{"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/deep-emotion-facial-expression-recognition","title":"Deep-Emotion: Facial Expression Recognition Using Attentional Convolutional Network","arxiv_id":"1902.01019","date":"2019-02-04","proceeding":null,"authors":["Shervin Minaee","Amirali Abdolrashidi"],"abstract":"Facial expression recognition has been an active research area over the past\nfew decades, and it is still challenging due to the high intra-class variation.\n  Traditional approaches for this problem rely on hand-crafted features such as\nSIFT, HOG and LBP, followed by a classifier trained on a database of images or\nvideos.\n  Most of these works perform reasonably well on datasets of images captured in\na controlled condition, but fail to perform as good on more challenging\ndatasets with more image variation and partial faces.\n  In recent years, several works proposed an end-to-end framework for facial\nexpression recognition, using deep learning models.\n  Despite the better performance of these works, there still seems to be a\ngreat room for improvement.\n  In this work, we propose a deep learning approach based on attentional\nconvolutional network, which is able to focus on important parts of the face,\nand achieves significant improvement over previous models on multiple datasets,\nincluding FER-2013, CK+, FERG, and JAFFE.\n  We also use a visualization technique which is able to find important face\nregions for detecting different emotions, based on the classifier's output.\n  Through experimental results, we show that different emotions seems to be\nsensitive to different parts of the face.","url_abs":"http://arxiv.org/abs/1902.01019v1","url_pdf":"http://arxiv.org/pdf/1902.01019v1.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":"deep-emotion-facial-expression-recognition","repo_url":"https://github.com/KLT20/Realtime-Face-Emotion-Recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-emotion-facial-expression-recognition","repo_url":"https://github.com/kaushal-k/Deep-Emotion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"deep-emotion-facial-expression-recognition","repo_url":"https://github.com/omarsayed7/Deep-Emotion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"facial-expression-recognition-1","task_name":"Facial Expression Recognition"},{"task_slug":"facial-expression-recognition","task_name":"Facial Expression Recognition (FER)"},{"task_slug":"image-variation","task_name":"Image-Variation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/facial-expression-recognition-on-ck","task":"Facial Expression Recognition (FER)","dataset":"CK+","model":"DeepEmotion","rank_in_archive_order":7,"of":7,"metrics":{"Accuracy (7 emotion)":"98"},"uses_additional_data":false},{"leaderboard":"/sota/facial-expression-recognition-on-fer2013","task":"Facial Expression Recognition (FER)","dataset":"FER2013","model":"DeepEmotion","rank_in_archive_order":16,"of":17,"metrics":{"Accuracy":"70.02"},"uses_additional_data":false},{"leaderboard":"/sota/facial-expression-recognition-on-ferg","task":"Facial Expression Recognition (FER)","dataset":"FERG","model":"DeepEmotion","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"99.3"},"uses_additional_data":false},{"leaderboard":"/sota/facial-expression-recognition-on-jaffe","task":"Facial Expression Recognition (FER)","dataset":"JAFFE","model":"DeepEmotion","rank_in_archive_order":4,"of":4,"metrics":{"Accuracy":"92.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.01019","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}