{"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/multi-task-multi-modal-self-supervised","title":"Multi-Task Multi-Modal Self-Supervised Learning for Facial Expression Recognition","arxiv_id":"2404.10904","date":"2024-04-16","proceeding":null,"authors":["Marah Halawa","Florian Blume","Pia Bideau","Martin Maier","Rasha Abdel Rahman","Olaf Hellwich"],"abstract":"Human communication is multi-modal; e.g., face-to-face interaction involves auditory signals (speech) and visual signals (face movements and hand gestures). Hence, it is essential to exploit multiple modalities when designing machine learning-based facial expression recognition systems. In addition, given the ever-growing quantities of video data that capture human facial expressions, such systems should utilize raw unlabeled videos without requiring expensive annotations. Therefore, in this work, we employ a multitask multi-modal self-supervised learning method for facial expression recognition from in-the-wild video data. Our model combines three self-supervised objective functions: First, a multi-modal contrastive loss, that pulls diverse data modalities of the same video together in the representation space. Second, a multi-modal clustering loss that preserves the semantic structure of input data in the representation space. Finally, a multi-modal data reconstruction loss. We conduct a comprehensive study on this multimodal multi-task self-supervised learning method on three facial expression recognition benchmarks. To that end, we examine the performance of learning through different combinations of self-supervised tasks on the facial expression recognition downstream task. Our model ConCluGen outperforms several multi-modal self-supervised and fully supervised baselines on the CMU-MOSEI dataset. Our results generally show that multi-modal self-supervision tasks offer large performance gains for challenging tasks such as facial expression recognition, while also reducing the amount of manual annotations required. We release our pre-trained models as well as source code publicly","url_abs":"https://arxiv.org/abs/2404.10904v2","url_pdf":"https://arxiv.org/pdf/2404.10904v2.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":"multi-task-multi-modal-self-supervised","repo_url":"https://github.com/tub-cv-group/conclugen","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"emotion-classification","task_name":"Emotion Classification"},{"task_slug":"emotion-recognition-in-conversation","task_name":"Emotion Recognition in Conversation"},{"task_slug":"facial-expression-recognition-1","task_name":"Facial Expression Recognition"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"k-means-clustering","method_name":"k-Means Clustering"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/emotion-classification-on-cmu-mosei","task":"Emotion Classification","dataset":"CMU-MOSEI","model":"ConCluGen","rank_in_archive_order":4,"of":4,"metrics":{"Accuracy":"66.48","Weighted Accuracy":"66.48"},"uses_additional_data":false},{"leaderboard":"/sota/emotion-recognition-in-conversation-on-meld","task":"Emotion Recognition in Conversation","dataset":"MELD","model":"ConCluGen","rank_in_archive_order":67,"of":68,"metrics":{"Accuracy":"60.03","Balanced Accuracy":"60.03"},"uses_additional_data":false},{"leaderboard":"/sota/facial-expression-recognition-on-cmu-mosei","task":"Facial Expression Recognition","dataset":"CMU-MOSEI","model":"ConCluGen","rank_in_archive_order":1,"of":1,"metrics":{"Weighted Accuracy":"66.48"},"uses_additional_data":false},{"leaderboard":"/sota/facial-expression-recognition-on-meld","task":"Facial Expression Recognition","dataset":"MELD","model":"ConCluGen","rank_in_archive_order":1,"of":1,"metrics":{"Weighted Accuracy":"60.03"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.10904","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}