Publications (10)
VEATIC: Video-based Emotion and Affect Tracking in Context Dataset
Zhihang Ren, Jefferson Ortega, Yifan Wang +4
Human affect recognition has been a significant topic in psychophysics and computer vision. However, the currently published datasets have many limitations. For example, most datas…
Communicating Robot Arm Motion Intent Through Mixed Reality Head-mounted Displays
Eric Rosen, David Whitney, Elizabeth Phillips +4
Efficient motion intent communication is necessary for safe and collaborative work environments with collocated humans and robots. Humans efficiently communicate their motion inten…
Human-computer interactions predict mental health
Veith Weilnhammer, Jefferson Ortega, David Whitney
Scalable assessments of mental illness remain a critical roadblock toward accessible and equitable care. Here, we show that everyday human-computer interactions encode mental healt…
On Doubly Robust Inference for Double Machine Learning in Semiparametric Regression
Oliver Dukes, Stijn Vansteelandt, David Whitney
Due to concerns about parametric model misspecification, there is interest in using machine learning to adjust for confounding when evaluating the causal effect of an exposure on a…
SIMMC: Situated Interactive Multi-Modal Conversational Data Collection And Evaluation Platform
Paul A. Crook, Shivani Poddar, Ankita De +4
As digital virtual assistants become ubiquitous, it becomes increasingly important to understand the situated behaviour of users as they interact with these assistants. To this end…
Predicting Driver Attention in Critical Situations
Ye Xia, Danqing Zhang, Jinkyu Kim +3
Robust driver attention prediction for critical situations is a challenging computer vision problem, yet essential for autonomous driving. Because critical driving moments are so r…
Curiosity Based Exploration for Learning Terrain Models
Yogesh Girdhar, David Whitney, Gregory Dudek
We present a robotic exploration technique in which the goal is to learn to a visual model and be able to distinguish between different terrains and other visual components in an u…
Situated and Interactive Multimodal Conversations
Seungwhan Moon, Satwik Kottur, Paul A. Crook +9
Next generation virtual assistants are envisioned to handle multimodal inputs (e.g., vision, memories of previous interactions, in addition to the user's utterances), and perform m…
Periphery-Fovea Multi-Resolution Driving Model guided by Human Attention
Ye Xia, Jinkyu Kim, John Canny +2
Inspired by human vision, we propose a new periphery-fovea multi-resolution driving model that predicts vehicle speed from dash camera videos. The peripheral vision module of the m…
Learning Robust Dialog Policies in Noisy Environments
Maryam Fazel-Zarandi, Shang-Wen Li, Jin Cao +4
Modern virtual personal assistants provide a convenient interface for completing daily tasks via voice commands. An important consideration for these assistants is the ability to r…