{"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/classifying-and-visualizing-emotions-with","title":"Classifying and Visualizing Emotions with Emotional DAN","arxiv_id":"1810.10529","date":"2018-10-23","proceeding":null,"authors":["Ivona Tautkute","Tomasz Trzcinski"],"abstract":"Classification of human emotions remains an important and challenging task\nfor many computer vision algorithms, especially in the era of humanoid robots\nwhich coexist with humans in their everyday life. Currently proposed methods\nfor emotion recognition solve this task using multi-layered convolutional\nnetworks that do not explicitly infer any facial features in the classification\nphase. In this work, we postulate a fundamentally different approach to solve\nemotion recognition task that relies on incorporating facial landmarks as a\npart of the classification loss function. To that end, we extend a recently\nproposed Deep Alignment Network (DAN) with a term related to facial features.\nThanks to this simple modification, our model called EmotionalDAN is able to\noutperform state-of-the-art emotion classification methods on two challenging\nbenchmark dataset by up to 5%. Furthermore, we visualize image regions analyzed\nby the network when making a decision and the results indicate that our\nEmotionalDAN model is able to correctly identify facial landmarks responsible\nfor expressing the emotions.","url_abs":"http://arxiv.org/abs/1810.10529v1","url_pdf":"http://arxiv.org/pdf/1810.10529v1.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":"classifying-and-visualizing-emotions-with","repo_url":"https://github.com/IvonaTau/emotionaldan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"classifying-and-visualizing-emotions-with","repo_url":"https://github.com/qxtaiba/Emotional-Dystopia","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"emotion-classification","task_name":"Emotion Classification"},{"task_slug":"emotion-recognition","task_name":"Emotion Recognition"},{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}