Hello! I am a PhD student at the University of Maryland. My research areas are Computer Vision and Machine Learning. I was previously funded by the NDSEG Graduate Fellowship.
Email  |  Google Scholar  |  Twitter  |  Github
We find that the sensitivity of a Gaussian to the L2 loss across the scene -- captured as as a second order approximation -- is a surprisingly effective pruning score.
Training on some skewed race distributions of a popular training dataset to mitigate racial bias produces more equitable models.
Spreading out feature embeddings via SVD improves image retreival and mitigates model collapse.
Two new architectures for detecting violence in videos from differnt violence domains.
Reconstruct multi-view depth maps from a single RGB or depth image source.
Image classification by predicting where to look next in an image.
I enjoy doing puzzles in my free time, including escape room / puzzle hunt type puzzles, and have even written a few:
Harry Potter and The Giver.