BEGIN:VCALENDAR VERSION:2.0 METHOD:PUBLISH PRODID:-//Telerik Inc.//Sitefinity CMS 15.4//EN BEGIN:VTIMEZONE TZID:Central Standard Time BEGIN:STANDARD DTSTART:20251102T020000 RRULE:FREQ=YEARLY;BYDAY=1SU;BYHOUR=2;BYMINUTE=0;BYMONTH=11 TZNAME:Central Standard Time TZOFFSETFROM:-0500 TZOFFSETTO:-0600 END:STANDARD BEGIN:DAYLIGHT DTSTART:20250301T020000 RRULE:FREQ=YEARLY;BYDAY=2SU;BYHOUR=2;BYMINUTE=0;BYMONTH=3 TZNAME:Central Daylight Time TZOFFSETFROM:-0600 TZOFFSETTO:-0500 END:DAYLIGHT END:VTIMEZONE BEGIN:VEVENT DESCRIPTION:Event Type: LectureSpeaker Information: Dr. James RehgThe annua l Goldstick Lecture will be held on Thursday\, October 17\, 2024\, at 4:00 p.m. at the IHotel and Conference Center in Champaign. This year's lectur e will be delivered by Dr. James M. Rehg\, Founder Professor in the Depart ments of Computer Science and Industrial and Enterprise Systems Engineerin g at Illinois and director of the Health Care Engineering Systems Center.W atch the lecture here.His Lecture is titled Leveraging AI to Measure and M odel Social Behavior.Beginning in infancy\, individuals acquire the social and communication skills that are vital for a healthy and productive life . Children with autism face great challenges in acquiring these skills\, r esulting in substantial lifetime risks. As the neural basis for ASD is unc lear\, the diagnosis\, treatment\, and study of autism depends fundamental ly on the analysis of child behavior. Standard methods for behavioral obse rvation and coding are the backbone of research studies but are inherently coarse-grained and not easily scalable. In this talk I will present our r esearch agenda that uses AI models and computer vision technology to autom ate the measurement of social behavior from video. Our goal is to unlock t he rich behavioral information that is present in video and make it availa ble for large-scale data-driven modeling and assessment. I will present se veral recent findings that demonstrate the feasibility of this approach\, including a method for detecting eye contact that has been shown to achiev e human-level accuracy. I will describe recent work in combining vision an d language to model social deduction games and progress in developing long itudinal models of language development. I will describe potential applica tions of this technology to the diagnosis and treatment of autism and othe r developmental conditions.Dr. Rehg received his Ph.D. from CMU in 1995 an d worked at the Cambridge Research Lab of DEC (and then Compaq) from 1995- 2001\, where he managed the computer vision research group. He was a profe ssor in the College of Computing at Georgia Tech from 2001-2022. He receiv ed an NSF CAREER award in 2001 and a Raytheon Faculty Fellowship from Geor gia Tech in 2005. He and his students have received the best student paper awards at ICML 2005\, BMVC 2010 and 2022\, Mobihealth 2014\, Face and Ges ture 2015\, and a Method of the Year Award from the journal Nature Methods . Dr. Rehg served as the Program co-chair for ACCV 2012 and CVPR 2017 and General co-chair for CVPR 2009. He has authored more than 200 peer-reviewe d scientific papers and holds 30 issued US patents. His research interests include computer vision\, machine learning\, and mobile and computational health (https://rehg.org). Dr. Rehg was the lead PI on an NSF Expedition to develop the science and technology of Behavioral Imaging\, the measurem ent and analysis of social and communicative behavior using multi-modal se nsing\, with applications to developmental conditions such as autism. He i s currently the Deputy Director and TR&\;D1 Lead for the mHealth Center for Discovery\, Optimization\, and Translation of Temporally-Precise Inte rventions (mDOT)\, which is developing novel on-body sensing and predictiv e analytics for improving health outcomes.Cost: FreeContact: Alyson Stephe nson217-265-6525alyson4@illinois.eduSponsor: College of Education DTEND:20241017T210000Z DTSTAMP:20260511T181557Z DTSTART:20241017T210000Z LOCATION:IL\,USA\,Champaign\,IHotel - Chancellor's Ballroom SEQUENCE:0 SUMMARY:The 20th Annual Goldstick Family Lecture in the Study of Communicat ion Disorders UID:RFCALITEM639141021570765535 X-ALT-DESC;FMTTYPE=text/html:

Event Type: Lecture

Speaker Information: Dr. James Rehg

The annual Goldstick Lecture will be held on Thursday\, October 17\ , 2024\, at 4:00 p.m. at the IHotel and Conference Center in Champaign. Th is year's lecture will be delivered by Dr. James M. Rehg\, Founder Profess or in the Departments of Computer Science and Industrial and Enterprise Sy stems Engineering at Illinois and director of the Health Care Engineering Systems Center.

Watch the lecture here.

His Lecture is titled Leveraging AI to Measure and Model Soc ial Behavior.

Beginning in infancy\, individuals acquire the social and communication skills that are vital for a healthy and producti ve life. Children with autism face great challenges in acquiring these ski lls\, resulting in substantial lifetime risks. As the neural basis for ASD is unclear\, the diagnosis\, treatment\, and study of autism depends fund amentally on the analysis of child behavior. Standard methods for behavior al observation and coding are the backbone of research studies but are inh erently coarse-grained and not easily scalable. In this talk I will presen t our research agenda that uses AI models and computer vision technology t o automate the measurement of social behavior from video. Our goal is to u nlock the rich behavioral information that is present in video and make it available for large-scale data-driven modeling and assessment. I will pre sent several recent findings that demonstrate the feasibility of this appr oach\, including a method for detecting eye contact that has been shown to achieve human-level accuracy. I will describe recent work in combining vi sion and language to model social deduction games and progress in developi ng longitudinal models of language development. I will describe potential applications of this technology to the diagnosis and treatment of autism a nd other developmental conditions.

Dr. Rehg received his Ph.D. from CMU in 1995 and worked at the Cambridge Research Lab of DEC (and the n Compaq) from 1995-2001\, where he managed the computer vision research g roup. He was a professor in the College of Computing at Georgia Tech from 2001-2022. He received an NSF CAREER award in 2001 and a Raytheon Faculty Fellowship from Georgia Tech in 2005. He and his students have received th e best student paper awards at ICML 2005\, BMVC 2010 and 2022\, Mobihealth 2014\, Face and Gesture 2015\, and a Method of the Year Award from the jo urnal Nature Methods. Dr. Rehg served as the Program co-chair for ACCV 201 2 and CVPR 2017 and General co-chair for CVPR 2009. He has authored more t han 200 peer-reviewed scientific papers and holds 30 issued US patents. Hi s research interests include computer vision\, machine learning\, and mobi le and computational health (https://rehg.org). Dr. Rehg was the lead PI o n an NSF Expedition to develop the science and technology of Behavioral Im aging\, the measurement and analysis of social and communicative behavior using multi-modal sensing\, with applications to developmental conditions such as autism. He is currently the Deputy Director and TR&\;D1 Lead fo r the mHealth Center for Discovery\, Optimization\, and Translation of Tem porally-Precise Interventions (mDOT)\, which is developing novel on-body s ensing and predictive analytics for improving health outcomes.

< p class="cost">Cost: Free

Contact: Alyson S tephenson217-265-6525
alyson4@ill inois.edu

END:VEVENT END:VCALENDAR