Research
I am interested in Human Poses and Behavioral Analysis using interaction between different modalities. Human behavior understanding can be improved using different modalities. For instance, can we generate text instructions to correct incorrectly performed movements, such as sport performance? These research questions connect prior behavioral studies with applications.
|
|
Day-Night-Transfomation-for-improving-feature-matching
Computer Vision Project [Github]
We transformed illumination of day-night image pairs using CycleGAN to improve feature matching.
|
|
Super-Resolution on Computer Texts
Undergraduate Research Opportunity Program, Supervised by Prof. Qifeng Chen
[Github]
We designed two-stream model to simultaneuously improve text boundary clarity and colors on text images.
|
Feel free to use this website's source code. Do not scrape the HTML from this page itself, as it includes analytics tags that you do not want on your own website — use the github code instead. Also, consider using Leonid Keselman's Jekyll fork of this page.
|
|