[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-149268-105":59,"doc-detail-149268-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","smile-intensity-detection-in-multiparty-interaction-using-deep-learning","Smile Intensity Detection in Multiparty Interaction - using Deep Learning","","Emotion expression recognition supports decision making in autonomous agents that interact with humans. This paper describes the development of a software component for smile intensity detection in multiparty interaction. It details the deep learning architecture and training process, then analyzes test results from the trained network. Finally, it presents implementation and visualization steps for deploying the model as a real-time software component.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/smile-intensity-detection-in-multiparty-interaction-using-deep-learning/149268/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/smile-intensity-detection-in-multiparty-interaction-using-deep-learning/149268.png","ImageObject",300,407,{"name":92,"@type":93},"Miles","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-17","2026-08-27",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",13,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What problem does the paper address?","Question",{"text":113,"@type":114},"The paper focuses on detecting smile intensity for agents interacting with multiple people, enabling emotion-aware decision making.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How is the smile intensity model developed?",{"text":118,"@type":114},"The work develops a deep learning architecture and explains its training process, then evaluates performance on test results.",{"name":120,"@type":111,"acceptedAnswer":121},"How is the model deployed for real-time use?",{"text":122,"@type":114},"The paper outlines implementation and visualization steps to integrate the trained network into a responsive real-time software component for multiparty interaction.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},149268,1787797330,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":34,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":130,"read_time":144,"preview_page_count":4},13056703019404,"https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0","2019 8th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW)  \nSmile Intensity Detection in Multiparty Interaction  \nusing Deep Learning  \nPhiline Witzig  \nDisney Research Los Angeles Glendale, California, USA [philine.witzig@gmail.com](philine.witzig@gmail.com)  \nJames Kennedy  \nDisney Research Los Angeles Glendale, California, USA [james.r.kennedy@disney.com](james.r.kennedy@disney.com)  \nCristina Segalin  \nDisney Research Los Angeles Glendale, California, USA [cristina.segalin@disney.com](cristina.segalin@disney.com)  \nAbstract—Emotion expression recognition is an important aspect for enabling decision making in autonomous agents and systems designed to interact with humans. In this paper, we present our experience in developing a software component for smile intensity detection for multiparty interaction. First, the deep learning architecture and training process is described in detail. This is followed by analysis of the results obtained from testing the trained network. Finally, we outline the steps taken to implement and visualize this network in a real-time software component.  \nIndex Terms—smile intensity, deep learning, groups, multiparty interaction  \nI. INTRODUCTION  \nAs social animals, humans are primed to assess and respond to social signals in others [22] . Emotions are key to establishing and maintaining relations between humans and their environment, including others [2] . Consequently, emotions are often used as a basis for decision-making in human-human interactions; “the emotional signals of another guide action”  \n[2] . This carries over into interactions between humans and agents [28],[36],[37] . The quality of emotion regulation in an interaction directly relates to the quality of social interactions [24] . For artificial agents to effectively regulate emotion and use emotion as the basis for decisions, fast and accurate emotion detection is an essential precursor.  \nA great deal of research has previously been conducted into emotion recognition using many different techniques [3], [32], [35] . More recently, attention has turned toward deep learning for emotion recognition [16], [17] . While much progress is being made, the majority of these existing works focus on developing new algorithms for emotion detection, and show results benchmarking against datasets. It is less common to discuss the deployment of these algorithms in online systems, particularly in cases where hardware resources might be limited.  \nIn this paper, we present a smile intensity machine learning model, but also describe the deployment in a responsive software component. Our work is specifically targeted toward an agent interacting with groups of people. Dealing with groups of people increases the complexity of the deployment due to the varied, and increased numbers of people in the scene. This requires additional computational resources, which are not always available at the point of deployment, placing  \nconstraints on the software design. By discussing the deployment process and associated challenges, we contribute our lessons learned and potential solutions.  \nII. RELATED WORK  \nSeveral deep learning models have been proposed for arousal/valence classification (e.g., [21]), however, smile detection is a less explored problem. Smile detection can be used to motivate agent behavior, or to further inform other affective detection components and reasoning. Detecting different smile intensities allows agents to respond appropriately based on the strength of the input expression from one or more users. This will enable the design and creation of more natural interactions.  \nWhitehill et al. developed a smile detector using Support Vector Machines (SVM) with Gabor features [38], [39] . The results showed the promise of smile intensity detection, but uses source data with coarse annotation (`happy' vs. `not happy'), as well as mostly images, rather than videos. Consequently, information c","cbCaii3TTwKxbiuj","https://ap.wps.com/l/cbCaii3TTwKxbiuj","pdf",5788918,"English","# Introduction\n# Related Work","[{\"question\":\"What problem does the paper address?\",\"answer\":\"The paper focuses on detecting smile intensity for agents interacting with multiple people, enabling emotion-aware decision making.\"},{\"question\":\"How is the smile intensity model developed?\",\"answer\":\"The work develops a deep learning architecture and explains its training process, then evaluates performance on test results.\"},{\"question\":\"How is the model deployed for real-time use?\",\"answer\":\"The paper outlines implementation and visualization steps to integrate the trained network into a responsive real-time software component for multiparty interaction.\"}]","Smile Intensity Detection in Multiparty Interaction - using Deep Learning | PDF",18]