I am a Systems Scientist (faculty) in the Robotics Institute at Carnegie-Mellon University. I focus on advancing the state-of-the-art in multi-modal methods for computational behavior science, specifically in areas of modelling, analysis, and synthesis of human behavior and emotion using diverse sensors.


05/2019 I am organizing a workshop & challenge on Dense 3D Face Reconstruction in the Wild from Video (3DFAW-Video), In conjunction with ICCV 2019, Seoul, Korea!!

03/2019 Demo Paper accepted to Face & Gesture 2019: AFAR: A deep learning based tool for automated facial affect recognition!

01/2019 Paper accepted as oral presentation to Face & Gesture 2019: Cross-domain AU Detection: Domains, Learning Approaches, and Measures!

11/2018 Book chapter to appear in Multimodal Behavior Analysis in the Wild: Chapter 19 - Affective facial computing: Generalizability across domains!

09/2018 Journal article to appear Image and Vision Computing: Modeling and synthesis of kinship patterns of facial expressions!

07/2018 Paper accepted as oral presentation to ICMI 2018: Automated Affect Detection in Deep Brain Stimulation for Obsessive-Compulsive Disorder!

04/2018 Paper accepted to CVPR-W 2018: FACSCaps: Pose-Independent Facial Action Coding with Capsules!

08/2016 I am organizing a workshop on 3D Face Alignment in the Wild (3DFAW) & Challenge, In conjunction with ECCV 2016, Amsterdam, The Netherlands!!

05/2015 At FG 2015 I received an Outstanding Reviewer Award and a Best Paper Award with Jeffrey F. Cohn and Takeo Kanade for our paper on Dense 3D Face Alignment from 2D Videos in Real-Time!

02/2015 Our papers on Dense 3D Face Alignment from 2D Videos in Real-Time and on How much training data for facial action unit detection? will be presented at FG 2015!

12/2014 Our journal paper on Spontaneous facial expression in unscripted social interactions can be measured automatically has been published in Behavior Research Methods (Springer, IF: 2.458)!

08/2014 I will be presenting our work on Spatio-temporal Event Classification using Time-series Kernel based Structured Sparsity at ECCV 2014!