Rate My Professor Hamid Rezatofighi

Rezatofighi's research specializes in computer vision, robot vision, robot perception, robotics, deep learning, and machine learning. His work emphasizes vision-based perception for autonomous robots in human environments, encompassing object and person detection, multiple object tracking, social trajectory forecasting, social activity and human pose prediction, and autonomous social robot planning. He possesses expertise in Bayesian filtering, estimation, and learning via point processes and finite set statistics, and pioneers set learning with deep neural networks. With over 100 publications garnering more than 19,500 citations—including 15 papers cited over 100 times and three exceeding 1,000 citations—his contributions feature in premier venues such as CVPR, ECCV, ICCV, NeurIPS, AAAI, IJCAI, ICRA, and IROS. Key recent works include 'Acoustic-to-hyper-spectral: real-time perimeter intrusion detection system monitoring through learnable filters and hyper-spectral image generation from distributed acoustic sensing systems' (Optics Express, 2025), 'Diffusion Model for Robust Multi-sensor Fusion in 3D Object Detection and BEV Segmentation' (ECCV 2024), and 'DrVideo: Document Retrieval Based Long Video Understanding' (CVPR 2025). He serves as Senior Associate Editor for IEEE Transactions on Image Processing and Associate Editor for Artificial Intelligence Journal since 2020, and as area chair for major conferences since 2020. Rezatofighi has attracted over $17 million in research funding since 2020, including as Lead PI on a DARPA project and co-PI on two others, plus lead CI for an ARC Discovery Project.