{"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/group-level-emotion-recognition-using","title":"Group-level Emotion Recognition using Transfer Learning from Face Identification","arxiv_id":"1709.01688","date":"2017-09-06","proceeding":null,"authors":["Alexandr G. Rassadin","Alexey S. Gruzdev","Andrey V. Savchenko"],"abstract":"In this paper, we describe our algorithmic approach, which was used for\nsubmissions in the fifth Emotion Recognition in the Wild (EmotiW 2017)\ngroup-level emotion recognition sub-challenge. We extracted feature vectors of\ndetected faces using the Convolutional Neural Network trained for face\nidentification task, rather than traditional pre-training on emotion\nrecognition problems. In the final pipeline an ensemble of Random Forest\nclassifiers was learned to predict emotion score using available training set.\nIn case when the faces have not been detected, one member of our ensemble\nextracts features from the whole image. During our experimental study, the\nproposed approach showed the lowest error rate when compared to other explored\ntechniques. In particular, we achieved 75.4% accuracy on the validation data,\nwhich is 20% higher than the handcrafted feature-based baseline. The source\ncode using Keras framework is publicly available.","url_abs":"http://arxiv.org/abs/1709.01688v3","url_pdf":"http://arxiv.org/pdf/1709.01688v3.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":"group-level-emotion-recognition-using","repo_url":"https://github.com/arassadin/emotiw2017","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"emotion-recognition","task_name":"Emotion Recognition"},{"task_slug":"face-identification","task_name":"Face Identification"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}