{"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/cogmen-contextualized-gnn-based-multimodal","title":"COGMEN: COntextualized GNN based Multimodal Emotion recognitioN","arxiv_id":"2205.02455","date":"2022-05-05","proceeding":"NAACL 2022 7","authors":["Abhinav Joshi","Ashwani Bhat","Ayush Jain","Atin Vikram Singh","Ashutosh Modi"],"abstract":"Emotions are an inherent part of human interactions, and consequently, it is imperative to develop AI systems that understand and recognize human emotions. During a conversation involving various people, a person's emotions are influenced by the other speaker's utterances and their own emotional state over the utterances. In this paper, we propose COntextualized Graph Neural Network based Multimodal Emotion recognitioN (COGMEN) system that leverages local information (i.e., inter/intra dependency between speakers) and global information (context). The proposed model uses Graph Neural Network (GNN) based architecture to model the complex dependencies (local and global information) in a conversation. Our model gives state-of-the-art (SOTA) results on IEMOCAP and MOSEI datasets, and detailed ablation experiments show the importance of modeling information at both levels.","url_abs":"https://arxiv.org/abs/2205.02455v1","url_pdf":"https://arxiv.org/pdf/2205.02455v1.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":"cogmen-contextualized-gnn-based-multimodal","repo_url":"https://github.com/exploration-lab/cogmen","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"cogmen-contextualized-gnn-based-multimodal","repo_url":"https://github.com/m-muaz/Cogmen_SLT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"emotion-recognition","task_name":"Emotion Recognition"},{"task_slug":"emotion-recognition-in-conversation","task_name":"Emotion Recognition in Conversation"},{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"multimodal-emotion-recognition","task_name":"Multimodal Emotion Recognition"}],"methods":[{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/emotion-recognition-in-conversation-on-cmu-2","task":"Emotion Recognition in Conversation","dataset":"CMU-MOSEI-Sentiment","model":"COGMEN","rank_in_archive_order":3,"of":7,"metrics":{"Weighted F1":"43.90"},"uses_additional_data":false},{"leaderboard":"/sota/emotion-recognition-in-conversation-on-7","task":"Emotion Recognition in Conversation","dataset":"IEMOCAP-4","model":"COGMEN","rank_in_archive_order":3,"of":8,"metrics":{"Weighted F1":"84.50"},"uses_additional_data":false},{"leaderboard":"/sota/multimodal-emotion-recognition-on-iemocap-4","task":"Multimodal Emotion Recognition","dataset":"IEMOCAP-4","model":"COGMEN","rank_in_archive_order":3,"of":11,"metrics":{"Weighted F1":"84.50"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2205.02455","atlas_url":"https://app.syntology.ai/?focus=2205.02455","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}