{"689046":{"#nid":"689046","#data":{"type":"event","title":"PhD Defense by Fiona Ryan","body":[{"value":"\u003Cp\u003ETitle: Towards Human-Centric Perception: Grounding Human Behavior in Multimodal Context\u003C\/p\u003E\u003Cp\u003EDate: Tuesday, April 7th 2026\u003Cbr\u003ETime: \u0026nbsp;3:00-5:00 PM ET\u003Cbr\u003ELocation: \u0026nbsp;Coda 0915 \u0026amp; Zoom (https:\/\/gatech.zoom.us\/j\/95248425147)\u003Cbr\u003E\u0026nbsp;\u003Cbr\u003EFiona Ryan\u003Cbr\u003EPh.D. Student\u003Cbr\u003ESchool of Interactive Computing\u0026nbsp;\u003Cbr\u003EGeorgia Institute of Technology\u003C\/p\u003E\u003Cp\u003ECommittee\u0026nbsp;\u003Cbr\u003EDr. Judy Hoffman (Advisor) - School of Interactive Computing, Georgia Institute of Technology\u003Cbr\u003EDr. James Rehg (Advisor) - School of Interactive Computing, Georgia Institute of Technology\u003Cbr\u003EDr. James Hays - School of Interactive Computing, Georgia Institute of Technology\u003Cbr\u003EDr. Zsolt Kira - School of Interactive Computing, Georgia Institute of Technology\u003Cbr\u003EDr. Josef Sivic - Czech Institute of Informatics, Robotics, and Cybernetics, Czech Technical University in Prague\u003C\/p\u003E\u003Cp\u003EAbstract\u0026nbsp;\u003Cbr\u003EPerceiving and understanding human behavior with computer vision is a core challenge for developing AI systems that can effectively interact with and assist people in everyday life. Modeling human behavior is challenging because it requires not only visually recognizing behaviors like gaze, gesture, and movement, but also grounding them in the context in which they occur. Human behavior is shaped by intent and higher-level goals, the surrounding physical environment, social interactions with other people, and additional modalities such as speech and language, making it inherently multimodal and situated.\u003C\/p\u003E\u003Cp\u003EThis thesis explores how to model human behavior in context by addressing three core needs: (1) datasets that capture naturalistic human interactions in everyday environments, enabling new behavior modeling tasks, (2) multimodal methods that ground behavior by leveraging information across multiple modalities including vision, audio, and language, and (3) robust methods for recognizing behavioral cues that leverage advances in foundation models to encode context. First, I present contributions to large-scale multimodal egocentric datasets that capture social interactions and human object interactions during activities. Second, I present a modeling approach and dataset for the novel task of identifying targets of selective auditory attention during social conversations in noisy environments. Third, I present a method for efficiently adapting vision-language retrieval models to represent new concepts and recognize them in different contexts. Fourth, I propose a framework for estimating gaze targets in scenes using the representation from a visual foundation model. Finally, I extend this framework to forecasting gaze behavior in egocentric video.\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003ETowards Human-Centric Perception: Grounding Human Behavior in Multimodal Context\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Towards Human-Centric Perception: Grounding Human Behavior in Multimodal Context"}],"uid":"27707","created_gmt":"2026-03-19 15:35:12","changed_gmt":"2026-03-19 15:36:37","author":"Tatianna Richardson","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2026-04-07T15:00:00-04:00","event_time_end":"2026-04-07T17:00:00-04:00","event_time_end_last":"2026-04-07T17:00:00-04:00","gmt_time_start":"2026-04-07 19:00:00","gmt_time_end":"2026-04-07 21:00:00","gmt_time_end_last":"2026-04-07 21:00:00","rrule":null,"timezone":"America\/New_York"},"location":"Coda 0915 \u0026 Zoom ","extras":[],"groups":[{"id":"221981","name":"Graduate Studies"}],"categories":[],"keywords":[{"id":"100811","name":"Phd Defense"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1788","name":"Other\/Miscellaneous"}],"invited_audience":[{"id":"78771","name":"Public"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}