Broadly, my research interests lie in computer vision and machine learning. My academic research addresses robustness of deep neural networks against adversarial examples and adversarial or random bit errors in (quantized) weights. Previously, I worked on weakly-supervised 3D reconstruction and superpixel segmentation. In industry, I worked on various computer vision problems including line segment/kaypoint tracking and pedestrian detection. Generally, I am interested in trustworthy machine learning and deep learning for (3D) computer vision applications.