{"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/maven-multi-modal-attention-for-valence","title":"MAVEN: Multi-modal Attention for Valence-Arousal Emotion Network","arxiv_id":"2503.12623","date":"2025-03-16","proceeding":null,"authors":["Vrushank Ahire","Kunal Shah","Mudasir Nazir Khan","Nikhil Pakhale","Lownish Rai Sookha","M. A. Ganaie","Abhinav Dhall"],"abstract":"Dynamic emotion recognition in the wild remains challenging due to the transient nature of emotional expressions and temporal misalignment of multi-modal cues. Traditional approaches predict valence and arousal and often overlook the inherent correlation between these two dimensions. The proposed Multi-modal Attention for Valence-Arousal Emotion Network (MAVEN) integrates visual, audio, and textual modalities through a bi-directional cross-modal attention mechanism. MAVEN uses modality-specific encoders to extract features from synchronized video frames, audio segments, and transcripts, predicting emotions in polar coordinates following Russell's circumplex model. The evaluation of the Aff-Wild2 dataset using MAVEN achieved a concordance correlation coefficient (CCC) of 0.3061, surpassing the ResNet-50 baseline model with a CCC of 0.22. The multistage architecture captures the subtle and transient nature of emotional expressions in conversational videos and improves emotion recognition in real-world situations. The code is available at: https://github.com/Vrushank-Ahire/MAVEN_8th_ABAW","url_abs":"https://arxiv.org/abs/2503.12623v2","url_pdf":"https://arxiv.org/pdf/2503.12623v2.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":"maven-multi-modal-attention-for-valence","repo_url":"https://github.com/vrushank-ahire/maven_8th_abaw","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"emotion-recognition","task_name":"Emotion Recognition"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2503.12623","atlas_url":"https://app.syntology.ai/?focus=2503.12623","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}