{"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/vipl-hr-a-multi-modal-database-for-pulse","title":"VIPL-HR: A Multi-modal Database for Pulse Estimation from Less-constrained Face Video","arxiv_id":"1810.04927","date":"2018-10-11","proceeding":null,"authors":["Xuesong Niu","Hu Han","Shiguang Shan","Xilin Chen"],"abstract":"Heart rate (HR) is an important physiological signal that reflects the\nphysical and emotional activities of humans. Traditional HR measurements are\nmainly based on contact monitors, which are inconvenient and may cause\ndiscomfort for the subjects. Recently, methods have been proposed for remote HR\nestimation from face videos. However, most of the existing methods focus on\nwell-controlled scenarios, their generalization ability into less-constrained\nscenarios are not known. At the same time, lacking large-scale databases has\nlimited the use of deep representation learning methods in remote HR\nestimation. In this paper, we introduce a large-scale multi-modal HR database\n(named as VIPL-HR), which contains 2,378 visible light videos (VIS) and 752\nnear-infrared (NIR) videos of 107 subjects. Our VIPL-HR database also contains\nvarious variations such as head movements, illumination variations, and\nacquisition device changes. We also learn a deep HR estimator (named as\nRhythmNet) with the proposed spatial-temporal representation, which achieves\npromising results on both the public-domain and our VIPL-HR HR estimation\ndatabases. We would like to put the VIPL-HR database into the public domain.","url_abs":"http://arxiv.org/abs/1810.04927v2","url_pdf":"http://arxiv.org/pdf/1810.04927v2.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":"vipl-hr-a-multi-modal-database-for-pulse","repo_url":"https://github.com/phuselab/pyVHR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[{"slug":"vipl-hr","name":"VIPL-HR","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.04927","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}