{"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/facial-expression-and-peripheral-physiology","title":"Facial Expression and Peripheral Physiology Fusion to Decode Individualized Affective Experience","arxiv_id":"1811.07392","date":"2018-11-18","proceeding":null,"authors":["Yu Yin","Mohsen Nabian","Miolin Fan","Chun-An Chou","Maria Gendron","Sarah Ostadabbas"],"abstract":"In this paper, we present a multimodal approach to simultaneously analyze\nfacial movements and several peripheral physiological signals to decode\nindividualized affective experiences under positive and negative emotional\ncontexts, while considering their personalized resting dynamics. We propose a\nperson-specific recurrence network to quantify the dynamics present in the\nperson's facial movements and physiological data. Facial movement is\nrepresented using a robust head vs. 3D face landmark localization and tracking\napproach, and physiological data are processed by extracting known attributes\nrelated to the underlying affective experience. The dynamical coupling between\ndifferent input modalities is then assessed through the extraction of several\ncomplex recurrent network metrics. Inference models are then trained using\nthese metrics as features to predict individual's affective experience in a\ngiven context, after their resting dynamics are excluded from their response.\nWe validated our approach using a multimodal dataset consists of (i) facial\nvideos and (ii) several peripheral physiological signals, synchronously\nrecorded from 12 participants while watching 4 emotion-eliciting video-based\nstimuli. The affective experience prediction results signified that our\nmultimodal fusion method improves the prediction accuracy up to 19% when\ncompared to the prediction using only one or a subset of the input modalities.\nFurthermore, we gained prediction improvement for affective experience by\nconsidering the effect of individualized resting dynamics.","url_abs":"http://arxiv.org/abs/1811.07392v1","url_pdf":"http://arxiv.org/pdf/1811.07392v1.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":"facial-expression-and-peripheral-physiology","repo_url":"https://github.com/ostadabbas/3d-facial-landmark-detection-and-tracking","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"prediction","task_name":"Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}