{"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/unsupervised-learning-of-eye-gaze","title":"Unsupervised Learning of Eye Gaze Representation from the Web","arxiv_id":"1904.02459","date":"2019-04-04","proceeding":null,"authors":["Neeru Dubey","Shreya Ghosh","Abhinav Dhall"],"abstract":"Automatic eye gaze estimation has interested researchers for a while now. In\nthis paper, we propose an unsupervised learning based method for estimating the\neye gaze region. To train the proposed network \"Ize-Net\" in self-supervised\nmanner, we collect a large `in the wild' dataset containing 1,54,251 images\nfrom the web. For the images in the database, we divide the gaze into three\nregions based on an automatic technique based on pupil-centers localization and\nthen use a feature-based technique to determine the gaze region. The\nperformance is evaluated on the Tablet Gaze and CAVE datasets by fine-tuning\nresults of Ize-Net for the task of eye gaze estimation. The feature\nrepresentation learned is also used to train traditional machine learning\nalgorithms for eye gaze estimation. The results demonstrate that the proposed\nmethod learns a rich data representation, which can be efficiently fine-tuned\nfor any eye gaze estimation dataset.","url_abs":"http://arxiv.org/abs/1904.02459v1","url_pdf":"http://arxiv.org/pdf/1904.02459v1.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":"unsupervised-learning-of-eye-gaze","repo_url":"https://github.com/Neerudubey/Unsupervised-Eye-gaze-estimation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"gaze-estimation","task_name":"Gaze Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}