Presenting two conference papers, co-organizing two workshops, and presenting seven workshop papers at CVPR 2025. One paper titled 'UWAV: Uncertainty-weighted Weakly-supervised Audio-Visual Video Parsing' proposes a novel, uncertainty-aware algorithm that achieves state-of-the-art performance in audio-visual video parsing. Another paper titled 'TailedCore: Few-Shot Sampling for Unsupervised Long-Tail Noisy Anomaly Detection' introduces TailSampler to estimate class sizes and develops TailedCore, a memory-based model.
Research Experience
Currently a Senior Principal Research Scientist at Mitsubishi Electric Research Laboratories, with research areas spanning machine learning, artificial intelligence, signal processing, communications, optimization, information security, electronic and photonic devices, multi-physical modeling, computer vision, computational sensing, electric systems, robotics, applied physics, and human-computer interaction.
Education
Ph.D., Boston University, 2011
Background
Research interests include information security, biometric authentication, and data privacy. Was a member of the Information Systems and Sciences Laboratory at Boston University, where he studied information-theoretically secure multiparty computation.