{"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/facial-expression-recognition-using","title":"Facial Expression Recognition using Convolutional Neural Networks: State of the Art","arxiv_id":"1612.02903","date":"2016-12-09","proceeding":null,"authors":["Christopher Pramerdorfer","Martin Kampel"],"abstract":"The ability to recognize facial expressions automatically enables novel\napplications in human-computer interaction and other areas. Consequently, there\nhas been active research in this field, with several recent works utilizing\nConvolutional Neural Networks (CNNs) for feature extraction and inference.\nThese works differ significantly in terms of CNN architectures and other\nfactors. Based on the reported results alone, the performance impact of these\nfactors is unclear. In this paper, we review the state of the art in\nimage-based facial expression recognition using CNNs and highlight algorithmic\ndifferences and their performance impact. On this basis, we identify existing\nbottlenecks and consequently directions for advancing this research field.\nFurthermore, we demonstrate that overcoming one of these bottlenecks - the\ncomparatively basic architectures of the CNNs utilized in this field - leads to\na substantial performance increase. By forming an ensemble of modern deep CNNs,\nwe obtain a FER2013 test accuracy of 75.2%, outperforming previous works\nwithout requiring auxiliary training data or face registration.","url_abs":"http://arxiv.org/abs/1612.02903v1","url_pdf":"http://arxiv.org/pdf/1612.02903v1.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":"facial-expression-recognition-using","repo_url":"https://github.com/amilkh/cs230-fer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"facial-expression-recognition-using","repo_url":"https://github.com/apuayush/face_express","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"facial-expression-recognition-using","repo_url":"https://github.com/janZub-AI/EmotionDetectionVGG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"facial-expression-recognition-using","repo_url":"https://github.com/pranjalrai-iitd/FER2013-Facial-Emotion-Recognition-","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"facial-expression-recognition-1","task_name":"Facial Expression Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/facial-expression-recognition-on-fer2013-1","task":"Facial Expression Recognition","dataset":"FER2013","model":"VGG","rank_in_archive_order":1,"of":3,"metrics":{"Accuracy":"72.7"},"uses_additional_data":false},{"leaderboard":"/sota/facial-expression-recognition-on-fer2013-1","task":"Facial Expression Recognition","dataset":"FER2013","model":"Res-Net","rank_in_archive_order":2,"of":3,"metrics":{"Accuracy":"72.4"},"uses_additional_data":false},{"leaderboard":"/sota/facial-expression-recognition-on-fer2013-1","task":"Facial Expression Recognition","dataset":"FER2013","model":"Inception","rank_in_archive_order":3,"of":3,"metrics":{"Accuracy":"71.6"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}