Cheng-Yen Hsieh is a student at Master of Science in Computer Vision (MSCV), Carnegie Mellon University (CMU) advised by Prof. Deva Ramanan. His research interests focus on Computer Vision and Machine Learning, including topics ranging from self-supervised representation learning, federated learning, segmentation, and object tracking.
Develop amodal detection & tracking methods;
Implementation of segmentation, detection, and tracking;
Idea discussion and experiments design;
Experiments on TAO-Amodal Dataset;
I am a Ph.D. student at The Robotics Institute, Carnegie Mellon University advised by Prof. Deva Ramanan. My research focus is broadly on spatiotemporal 3D scene understanding. Previously, during my Masters at CMU RI, I worked on estimating and exploiting 3D scene geometry from single images, to reason about occlusions and densify sparse depth input.