Nothing Special   »   [go: up one dir, main page]

skip to main content
10.1145/3689062.3689082acmconferencesArticle/Chapter ViewAbstractPublication PagesmmConference Proceedingsconference-collections
research-article
Open access

Feature-wise Optimization and Performance-weighted Multimodal Fusion for Social Perception Recognition

Published: 28 October 2024 Publication History

Abstract

Automatic social perception recognition is a new task to mimic the measurement of human traits, which was previously done by humans via questionnaires. We evaluated unimodal and multimodal systems to predict agentive and communal traits from the LMU-ELP dataset. We optimized variants of recurrent neural networks from each feature from audio and video data and then fused them to predict the traits. Results on the development set show a consistent trend that multimodal fusion outperforms unimodal systems. The performance-weighted fusion also consistently outperforms mean and maximum fusions. We found two important factors that influence the performance of performance-weighted fusion. These factors are normalization and the number of models.

References

[1]
Andrea E. Abele and Bogdan Wojciszke. 2014. Communal and agentic content in social cognition: A dual perspective model 1 ed.). Vol. 50. Elsevier Inc. 195--255 pages. https://doi.org/10.1016/B978-0--12--800284--1.00004--7
[2]
Takuya Akiba, Shotaro Sano, Toshihiko Yanase, Takeru Ohta, and Masanori Koyama. 2019. Optuna: A Next-generation Hyperparameter Optimization Framework. Proc. ACM SIGKDD Int. Conf. Knowl. Discov. Data Min. (2019), 2623--2631. https://doi.org/10.1145/3292500.3330701 arxiv: 1907.10902
[3]
Shahin Amiriparian, Lukas Christ, Alexander Kathan, Maurice Gerczuk, Niklas Muller, Steffen Klug, Lukas Stappen, Andreas Konig, Erik Cambria, Bj$backslash$"orn Schuller, and Simone Eulitz. 2014. The MuSe 2024 Multimodal Sentiment Analysis Challenge: Social Perception and Humor Recognition. In MM 2024 - Proc. 2024 ACM Multimed. Conf.
[4]
Shahin Amiriparian, Maurice Gerczuk, Sandra Ottl, Nicholas Cummins, Michael Freitag, Sergey Pugachevskiy, Alice Baird, and Björn Schuller. 2017. Snore Sound Classification Using Image-Based Deep Spectrum Features. In Interspeech 2017. ISCA, ISCA, 3512--3516. https://doi.org/10.21437/Interspeech.2017--434
[5]
Shahin Amiriparian, Artem Sokolov, Ilhan Aslan, Lukas Christ, Maurice Gerczuk, Tobias Hübner, Dmitry Lamanov, Manuel Milling, Sandra Ottl, Ilya Poduremennykh, Evgeniy Shuranov, and Björn W. Schuller. 2021. On the Impact of Word Error Rate on Acoustic-Linguistic Speech Emotion Recognition: An Update for the Deep Learning Era. (2021), 2--6. arxiv: 2104.10121 http://arxiv.org/abs/2104.10121
[6]
B. T. Atmaja and M. Akagi. 2021. Evaluation of error- And correlation-based loss functions for multitask learning dimensional speech emotion recognition. J. Phys. Conf. Ser., Vol. 1896, 1 (2021), 012004. https://doi.org/10.1088/1742--6596/1896/1/012004 arxiv: 2003.10724
[7]
Bagus Tris Atmaja and Akira Sasou. 2023. Ensembling Multilingual Pre-Trained Models for Predicting Multi-Label Regression Emotion Share from Speech. In 2023 Asia Pacific Signal Inf. Process. Assoc. Annu. Summit Conf. (APSIPA ASC). IEEE, 1026--1029. https://doi.org/10.1109/APSIPAASC58517.2023.10317109
[8]
Bagus Tris Atmaja and Akira Sasou. 2023. Evaluating Variants of wav2vec 2.0 on Affective Vocal Burst Tasks. In ICASSP 2023 - 2023 IEEE Int. Conf. Acoust. Speech Signal Process. IEEE, 1--5. https://doi.org/10.1109/icassp49357.2023.10096552
[9]
Aayushi Chaudhari, Chintan Bhatt, Achyut Krishna, and Pier Luigi Mazzeo. 2022. ViTFER: Facial Emotion Recognition with Vision Transformers. Appl. Syst. Innov. 2022, Vol. 5, 4 (2022). https://doi.org/10.3390/asi5040080
[10]
Robyn Dunlop and Caren Brenda Scheepers. 2023. The influence of female agentic and communal leadership on work engagement: vigour, dedication and absorption. Manag. Res. Rev., Vol. 46, 3 (feb 2023), 437--466. https://doi.org/10.1108/MRR-11--2021-0796
[11]
Florian Eyben, Klaus R. Scherer, Bjorn W. Schuller, Johan Sundberg, Elisabeth Andre, Carlos Busso, Laurence Y. Devillers, Julien Epps, Petri Laukka, Shrikanth S. Narayanan, and Khiet P. Truong. 2016. The Geneva Minimalistic Acoustic Parameter Set (GeMAPS) for Voice Research and Affective Computing. IEEE Trans. Affect. Comput., Vol. 7, 2 (apr 2016), 190--202. https://doi.org/10.1109/TAFFC.2015.2457417
[12]
Florian Eyben, Felix Weninger, Martin Wollmer, Björn Bjorn Schuller, Martin Wöllmer, and Björn Bjorn Schuller. 2015. OpenSMILE - The Munich versatile and fast open-source audio feature extractor. Number December. 1--65 pages. https://doi.org/10.1145/1873951.1874246
[13]
Laura Froehlich, Maria I. T. Olsson, Angela R. Dorrough, and Sarah E. Martiny. 2020. Gender at Work Across Nations: Men and Women Working in Male?Dominated and Female-Dominated Occupations are Differentially Associated with Agency and Communion. J. Soc. Issues, Vol. 76, 3 (sep 2020), 484--511. https://doi.org/10.1111/josi.12390
[14]
Ammarah Hashmi, Sahibzada Adil Shahzad, Wasim Ahmad, Chia Wen Lin, Yu Tsao, and Hsin-min Wang. 2022. Multimodal Forgery Detection Using Ensemble Learning. 1521--1529.
[15]
Reza Lotfian and Carlos Busso. 2019. Building Naturalistic Emotionally Balanced Speech Corpus by Retrieving Emotional Speech from Existing Podcast Recordings. IEEE Trans. Affect. Comput., Vol. 10, 4 (2019), 471--483. https://doi.org/10.1109/TAFFC.2017.2736999
[16]
Emad A. Mohammed, Mohammad Keyhani, Amir Sanati-Nezhad, S. Hossein Hejazi, and Behrouz H. Far. 2021. An ensemble learning approach to digital corona virus preliminary screening from cough sounds. Sci. Rep., Vol. 11, 1 (2021), 1--11. https://doi.org/10.1038/s41598-021--95042--2
[17]
Radu Tudor Ionescu. 2021. Self-paced ensemble learning for speech and audio classification. Proc. Annu. Conf. Int. Speech Commun. Assoc. INTERSPEECH, Vol. 2 (2021), 1276--1280. https://doi.org/10.21437/Interspeech.2021--155 arxiv: 2103.11988
[18]
Florian Schroff, Dmitry Kalenichenko, and James Philbin. 2015. FaceNet: A unified embedding for face recognition and clustering. Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., Vol. 07--12-June (2015), 815--823. https://doi.org/10.1109/CVPR.2015.7298682 arxiv: 1503.03832
[19]
Ruoqi Shen, Liyao Gao, and Yi-An Ma. 2022. On Optimal Early Stopping: Over-informative versus Under-informative Parametrization. (feb 2022), 1--30. arxiv: 2202.09885 http://arxiv.org/abs/2202.09885
[20]
Paul D. Trapnell and Delroy L. Paulhus. 2012. Agentic and communal values: Their scope and measurement. J. Pers. Assess., Vol. 94, 1 (2012), 39--52. https://doi.org/10.1080/00223891.2011.627968
[21]
Andrea C. Vial and Jaime L. Napier. 2018. Unnecessary Frills: Communality as a Nice (But Expendable) Trait in Leaders. Front. Psychol., Vol. 9 (oct 2018). https://doi.org/10.3389/fpsyg.2018.01866
[22]
Athena Vongalis-Macrow. 2016. It's About the Leadership: The Importance of Women Leaders Doing Leadership for Women. NASPA J. About Women High. Educ., Vol. 9, 1 (jan 2016), 90--103. https://doi.org/10.1080/19407882.2015.1114953
[23]
Johannes Wagner, Andreas Triantafyllopoulos, Hagen Wierstorf, Maximilian Schmitt, Felix Burkhardt, Florian Eyben, and Björn W. Schuller. 2023. Dawn of the Transformer Era in Speech Emotion Recognition: Closing the Valence Gap. IEEE Trans. Pattern Anal. Mach. Intell., Vol. 45, 9 (sep 2023), 10745--10759. https://doi.org/10.1109/TPAMI.2023.3263585
[24]
Bogdan Wojciszke and Olga Bialobrzeska. 2014. Agency versus Communion as Predictors of Self-esteem: Searching for the Role of Culture and Self-construal. Polish Psychol. Bull., Vol. 45, 4 (dec 2014), 469--479. https://doi.org/10.2478/ppb-2014-0057

Cited By

View all
  • (2024)MuSe '24: The 5th Multimodal Sentiment Analysis Challenge and Workshop: Social Perception & HumorProceedings of the 5th on Multimodal Sentiment Analysis Challenge and Workshop: Social Perception and Humor10.1145/3689062.3695939(10-11)Online publication date: 28-Oct-2024

Index Terms

  1. Feature-wise Optimization and Performance-weighted Multimodal Fusion for Social Perception Recognition

      Recommendations

      Comments

      Please enable JavaScript to view thecomments powered by Disqus.

      Information & Contributors

      Information

      Published In

      cover image ACM Conferences
      MuSe'24: Proceedings of the 5th on Multimodal Sentiment Analysis Challenge and Workshop: Social Perception and Humor
      October 2024
      76 pages
      ISBN:9798400711992
      DOI:10.1145/3689062
      This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike International 4.0 License.

      Sponsors

      Publisher

      Association for Computing Machinery

      New York, NY, United States

      Publication History

      Published: 28 October 2024

      Check for updates

      Author Tags

      1. multimodal fusion
      2. parameter optimization
      3. sentiment analysis
      4. social perception

      Qualifiers

      • Research-article

      Funding Sources

      Conference

      MM '24
      Sponsor:
      MM '24: The 32nd ACM International Conference on Multimedia
      October 28 - November 1, 2024
      Melbourne VIC, Australia

      Acceptance Rates

      Overall Acceptance Rate 14 of 17 submissions, 82%

      Contributors

      Other Metrics

      Bibliometrics & Citations

      Bibliometrics

      Article Metrics

      • Downloads (Last 12 months)30
      • Downloads (Last 6 weeks)30
      Reflects downloads up to 29 Nov 2024

      Other Metrics

      Citations

      Cited By

      View all
      • (2024)MuSe '24: The 5th Multimodal Sentiment Analysis Challenge and Workshop: Social Perception & HumorProceedings of the 5th on Multimodal Sentiment Analysis Challenge and Workshop: Social Perception and Humor10.1145/3689062.3695939(10-11)Online publication date: 28-Oct-2024

      View Options

      View options

      PDF

      View or Download as a PDF file.

      PDF

      eReader

      View online with eReader.

      eReader

      Login options

      Media

      Figures

      Other

      Tables

      Share

      Share

      Share this Publication link

      Share on social media