{"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/stressid-a-multimodal-dataset-for-stress","title":"StressID: a Multimodal Dataset for Stress Identification","arxiv_id":null,"date":"2023-09-26","proceeding":"NeurIPS 2023 11","authors":[],"abstract":"StressID is a new dataset specifically designed for stress identification from\nunimodal and multimodal data. It contains videos of facial expressions, audio\nrecordings, and physiological signals. The video and audio recordings are acquired\nusing an RGB camera with an integrated microphone. The physiological data\nis composed of electrocardiography (ECG), electrodermal activity (EDA), and\nrespiration signals that are recorded and monitored using a wearable device. This\nexperimental setup ensures a synchronized and high-quality multimodal data col-\nlection. Different stress-inducing stimuli, such as emotional video clips, cognitive\ntasks including mathematical or comprehension exercises, and public speaking\nscenarios, are designed to trigger a diverse range of emotional responses. The\nfinal dataset consists of recordings from 65 participants who performed 11 tasks,\nas well as their ratings of perceived relaxation, stress, arousal, and valence levels.\nStressID is one of the largest datasets for stress identification that features three\ndifferent sources of data and varied classes of stimuli, representing more than\n39 hours of annotated data in total. StressID offers baseline models for stress\nclassification including a cleaning, feature extraction, and classification phase for\neach modality. Additionally, we provide multimodal predictive models combining\nvideo, audio, and physiological inputs. The data and the code for the baselines are\navailable at https://project.inria.fr/stressid/.","url_abs":"https://openreview.net/forum?id=qWsQi9DGJb","url_pdf":"https://openreview.net/pdf?id=qWsQi9DGJb","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":"stressid-a-multimodal-dataset-for-stress","repo_url":"https://github.com/robustml-eurecom/stressid","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}