I am a PhD student at the Computer Science Department of Northwestern University. My research at HABits Lab is focused on developing efficient methods for vision-based hand-related activity recognition using wearable devices and machine-learning. Recently, I interned at Apple where I worked on multiple machine-learning projects using different sensing technologies. You can find my resume here.
My research is situated at the intersection of human activity sensing and machine learning, with a specific focus on hand-related activities in health and human-computer interaction (HCI) contexts. I have developed techniques to enhance privacy and efficiency in detecting hand-related activities. More recently, I have investigated data-efficient methods for recognizing hand gestures.
A wearable necklace with a deep-learning data analysis pipeline that automatically detects smoking and extracts smoking topography. SmokeMon has received worldwide attention from news media outlets including BBC, WebMD, Fox News, DigitalTrends, NPR. [https://dl.acm.org/doi/abs/10.1145/3569460]
Work done during internship at Apple. We employ transformers and meta-learning techniques to address few-shot learning challenges. Unlike prior work, our method supports any combination of one-handed, two-handed, static, and dynamic gestures, including different viewpoints, and the ability to handle irrelevant hand movements. [https://dl.acm.org/doi/abs/10.1145/3654777.3676378]