{"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/190501972","title":"A Self-Attentive Emotion Recognition Network","arxiv_id":"1905.01972","date":"2019-04-24","proceeding":null,"authors":["Harris Partaourides","Kostantinos Papadamou","Nicolas Kourtellis","Ilias Leontiadis","Sotirios Chatzis"],"abstract":"Modern deep learning approaches have achieved groundbreaking performance in\nmodeling and classifying sequential data. Specifically, attention networks\nconstitute the state-of-the-art paradigm for capturing long temporal dynamics.\nThis paper examines the efficacy of this paradigm in the challenging task of\nemotion recognition in dyadic conversations. In contrast to existing\napproaches, our work introduces a novel attention mechanism capable of\ninferring the immensity of the effect of each past utterance on the current\nspeaker emotional state. The proposed attention mechanism performs this\ninference procedure without the need of a decoder network; this is achieved by\nmeans of innovative self-attention arguments. Our self-attention networks\ncapture the correlation patterns among consecutive encoder network states, thus\nallowing to robustly and effectively model temporal dynamics over arbitrary\nlong temporal horizons. Thus, we enable capturing strong affective patterns\nover the course of long discussions. We exhibit the effectiveness of our\napproach considering the challenging IEMOCAP benchmark. As we show, our devised\nmethodology outperforms state-of-the-art alternatives and commonly used\napproaches, giving rise to promising new research directions in the context of\nOnline Social Network (OSN) analysis tasks.","url_abs":"http://arxiv.org/abs/1905.01972v1","url_pdf":"http://arxiv.org/pdf/1905.01972v1.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":"190501972","repo_url":"https://github.com/Partaourides/SERN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"emotion-recognition","task_name":"Emotion Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}