal end-to-end group emotion recognition using cross-modal attention. arXiv preprint arXiv:2111.05890."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3678957.3685757"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Jean Gaudart Bernard Giusiano and Laetitia Huiart. 2004. Comparison of the performance of multi-layer perceptron and linear regression for epidemiological data. Computational statistics & data analysis 44 4 547--570.","DOI":"10.1016\/S0167-9473(02)00257-8"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP51287.2024.10647692"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Kurt Hornik Maxwell Stinchcombe and Halbert White. 1989. Multilayer feedforward networks are universal approximators. Neural networks 2 5 359-- 366.","DOI":"10.1016\/0893-6080(89)90020-8"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3688986"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"I Lawrence and Kuei Lin. 1989. A concordance correlation coefficient to evaluate reproducibility. Biometrics 255--268.","DOI":"10.2307\/2532051"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3688988"},{"key":"e_1_3_2_1_13_1","unstructured":"Ziming Liu Yixuan Wang Sachin Vaidya Fabian Ruehle James Halverson Thomas Y Hou and Max Tegmark. 2024. Kan: kolmogorovarnold networks. arXiv preprint arXiv:2404.19756."},{"volume-title":"Joint european conference on machine learning and knowledge discovery in databases","author":"Nezami Omid Mohamad","key":"e_1_3_2_1_14_1","unstructured":"Omid Mohamad Nezami, Mark Dras, Len Hamey, Deborah Richards, Stephen Wan, and C\u00e9cile Paris. 2019. Automatic recognition of student engagement using deep learning and facial expression. In Joint european conference on machine learning and knowledge discovery in databases. Springer, 273--289."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3172944.3172969"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3204493.3204549"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3479219"},{"volume-title":"Proceedings of the 31st ACM International Conference on Multimedia, 9640--9645","author":"Philipp","key":"e_1_3_2_1_18_1","unstructured":"Philipp M\u00fcller et al. 2023. Multimediate'23: engagement estimation and bodily behaviour recognition in social interactions. In Proceedings of the 31st ACM International Conference on Multimedia, 9640--9645."},{"volume-title":"Proceedings of the 32nd ACM International Conference on Multimedia, 11377--11382","author":"Philipp","key":"e_1_3_2_1_19_1","unstructured":"Philipp M\u00fcller et al. 2024. Multimediate'24: multi-domain engagement estimation. In Proceedings of the 32nd ACM International Conference on Multimedia, 11377--11382."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.3389\/fcomp.2023.1062342"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2011.11.028"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-22918-3_5"},{"key":"e_1_3_2_1_24_1","volume-title":"Md Monzurul Islam, Diwas Pandit, and Subasish Das.","author":"Somvanshi Shriyank","year":"2024","unstructured":"Shriyank Somvanshi, Syed Aaqib Javed, Md Monzurul Islam, Diwas Pandit, and Subasish Das. 2024. A survey on kolmogorov-arnold network. ACM Computing Surveys."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3127692"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612857"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the 33rd ACM International Conference on Multimedia (MM '25)","author":"Withanage Daksitha","year":"2025","unstructured":"Daksitha Withanage Don et al. 2025. MultiMediate '25: Cross-cultural Multidomain Engagement Estimation. In Proceedings of the 33rd ACM International Conference on Multimedia (MM '25) (MM '25). Association for Computing Machinery, Dublin, Ireland (Oct. 2025). isbn: 979--8--4007--2035--2\/2025\/10. doi:1 0.1145\/3746027.3762076."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612873"},{"key":"e_1_3_2_1_30_1","volume-title":"Juan Carlos Niebles, and Ehsan Adeli","author":"Yu Heng","year":"2025","unstructured":"Heng Yu, Juze Zhang, Changan Chen, Tiange Xiang, Yusu Fang, Juan Carlos Niebles, and Ehsan Adeli. 2025. Socialgen: modeling multi-human social interaction with language models. arXiv preprint arXiv:2503.22906."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612852"},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, 3187--3195","author":"Yu Jun","year":"2024","unstructured":"Jun Yu, Keda Lu, Ji Zhao, Zhihong Wei, Iek-Heng Chu, and Peng Chang. 2024. Dialogue cross-enhanced central engagement attention model for real-time engagement estimation. In Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, 3187--3195."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3762078","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:36:59Z","timestamp":1765309019000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3762078"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":32,"alternative-id":["10.1145\/3746027.3762078","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3762078","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}