{"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/self-supervised-learning-of-face","title":"Self-Supervised Learning of Face Representations for Video Face Clustering","arxiv_id":"1903.01000","date":"2019-03-03","proceeding":null,"authors":["Vivek Sharma","Makarand Tapaswi","M. Saquib Sarfraz","Rainer Stiefelhagen"],"abstract":"Analyzing the story behind TV series and movies often requires understanding\nwho the characters are and what they are doing. With improving deep face\nmodels, this may seem like a solved problem. However, as face detectors get\nbetter, clustering/identification needs to be revisited to address increasing\ndiversity in facial appearance. In this paper, we address video face clustering\nusing unsupervised methods. Our emphasis is on distilling the essential\ninformation, identity, from the representations obtained using deep pre-trained\nface networks. We propose a self-supervised Siamese network that can be trained\nwithout the need for video/track based supervision, and thus can also be\napplied to image collections. We evaluate our proposed method on three video\nface clustering datasets. The experiments show that our methods outperform\ncurrent state-of-the-art methods on all datasets. Video face clustering is\nlacking a common benchmark as current works are often evaluated with different\nmetrics and/or different sets of face tracks.","url_abs":"http://arxiv.org/abs/1903.01000v1","url_pdf":"http://arxiv.org/pdf/1903.01000v1.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":"self-supervised-learning-of-face","repo_url":"https://github.com/vivoutlaw/SSIAM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"face-clustering","task_name":"Face Clustering"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[{"method_slug":"siamese-network","method_name":"Siamese Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}