{"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-adaptive-attention-for-joint-facial","title":"Deep Adaptive Attention for Joint Facial Action Unit Detection and Face Alignment","arxiv_id":"1803.05588","date":"2018-03-15","proceeding":"ECCV 2018 9","authors":["Zhiwen Shao","Zhilei Liu","Jianfei Cai","Lizhuang Ma"],"abstract":"Facial action unit (AU) detection and face alignment are two highly\ncorrelated tasks since facial landmarks can provide precise AU locations to\nfacilitate the extraction of meaningful local features for AU detection. Most\nexisting AU detection works often treat face alignment as a preprocessing and\nhandle the two tasks independently. In this paper, we propose a novel\nend-to-end deep learning framework for joint AU detection and face alignment,\nwhich has not been explored before. In particular, multi-scale shared features\nare learned firstly, and high-level features of face alignment are fed into AU\ndetection. Moreover, to extract precise local features, we propose an adaptive\nattention learning module to refine the attention map of each AU adaptively.\nFinally, the assembled local features are integrated with face alignment\nfeatures and global features for AU detection. Experiments on BP4D and DISFA\nbenchmarks demonstrate that our framework significantly outperforms the\nstate-of-the-art methods for AU detection.","url_abs":"http://arxiv.org/abs/1803.05588v2","url_pdf":"http://arxiv.org/pdf/1803.05588v2.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-adaptive-attention-for-joint-facial","repo_url":"https://github.com/ZhiwenShao/JAANet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-unit-detection","task_name":"Action Unit Detection"},{"task_slug":"face-alignment","task_name":"Face Alignment"},{"task_slug":"facial-action-unit-detection","task_name":"Facial Action Unit Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/facial-action-unit-detection-on-bp4d","task":"Facial Action Unit Detection","dataset":"BP4D","model":"JAA-Net","rank_in_archive_order":8,"of":10,"metrics":{"Average F1":"60.0"},"uses_additional_data":false},{"leaderboard":"/sota/facial-action-unit-detection-on-disfa","task":"Facial Action Unit Detection","dataset":"DISFA","model":"JAA-Net","rank_in_archive_order":7,"of":8,"metrics":{"Average F1":"56.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1803.05588","atlas_url":"https://app.syntology.ai/?focus=1803.05588","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}