{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T18:13:20Z","timestamp":1776104000593,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,9]],"date-time":"2023-10-09T00:00:00Z","timestamp":1696809600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"PERSYVAL Labex","award":["ANR-11-LABX-0025"],"award-info":[{"award-number":["ANR-11-LABX-0025"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,9]]},"DOI":"10.1145\/3577190.3616546","type":"proceedings-article","created":{"date-parts":[[2023,10,7]],"date-time":"2023-10-07T22:30:48Z","timestamp":1696717848000},"page":"750-754","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Multimodal Group Emotion Recognition In-the-wild Using Privacy-Compliant Features"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-0634-0318","authenticated-orcid":false,"given":"Anderson","family":"Augusma","sequence":"first","affiliation":[{"name":"Univ. Grenoble Alpes, CNRS, Grenoble INP, LIG Grenoble, France, France and Univ. Grenoble Alpes, CNRS, Grenoble INP, LJK Grenoble, France, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8825-0973","authenticated-orcid":false,"given":"Dominique","family":"Vaufreydaz","sequence":"additional","affiliation":[{"name":"Univ. Grenoble Alpes, CNRS, Grenoble INP, LIG Grenoble, France, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2732-8359","authenticated-orcid":false,"given":"Fr\u00e9d\u00e9rique","family":"Letu\u00e9","sequence":"additional","affiliation":[{"name":"Univ. Grenoble Alpes, CNRS, Grenoble INP, LJK Grenoble, France, France"}]}],"member":"320","published-online":{"date-parts":[[2023,10,9]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Social Networks and Texts: 10th International Conference, AIST 2021","author":"Belova S","year":"2022","unstructured":"Natalya\u00a0 S Belova . 2022 . Group-Level Affect Recognition in Video Using Deviation of Frame Features. In Analysis of Images , Social Networks and Texts: 10th International Conference, AIST 2021 , Tbilisi, Georgia, December 16\u201318 , 2021, Revised Selected Papers, Vol.\u00a013217. Springer Nature, 199. Natalya\u00a0S Belova. 2022. Group-Level Affect Recognition in Video Using Deviation of Frame Features. In Analysis of Images, Social Networks and Texts: 10th International Conference, AIST 2021, Tbilisi, Georgia, December 16\u201318, 2021, Revised Selected Papers, Vol.\u00a013217. Springer Nature, 199."},{"key":"e_1_3_2_1_2_1","volume-title":"ACM ICMI","author":"Dhall Abhinav","year":"2023","unstructured":"Abhinav Dhall , Monisha Singh , Roland Goecke , Tom Gedeon , Donghuo Zeng , Yanan Wang , and Kazushi Ikeda . 2023 . EmotiW 2023: Emotion Recognition in the Wild Challenge . ACM ICMI 2023. Abhinav Dhall, Monisha Singh, Roland Goecke, Tom Gedeon, Donghuo Zeng, Yanan Wang, and Kazushi Ikeda. 2023. EmotiW 2023: Emotion Recognition in the Wild Challenge. ACM ICMI 2023."},{"key":"e_1_3_2_1_3_1","volume-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. (10","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy , Lucas Beyer , Alexander Kolesnikov , Dirk Weissenborn , Xiaohua Zhai , Thomas Unterthiner , Mostafa Dehghani , Matthias Minderer , Georg Heigold , Sylvain Gelly , Jakob Uszkoreit , and Neil Houlsby . 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. (10 2020 ). http:\/\/arxiv.org\/abs\/2010.11929 Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. (10 2020). http:\/\/arxiv.org\/abs\/2010.11929"},{"key":"e_1_3_2_1_4_1","volume-title":"Counting Out Time: Class Agnostic Video Repetition Counting in the Wild. (6","author":"Dwibedi Debidatta","year":"2020","unstructured":"Debidatta Dwibedi , Yusuf Aytar , Jonathan Tompson , Pierre Sermanet , and Andrew Zisserman . 2020. Counting Out Time: Class Agnostic Video Repetition Counting in the Wild. (6 2020 ). http:\/\/arxiv.org\/abs\/2006.15418 Debidatta Dwibedi, Yusuf Aytar, Jonathan Tompson, Pierre Sermanet, and Andrew Zisserman. 2020. Counting Out Time: Class Agnostic Video Repetition Counting in the Wild. (6 2020). http:\/\/arxiv.org\/abs\/2006.15418"},{"key":"e_1_3_2_1_5_1","volume-title":"FACES-a database of facial expressions in young, middle-aged, and older women and men: Development and validation. Behavior Research Methods 42 (2","author":"Ebner C.","year":"2010","unstructured":"Natalie\u00a0 C. Ebner , Michaela Riediger , and Ulman Lindenberger . 2010. FACES-a database of facial expressions in young, middle-aged, and older women and men: Development and validation. Behavior Research Methods 42 (2 2010 ), 351\u2013362. Issue 1. https:\/\/doi.org\/10.3758\/BRM.42.1.351 10.3758\/BRM.42.1.351 Natalie\u00a0C. Ebner, Michaela Riediger, and Ulman Lindenberger. 2010. FACES-a database of facial expressions in young, middle-aged, and older women and men: Development and validation. Behavior Research Methods 42 (2 2010), 351\u2013362. Issue 1. https:\/\/doi.org\/10.3758\/BRM.42.1.351"},{"key":"e_1_3_2_1_6_1","volume-title":"Multimodal End-to-End Group Emotion Recognition using Cross-Modal Attention. CoRR abs\/2111.05890","author":"Evtodienko Lev","year":"2021","unstructured":"Lev Evtodienko . 2021. Multimodal End-to-End Group Emotion Recognition using Cross-Modal Attention. CoRR abs\/2111.05890 ( 2021 ). arXiv:2111.05890https:\/\/arxiv.org\/abs\/2111.05890 Lev Evtodienko. 2021. Multimodal End-to-End Group Emotion Recognition using Cross-Modal Attention. CoRR abs\/2111.05890 (2021). arXiv:2111.05890https:\/\/arxiv.org\/abs\/2111.05890"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Xin Guo Luisa\u00a0F Polan\u00eda Charles Boncelet and Kenneth\u00a0E Barner. 2020. Graph Neural Networks for Image Understanding Based on Multiple Cues: Group Emotion Recognition and Event Recognition as Use Cases. https:\/\/github.com\/gxstudy\/Graph-Neural-Networks-for-  Xin Guo Luisa\u00a0F Polan\u00eda Charles Boncelet and Kenneth\u00a0E Barner. 2020. Graph Neural Networks for Image Understanding Based on Multiple Cues: Group Emotion Recognition and Event Recognition as Use Cases. https:\/\/github.com\/gxstudy\/Graph-Neural-Networks-for-","DOI":"10.1109\/WACV45572.2020.9093547"},{"key":"e_1_3_2_1_9_1","volume-title":"Scenes, Skeletons and Visual Attentions.","author":"Guo Xin","year":"2018","unstructured":"Xin Guo , Bin Zhu , Luisa\u00a0 F Polan\u00eda , Charles Boncelet , and Kenneth\u00a0 E Barner . 2018. Group-Level Emotion Recognition using Hybrid Deep Models based on Faces , Scenes, Skeletons and Visual Attentions. ( 2018 ). https:\/\/doi.org\/10.1145\/3242969 10.1145\/3242969 Xin Guo, Bin Zhu, Luisa\u00a0F Polan\u00eda, Charles Boncelet, and Kenneth\u00a0E Barner. 2018. Group-Level Emotion Recognition using Hybrid Deep Models based on Faces, Scenes, Skeletons and Visual Attentions. (2018). https:\/\/doi.org\/10.1145\/3242969"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3242969.3264985"},{"key":"e_1_3_2_1_11_1","volume-title":"Emotion recognition using deep learning approach from audio\u2013visual emotional big data. Information Fusion 49 (9","author":"Hossain Shamim","year":"2019","unstructured":"M.\u00a0 Shamim Hossain and Ghulam Muhammad . 2019. Emotion recognition using deep learning approach from audio\u2013visual emotional big data. Information Fusion 49 (9 2019 ), 69\u201378. https:\/\/doi.org\/10.1016\/j.inffus.2018.09.008 10.1016\/j.inffus.2018.09.008 M.\u00a0Shamim Hossain and Ghulam Muhammad. 2019. Emotion recognition using deep learning approach from audio\u2013visual emotional big data. Information Fusion 49 (9 2019), 69\u201378. https:\/\/doi.org\/10.1016\/j.inffus.2018.09.008"},{"key":"e_1_3_2_1_12_1","volume-title":"Group Level Audio-Video Emotion Recognition Using Hybrid Networks. ICMI 2020 - Proceedings of the 2020 International Conference on Multimodal Interaction, 807\u2013812","author":"Liu Chuanhe","year":"2020","unstructured":"Chuanhe Liu , Wenqiang Jiang , Minghao Wang , and Tianhao Tang . 2020 . Group Level Audio-Video Emotion Recognition Using Hybrid Networks. ICMI 2020 - Proceedings of the 2020 International Conference on Multimodal Interaction, 807\u2013812 . https:\/\/doi.org\/10.1145\/3382507.3417968 10.1145\/3382507.3417968 Chuanhe Liu, Wenqiang Jiang, Minghao Wang, and Tianhao Tang. 2020. Group Level Audio-Video Emotion Recognition Using Hybrid Networks. ICMI 2020 - Proceedings of the 2020 International Conference on Multimodal Interaction, 807\u2013812. https:\/\/doi.org\/10.1145\/3382507.3417968"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Manuel\u00a0J. Marin-Jimenez Vicky Kalogeiton Pablo Medina-Suarez and Andrew Zisserman. 2019. LAEO-Net: revisiting people Looking At Each Other in videos. arxiv:1906.05261\u00a0[cs.CV]  Manuel\u00a0J. Marin-Jimenez Vicky Kalogeiton Pablo Medina-Suarez and Andrew Zisserman. 2019. LAEO-Net: revisiting people Looking At Each Other in videos. arxiv:1906.05261\u00a0[cs.CV]","DOI":"10.1109\/CVPR.2019.00359"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3382507.3417964"},{"key":"e_1_3_2_1_15_1","volume-title":"Group-Level Emotion Recognition Using a Unimodal Privacy-Safe Non-Individual Approach. CoRR abs\/2009.07013","author":"Petrova Anastasia","year":"2020","unstructured":"Anastasia Petrova , Dominique Vaufreydaz , and Philippe Dessus . 2020. Group-Level Emotion Recognition Using a Unimodal Privacy-Safe Non-Individual Approach. CoRR abs\/2009.07013 ( 2020 ). arXiv:2009.07013https:\/\/arxiv.org\/abs\/2009.07013 Anastasia Petrova, Dominique Vaufreydaz, and Philippe Dessus. 2020. Group-Level Emotion Recognition Using a Unimodal Privacy-Safe Non-Individual Approach. CoRR abs\/2009.07013 (2020). arXiv:2009.07013https:\/\/arxiv.org\/abs\/2009.07013"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPAS50080.2020.9334943"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.3103\/S1060992X22030055"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3104170"},{"key":"e_1_3_2_1_19_1","volume-title":"Automatic Group Level Affect and Cohesion Prediction in Videos. 2019 8th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos, ACIIW 2019 (9 2019","author":"Sharma Garima","year":"2019","unstructured":"Garima Sharma , Shreya Ghosh , and Abhinav Dhall . 2019 . Automatic Group Level Affect and Cohesion Prediction in Videos. 2019 8th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos, ACIIW 2019 (9 2019 ), 161\u2013167. https:\/\/doi.org\/10.1109\/ACIIW.2019.8925231 10.1109\/ACIIW.2019.8925231 Garima Sharma, Shreya Ghosh, and Abhinav Dhall. 2019. Automatic Group Level Affect and Cohesion Prediction in Videos. 2019 8th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos, ACIIW 2019 (9 2019), 161\u2013167. https:\/\/doi.org\/10.1109\/ACIIW.2019.8925231"},{"key":"e_1_3_2_1_20_1","volume-title":"Multi-modal Fusion Using Spatio-temporal and Static Features for Group Emotion Recognition. ICMI 2020 - Proceedings of the 2020 International Conference on Multimodal Interaction (10","author":"Sun Mo","year":"2020","unstructured":"Mo Sun , Jian Li , Hui Feng , Wei Gou , Haifeng Shen , Jian Tang , Yi Yang , and Jieping Ye . 2020 . Multi-modal Fusion Using Spatio-temporal and Static Features for Group Emotion Recognition. ICMI 2020 - Proceedings of the 2020 International Conference on Multimodal Interaction (10 2020), 835\u2013840. https:\/\/doi.org\/10.1145\/3382507.3417971 10.1145\/3382507.3417971 Mo Sun, Jian Li, Hui Feng, Wei Gou, Haifeng Shen, Jian Tang, Yi Yang, and Jieping Ye. 2020. Multi-modal Fusion Using Spatio-temporal and Static Features for Group Emotion Recognition. ICMI 2020 - Proceedings of the 2020 International Conference on Multimodal Interaction (10 2020), 835\u2013840. https:\/\/doi.org\/10.1145\/3382507.3417971"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3143015"},{"key":"e_1_3_2_1_22_1","volume-title":"(6","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani , Noam Shazeer , Niki Parmar , Jakob Uszkoreit , Llion Jones , Aidan\u00a0 N. Gomez , Lukasz Kaiser , and Illia Polosukhin . 2017. Attention Is All You Need. (6 2017 ). http:\/\/arxiv.org\/abs\/1706.03762 Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention Is All You Need. (6 2017). http:\/\/arxiv.org\/abs\/1706.03762"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3242969.3264991"},{"key":"e_1_3_2_1_24_1","volume-title":"Implicit Knowledge Injectable Cross Attention Audiovisual Model for Group Emotion Recognition. ICMI 2020 - Proceedings of the 2020 International Conference on Multimodal Interaction, 827\u2013834","author":"Wang Yanan","year":"2020","unstructured":"Yanan Wang , Jianming Wu , Panikos Heracleous , Shinya Wada , Rui Kimura , and Satoshi Kurihara . 2020 . Implicit Knowledge Injectable Cross Attention Audiovisual Model for Group Emotion Recognition. ICMI 2020 - Proceedings of the 2020 International Conference on Multimodal Interaction, 827\u2013834 . https:\/\/doi.org\/10.1145\/3382507.3417960 10.1145\/3382507.3417960 Yanan Wang, Jianming Wu, Panikos Heracleous, Shinya Wada, Rui Kimura, and Satoshi Kurihara. 2020. Implicit Knowledge Injectable Cross Attention Audiovisual Model for Group Emotion Recognition. ICMI 2020 - Proceedings of the 2020 International Conference on Multimodal Interaction, 827\u2013834. https:\/\/doi.org\/10.1145\/3382507.3417960"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2932797"},{"key":"e_1_3_2_1_26_1","volume-title":"LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop. (6","author":"Yu Fisher","year":"2015","unstructured":"Fisher Yu , Ari Seff , Yinda Zhang , Shuran Song , Thomas Funkhouser , and Jianxiong Xiao . 2015 . LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop. (6 2015). http:\/\/arxiv.org\/abs\/1506.03365 Fisher Yu, Ari Seff, Yinda Zhang, Shuran Song, Thomas Funkhouser, and Jianxiong Xiao. 2015. LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop. (6 2015). http:\/\/arxiv.org\/abs\/1506.03365"}],"event":{"name":"ICMI '23: INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","location":"Paris France","acronym":"ICMI '23","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3577190.3616546","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3577190.3616546","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:02Z","timestamp":1750178222000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3577190.3616546"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,9]]},"references-count":26,"alternative-id":["10.1145\/3577190.3616546","10.1145\/3577190"],"URL":"https:\/\/doi.org\/10.1145\/3577190.3616546","relation":{},"subject":[],"published":{"date-parts":[[2023,10,9]]},"assertion":[{"value":"2023-10-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}