{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/multimae-der-multimodal-masked-autoencoder","title":"MultiMAE-DER: Multimodal Masked Autoencoder for Dynamic Emotion Recognition","arxiv_id":"2404.18327","date":"2024-04-28","proceeding":null,"authors":["Peihao Xiang","Chaohao Lin","Kaida Wu","Ou Bai"],"abstract":"This paper presents a novel approach to processing multimodal data for dynamic emotion recognition, named as the Multimodal Masked Autoencoder for Dynamic Emotion Recognition (MultiMAE-DER). The MultiMAE-DER leverages the closely correlated representation information within spatiotemporal sequences across visual and audio modalities. By utilizing a pre-trained masked autoencoder model, the MultiMAEDER is accomplished through simple, straightforward finetuning. The performance of the MultiMAE-DER is enhanced by optimizing six fusion strategies for multimodal input sequences. These strategies address dynamic feature correlations within cross-domain data across spatial, temporal, and spatiotemporal sequences. In comparison to state-of-the-art multimodal supervised learning models for dynamic emotion recognition, MultiMAE-DER enhances the weighted average recall (WAR) by 4.41% on the RAVDESS dataset and by 2.06% on the CREMAD. Furthermore, when compared with the state-of-the-art model of multimodal self-supervised learning, MultiMAE-DER achieves a 1.86% higher WAR on the IEMOCAP dataset.","url_abs":"https://arxiv.org/abs/2404.18327v2","url_pdf":"https://arxiv.org/pdf/2404.18327v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"multimae-der-multimodal-masked-autoencoder","repo_url":"https://github.com/Peihao-Xiang/MultiMAE-DFER","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"emotion-recognition","task_name":"Emotion Recognition"},{"task_slug":"multimodal-emotion-recognition","task_name":"Multimodal Emotion Recognition"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"video-emotion-recognition","task_name":"Video Emotion Recognition"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"denoising-autoencoder","method_name":"Denoising Autoencoder"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"self-learning","method_name":"Self-Learning"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/emotion-recognition-on-ravdess","task":"Emotion Recognition","dataset":"RAVDESS","model":"MultiMAE-DER","rank_in_archive_order":5,"of":5,"metrics":{"WAR":"83.61%"},"uses_additional_data":false},{"leaderboard":"/sota/multimodal-emotion-recognition-on-iemocap-4","task":"Multimodal Emotion Recognition","dataset":"IEMOCAP-4","model":"MultiMAE-DER","rank_in_archive_order":11,"of":11,"metrics":{"Weighted Recall":"63.73"},"uses_additional_data":false},{"leaderboard":"/sota/video-emotion-recognition-on-crema-d","task":"Video Emotion Recognition","dataset":"CREMA-D","model":"MultiMAE-DER","rank_in_archive_order":4,"of":4,"metrics":{"WAR":"79.36%"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}