I am currently a first year Master student in Computer Vision (MSCV) in Robotics Institute (RI) at Carnegie Mellon University (CMU).
My research interests lie in Computer Vision and Deep Learning. Recently, I focus on the topic of object detection. Prior joining CMU, I had experiences on head pose estimation, video super resolution and approximate nearest neighbor search.
Project responsibility: RGB / thermal images fusion for object detection; domain adaptation for infrared to RGB; Experiments on FLIR dataset.
I am currently a Masters student in Computer Vision at The Robotics Institute at Carnegie Mellon University.
I am interested in object detection, image classification, medical image processing and etc,. My current focus is multi-model object detection for autonomous driving. Previously, I worked in: computer aided diabetic retinopathy diagnosis, intelligent prosthetic hand, computer aided tumor detection and identification.
I am currently a principle scientist at Argo AI and the director of the CMU Argo AI Center for Autonomous Vehicle Research.
My research focuses on computer vision, often motivated by the task of understanding people from visual data. My work tends to make heavy use of machine learning techniques, often using the human visual system as inspiration. For example, temporal processing is a key component of human perception, but is still relatively unexploited in current visual recognition systems. Machine learning from big (visual) data allows systems to learn subtle statistical regularities of the visual world. But humans have the ability to learn from very few examples.
My research interests are in the area of intelligent vehicles and autonomous driving in urban areas with an emphasis on development of a short range laser triangulation sensor and its application, and the short term prediction and analysis of future vehicle and object movements.
My research is motivated by a desire to create intelligent systems that benefit human life, primarily through sensor signals and interaction between human and machines. I focus on “open-world learning for fine-grained perception“.