{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T08:14:21Z","timestamp":1770279261290,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,29]],"date-time":"2023-10-29T00:00:00Z","timestamp":1698537600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.61831022,No.62276259,No.62201572,No.U21B2010"],"award-info":[{"award-number":["No.61831022,No.62276259,No.62201572,No.U21B2010"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Municipal Science&Technology Commission, Administrative Commission of Zhongguancun Science Park","award":["No.Z211100004821013"],"award-info":[{"award-number":["No.Z211100004821013"]}]},{"name":"CCF-Baidu Open Fund","award":["No.OF2022025"],"award-info":[{"award-number":["No.OF2022025"]}]},{"name":"Open Research Projects of Zhejiang Lab","award":["NO. 2021KH0AB06"],"award-info":[{"award-number":["NO. 2021KH0AB06"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,2]]},"DOI":"10.1145\/3606039.3613108","type":"proceedings-article","created":{"date-parts":[[2023,10,20]],"date-time":"2023-10-20T10:08:16Z","timestamp":1697796496000},"page":"73-80","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Exclusive Modeling for MuSe-Personalisation Challenge"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3485-3869","authenticated-orcid":false,"given":"Haiyang","family":"Sun","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences & Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3978-9373","authenticated-orcid":false,"given":"Zhuofan","family":"Wen","sequence":"additional","affiliation":[{"name":"UCAS & MAIS, CASIA, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1168-2054","authenticated-orcid":false,"given":"Mingyu","family":"Xu","sequence":"additional","affiliation":[{"name":"UCAS & MAIS, CASIA, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9477-0599","authenticated-orcid":false,"given":"Zheng","family":"Lian","sequence":"additional","affiliation":[{"name":"MAIS, CASIA, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7944-3458","authenticated-orcid":false,"given":"Licai","family":"Sun","sequence":"additional","affiliation":[{"name":"UCAS & MAIS, CASIA, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1322-2601","authenticated-orcid":false,"given":"Bin","family":"Liu","sequence":"additional","affiliation":[{"name":"UCAS & MAIS, CASIA, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0477-587X","authenticated-orcid":false,"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2023,10,29]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3610943"},{"key":"e_1_3_2_2_2_1","volume-title":"18th Annual Conference of the International Speech Communication Association","author":"Amiriparian Shahin","year":"2017","unstructured":"Shahin Amiriparian , Maurice Gerczuk , Sandra Ottl , Nicholas Cummins , Michael Freitag , Sergey Pugachevskiy , Alice Baird , and Bj\u00f6 rn W. Schuller . 2017 . Snore Sound Classification Using Image-Based Deep Spectrum Features. In Interspeech 2017 , 18th Annual Conference of the International Speech Communication Association , Stockholm, Sweden, August 20--24 , 2017. 3512--3516. Shahin Amiriparian, Maurice Gerczuk, Sandra Ottl, Nicholas Cummins, Michael Freitag, Sergey Pugachevskiy, Alice Baird, and Bj\u00f6 rn W. Schuller. 2017. Snore Sound Classification Using Image-Based Deep Spectrum Features. In Interspeech 2017, 18th Annual Conference of the International Speech Communication Association, Stockholm, Sweden, August 20--24, 2017. 3512--3516."},{"key":"e_1_3_2_2_3_1","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020","author":"Baevski Alexei","year":"2020","unstructured":"Alexei Baevski , Yuhao Zhou , Abdelrahman Mohamed , and Michael Auli . 2020 . wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations . In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020 , NeurIPS 2020, December 6--12, 2020, virtual. Alexei Baevski, Yuhao Zhou, Abdelrahman Mohamed, and Michael Auli. 2020. wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6--12, 2020, virtual."},{"key":"e_1_3_2_2_4_1","volume-title":"Emerging Properties in Self-Supervised Vision Transformers. In 2021 IEEE\/CVF International Conference on Computer Vision, ICCV 2021","author":"Caron Mathilde","year":"2021","unstructured":"Mathilde Caron , Hugo Touvron , Ishan Misra , Herv\u00e9 J\u00e9 gou, Julien Mairal , Piotr Bojanowski , and Armand Joulin . 2021 . Emerging Properties in Self-Supervised Vision Transformers. In 2021 IEEE\/CVF International Conference on Computer Vision, ICCV 2021 , Montreal, QC, Canada, October 10--17 , 2021. 9630--9640. Mathilde Caron, Hugo Touvron, Ishan Misra, Herv\u00e9 J\u00e9 gou, Julien Mairal, Piotr Bojanowski, and Armand Joulin. 2021. Emerging Properties in Self-Supervised Vision Transformers. In 2021 IEEE\/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, October 10--17, 2021. 9630--9640."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.3390\/asi5040080"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3037496"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"e_1_3_2_2_8_1","volume-title":"Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio.","author":"Cho Kyunghyun","year":"2014","unstructured":"Kyunghyun Cho , Bart van Merrienboer , cC aglar G\u00fc lcc ehre , Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014 . Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014, October 25--29, 2014, Doha, Qatar, A meeting of SIGDAT, a Special Interest Group of the ACL. 1724--1734. Kyunghyun Cho, Bart van Merrienboer, cC aglar G\u00fc lcc ehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014. Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014, October 25--29, 2014, Doha, Qatar, A meeting of SIGDAT, a Special Interest Group of the ACL. 1724--1734."},{"key":"e_1_3_2_2_9_1","volume-title":"MuSe'23: Proceedings of the 4th Multimodal Sentiment Analysis Workshop and Challenge. Association for Computing Machinery. co-located with ACM Multimedia","author":"Christ Lukas","year":"2022","unstructured":"Lukas Christ , Shahin Amiriparian , Alice Baird , Alexander Kathan , Niklas M\u00fcller , Steffen Klug , Chris Gagne , Panagiotis Tzirakis , Lukas Stappen , Eva-Maria Me\u00dfner , Andreas K\u00f6nig , Alan Cowen , Erik Cambria , and Bj\u00f6rn W. Schuller . 2023. The MuSe 2023 Multimodal Sentiment Analysis Challenge: Mimicked Emotions, Cross-Cultural Humour, and Personalisation . In MuSe'23: Proceedings of the 4th Multimodal Sentiment Analysis Workshop and Challenge. Association for Computing Machinery. co-located with ACM Multimedia 2022 , to appear. Lukas Christ, Shahin Amiriparian, Alice Baird, Alexander Kathan, Niklas M\u00fcller, Steffen Klug, Chris Gagne, Panagiotis Tzirakis, Lukas Stappen, Eva-Maria Me\u00dfner, Andreas K\u00f6nig, Alan Cowen, Erik Cambria, and Bj\u00f6rn W. Schuller. 2023. The MuSe 2023 Multimodal Sentiment Analysis Challenge: Mimicked Emotions, Cross-Cultural Humour, and Personalisation. In MuSe'23: Proceedings of the 4th Multimodal Sentiment Analysis Workshop and Challenge. Association for Computing Machinery. co-located with ACM Multimedia 2022, to appear."},{"key":"e_1_3_2_2_10_1","volume-title":"Lukas Stappen, Eva-Maria Me\u00dfner, Andreas K\u00f6 nig, Alan Cowen, Erik Cambria, and Bj\u00f6 rn W. Schuller.","author":"Christ Lukas","year":"2022","unstructured":"Lukas Christ , Shahin Amiriparian , Alice Baird , Panagiotis Tzirakis , Alexander Kathan , Niklas M\u00fc ller , Lukas Stappen, Eva-Maria Me\u00dfner, Andreas K\u00f6 nig, Alan Cowen, Erik Cambria, and Bj\u00f6 rn W. Schuller. 2022 . The MuSe 2022 Multimodal Sentiment Analysis Challenge: Humor, Emotional Reactions, and Stress. In MuSe@MM 2022: Proceedings of the 3rd International on Multimodal Sentiment Analysis Workshop and Challenge, Lisboa, Portugal , 10 October 2022. 5--14. Lukas Christ, Shahin Amiriparian, Alice Baird, Panagiotis Tzirakis, Alexander Kathan, Niklas M\u00fc ller, Lukas Stappen, Eva-Maria Me\u00dfner, Andreas K\u00f6 nig, Alan Cowen, Erik Cambria, and Bj\u00f6 rn W. Schuller. 2022. The MuSe 2022 Multimodal Sentiment Analysis Challenge: Humor, Emotional Reactions, and Stress. In MuSe@MM 2022: Proceedings of the 3rd International on Multimodal Sentiment Analysis Workshop and Challenge, Lisboa, Portugal, 10 October 2022. 5--14."},{"key":"e_1_3_2_2_11_1","volume-title":"21st Annual Conference of the International Speech Communication Association, Virtual Event","author":"Desplanques Brecht","year":"2020","unstructured":"Brecht Desplanques , Jenthe Thienpondt , and Kris Demuynck . 2020 . ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification. In Interspeech 2020 , 21st Annual Conference of the International Speech Communication Association, Virtual Event , Shanghai, China, 25- -29 October 2020. 3830--3834. Brecht Desplanques, Jenthe Thienpondt, and Kris Demuynck. 2020. ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification. In Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25--29 October 2020. 3830--3834."},{"key":"e_1_3_2_2_12_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin , Ming-Wei Chang , Kenton Lee , and Kristina Toutanova . 2019 . BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding . In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019 , Minneapolis, MN, USA, June 2--7 , 2019, Volume 1 (Long and Short Papers). 4171--4186. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2--7, 2019, Volume 1 (Long and Short Papers). 4171--4186."},{"key":"e_1_3_2_2_13_1","volume-title":"Facial action coding system. Environmental Psychology & Nonverbal Behavior","author":"Ekman Paul","year":"1978","unstructured":"Paul Ekman and Wallace V Friesen . 1978. Facial action coding system. Environmental Psychology & Nonverbal Behavior ( 1978 ). Paul Ekman and Wallace V Friesen. 1978. Facial action coding system. Environmental Psychology & Nonverbal Behavior (1978)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"e_1_3_2_2_16_1","volume-title":"Lisboa","author":"He Yu","year":"2022","unstructured":"Yu He , Licai Sun , Zheng Lian , Bin Liu , Jianhua Tao , Meng Wang , and Yuan Cheng . 2022 . Multimodal Temporal Attention in Sentiment Analysis. In MuSe@MM 2022: Proceedings of the 3rd International on Multimodal Sentiment Analysis Workshop and Challenge , Lisboa , Portugal , 10 October 2022. 61--66. Yu He, Licai Sun, Zheng Lian, Bin Liu, Jianhua Tao, Meng Wang, and Yuan Cheng. 2022. Multimodal Temporal Attention in Sentiment Analysis. In MuSe@MM 2022: Proceedings of the 3rd International on Multimodal Sentiment Analysis Workshop and Challenge, Lisboa, Portugal, 10 October 2022. 61--66."},{"key":"e_1_3_2_2_17_1","volume-title":"Densely Connected Convolutional Networks. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017","author":"Huang Gao","year":"2017","unstructured":"Gao Huang , Zhuang Liu , Laurens van der Maaten, and Kilian Q. Weinberger. 2017 . Densely Connected Convolutional Networks. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 , Honolulu, HI, USA, July 21--26 , 2017 . 2261--2269. Gao Huang, Zhuang Liu, Laurens van der Maaten, and Kilian Q. Weinberger. 2017. Densely Connected Convolutional Networks. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, July 21--26, 2017. 2261--2269."},{"key":"e_1_3_2_2_18_1","volume-title":"Multimodal Transformer Fusion for Continuous Emotion Recognition. In 2020 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2020","author":"Huang Jian","year":"2020","unstructured":"Jian Huang , Jianhua Tao , Bin Liu , Zheng Lian , and Mingyue Niu . 2020 . Multimodal Transformer Fusion for Continuous Emotion Recognition. In 2020 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2020 , Barcelona, Spain, May 4--8 , 2020. 3507--3511. Jian Huang, Jianhua Tao, Bin Liu, Zheng Lian, and Mingyue Niu. 2020. Multimodal Transformer Fusion for Continuous Emotion Recognition. In 2020 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2020, Barcelona, Spain, May 4--8, 2020. 3507--3511."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1159\/000119004"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-019-1176-9"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00623"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2736999"},{"key":"e_1_3_2_2_24_1","volume-title":"Hung Pham, Christopher Sch\u00f6lzel, and SH Annabel Chen.","author":"Makowski Dominique","year":"2021","unstructured":"Dominique Makowski , Tam Pham , Zen J Lau , Jan C Brammer , Francc ois Lespinasse , Hung Pham, Christopher Sch\u00f6lzel, and SH Annabel Chen. 2021 . NeuroKit2: A Python toolbox for neurophysiological signal processing. Behavior research methods (2021), 1--8. Dominique Makowski, Tam Pham, Zen J Lau, Jan C Brammer, Francc ois Lespinasse, Hung Pham, Christopher Sch\u00f6lzel, and SH Annabel Chen. 2021. NeuroKit2: A Python toolbox for neurophysiological signal processing. Behavior research methods (2021), 1--8."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_3_2_2_26_1","volume-title":"The INTERSPEECH 2010 paralinguistic challenge. In INTERSPEECH 2010, 11th Annual Conference of the International Speech Communication Association","author":"Schuller Bj\u00f6","year":"2010","unstructured":"Bj\u00f6 rn W. Schuller , Stefan Steidl , Anton Batliner , Felix Burkhardt , Laurence Devillers , Christian A. M\u00fc ller, and Shrikanth S. Narayanan . 2010 . The INTERSPEECH 2010 paralinguistic challenge. In INTERSPEECH 2010, 11th Annual Conference of the International Speech Communication Association , Makuhari, Chiba, Japan, September 26--30 , 2010 . 2794--2797. Bj\u00f6 rn W. Schuller, Stefan Steidl, Anton Batliner, Felix Burkhardt, Laurence Devillers, Christian A. M\u00fc ller, and Shrikanth S. Narayanan. 2010. The INTERSPEECH 2010 paralinguistic challenge. In INTERSPEECH 2010, 11th Annual Conference of the International Speech Communication Association, Makuhari, Chiba, Japan, September 26--30, 2010. 2794--2797."},{"key":"e_1_3_2_2_27_1","volume-title":"Lightface: A hybrid deep face recognition framework. In 2020 innovations in intelligent systems and applications conference (ASYU)","author":"Serengil Sefik Ilkin","year":"2020","unstructured":"Sefik Ilkin Serengil and Alper Ozpinar . 2020 . Lightface: A hybrid deep face recognition framework. In 2020 innovations in intelligent systems and applications conference (ASYU) . IEEE , 1--5. Sefik Ilkin Serengil and Alper Ozpinar. 2020. Lightface: A hybrid deep face recognition framework. In 2020 innovations in intelligent systems and applications conference (ASYU). IEEE, 1--5."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3475957.3484450"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3423327.3423672"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3475957.3484456"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-019-1175-x"},{"key":"e_1_3_2_2_32_1","volume-title":"Lisboa","author":"Vaiani Lorenzo","year":"2022","unstructured":"Lorenzo Vaiani , Moreno La Quatra , Luca Cagliero , and Paolo Garza . 2022 . ViPER: Video-based Perceiver for Emotion Recognition. In MuSe@MM 2022: Proceedings of the 3rd International on Multimodal Sentiment Analysis Workshop and Challenge , Lisboa , Portugal , 10 October 2022. 67--73. Lorenzo Vaiani, Moreno La Quatra, Luca Cagliero, and Paolo Garza. 2022. ViPER: Video-based Perceiver for Emotion Recognition. In MuSe@MM 2022: Proceedings of the 3rd International on Multimodal Sentiment Analysis Workshop and Challenge, Lisboa, Portugal, 10 October 2022. 67--73."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 4th on Multimodal Sentiment Analysis Challenge and Workshop: Mimicked Emotions, Humour and Personalisation"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3606039.3613108","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3606039.3613108","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:36:20Z","timestamp":1750178180000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3606039.3613108"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,29]]},"references-count":33,"alternative-id":["10.1145\/3606039.3613108","10.1145\/3606039"],"URL":"https:\/\/doi.org\/10.1145\/3606039.3613108","relation":{},"subject":[],"published":{"date-parts":[[2023,10,29]]},"assertion":[{"value":"2023-10-29","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}