Program
Program:
18 June, Half Day
Location: West 212, In-Person.
Time: 01.30pm-05.30pm Vancouver Local Time (PDT)
01.30pm-01.40pm -- Opening
01.40pm-02.30pm -- Keynote Speaker: Elisabeth André
Title: Computational Approaches for Assessing Emotional Alignment in Mental Health Research
Abstract: In my talk, I will discuss the importance of emotions in psychological therapies, particularly in emotional disorders like depression. In addition to the patient’s emotions, the interplay of the patient’s and the therapist’s emotions needs to be considered in the therapeutic process and outcome. Recent developments in machine learning offer new opportunities to efficiently assess emotional alignment in mental health research. The assessment is based on facial expression analysis, posture and gesture recognition, emotional speech analysis and multimodal combinations therefore. In my talk, I will discuss the ability of multimodal machine learning approaches to predict emotional states, symptoms of the psychological disorder, and processes of change in dyadic interactions, emotional coping, and experience. In addition to analyzing patient-therapist dyads, I will report on the dynamics of interaction patterns in conversations with mental health coaches on the patient’s mobile phone. Finally, I will share lessons learned when conducting interdisciplinary projects on mental health research.
02.30pm-02.50pm --
Human Gesture and Gait Analysis for Autism Detection
Sania Zahan (The University of Western Australia)*; Syed Zulqarnain Gilani (Edith Cowan University); Ghulam Mubashar Hassan (The University of Western Australia); Ajmal Mian (University of Western Australia)
02.50pm-03.10pm --
Privileged Knowledge Distillation for Dimensional Emotion Recognition in the Wild
Muhammad Haseeb Aslam (ETS)*; Muhammad Osama Zeeshan (École de technologie supérieure); Alessandro Lameiras Koerich (École de technologie supérieure ); Marco Pedersoli (École de technologie supérieure); Simon Bacon (Concordia University); Eric Granger (ETS Montreal )
03.10-03.45pm -- Afternoon coffee
03.45pm-04.35pm -- Keynote Speaker: Ehsan Adeli
Title: Human Pose and Gestures as Digital Biomarkers for Cognitive Aging and Neurodegenerative Diseases
Abstract: Digital biomarkers are data that can be directly collected about health or disease management through digital health technologies to explain, influence, and/or predict health-related outcomes. Recent developments in AI and computer vision present an exceptional opportunity for automating digital biomarker discovery and development. In this talk, I will go over these concepts and present some of our recent work on computer vision-based biomarker discovery.
04.35pm-05.20pm -- Keynote Speaker: Daniel McDuff
Title: Seeing Beneath the Skin with Computational Photography
Abstract: For more than two decades, telehealth held the promise of greater access to healthcare services in the home but remained as a niche opportunity due to a combination of regulatory, economic, and cultural barriers that prevented the expansion and innovation of digital health services. The SARS-CoV-2 pandemic promoted a rapid and explosive growth of telehealth that provided an effective mechanism for safely providing care without risk of exposure. Remote patient monitoring is now gaining adoption and new physiological and medical imaging modalities that leverage recent advances in computational photography are emerging. These methods use everyday sensors to non-invasively inspect and measure the internal state of the body. I will present research on physiological and behavioral measurement via ubiquitous hardware, and highlight approaches that capture multimodal signals (e.g., facial and motor movements, heart rate and HRV, respiration, blood pressure) without contact with the body. I'll show examples of state-of-the-art, on-device neural models and a synthetics data pipeline to help us learn more robust representations and achieve performance close to that of contact sensors. Following this, I will give examples of novel human-computer interfaces that leverage these signals to improve health, wellbeing and communication.