Scholar
Stefan Stojanov
Google Scholar ID: XC_WricAAAAJ
Postdoc at Stanford Vision Lab and Neuro AI Lab
Citations & Impact
Citations
544
H-index
10
i10-index
10
Publications
20
Co-authors
10
list available
Publications
Resume (English only)
Academic Achievements
- Published multiple papers including 'Taming Generative Video Models for Zero-shot Optical Flow Extraction', 'Discovering and Using Spelke Segments', 'Self-Supervised Learning of Motion Concepts by Optimizing Counterfactuals', and more. Participated in projects like the BabyView Dataset and ZeroShape: Regression-based Zero-shot Shape Reconstruction.
Research Experience
- Currently an applied scientist at Amazon, focusing on video understanding. Previously worked in the Stanford Vision and Learning Lab and the Stanford NeuroAILab, developing video foundation models and fine-grained object representations.
Education
- Received a PhD from the Georgia Institute of Technology, advised by James Rehg; Postdoctoral researcher at Stanford University, advised by Jiajun Wu and Dan Yamins.
Background
- Research interests include computer vision and machine learning, particularly 3D vision, self-supervision, data synthesis, and video-based learning. Aims to develop systems capable of efficiently learning rich, granular representations of the physical world.
