Vasiliy Karasev

I am a staff software engineer at Waymo where I work on perception for autonomous driving.

Previously, I spent several years doing computer vision at Zoox. I did my PhD at UCLA, and was advised by Prof. Stefano Soatto. My work revolved around ''value of information'' / decision making problems, optimization, and their applications in computer vision.

During my studies I had the opportunity to visit Honda Research Institute and Samsung Display. I received my bachelors from UC Berkeley.

Publications

Misc

	Intent-Aware Long-Term Prediction of Pedestrian Motion V. Karasev, A. Ayvaci, B. Heisele, and S. Soatto ICRA, 2016 video / details / pdf / bibtex @inproceedings{karasevAHS16, author = {Karasev, V. and Ayvaci, A. and Heisele, B. and Soatto, S.}, title = {Intent-Aware Long-Term Prediction of Pedestrian Motion}, booktitle = {ICRA}, year = {2016}, month = {May} } Forecasting what pedestrians intend to do is easier if they behave rationally. We show how this assumption simplifies motion prediction in the assisted/autonomous driving setting.
	Causal video object segmentation from persistence of occlusions B. Taylor, V. Karasev, and S. Soatto CVPR, 2015 (oral) video / details / pdf / bibtex @incollection{taylorKS15, author = {Taylor, B. and Karasev, V. and Soatto, S.}, title = {Causal Video Object Segmentation from Persistence of Occlusions}, booktitle = {CVPR}, year = {2015}, month = {June} } We show how to exploit occlusions to discover salient objects in video.
	Active frame, location, and detector selection for automated and manual video annotation V. Karasev, A. Ravichandran, and S. Soatto CVPR, 2014 video / details / pdf / bibtex @inproceedings{karasevRS14, author = {Karasev, V. and Ravichandran, A. and Soatto, S.}, title = {Active Frame, Location, and Detector Selection for Automated and Manual Video Annotation}, booktitle = {CVPR}, year = {2014}, month = {June} } How to choose where and which detectors to run (or m-turks to query), if we can run only a few of them? We answer this question using the ‘‘information gathering’’ framework, and show results on semantic video segmentation.
	Controlled recognition bounds for visual learning and exploration V. Karasev, A. Chiuso, and S. Soatto NIPS, 2012 pdf / bibtex @incollection{karasevCS12, author = {Karasev, V. and Chiuso, A. and Soatto, S.}, title = {Controlled Recognition Bounds for Visual Learning and Exploration}, booktitle = {NIPS}, year = {2012}, month = {December} } We show how to (greedily) search for an unknown object, under occlusions, quantization-scale, and uncertain measurements.
	Temporal presentation protocols in stereoscopic displays: flicker visibility, perceived motion, and perceived depth D. Hoffman, V. Karasev, and M. Banks Journal of the Society for Information Display, 2011 pdf / bibtex @incollection{hoffmanKB11, author = {Hoffman, D. and Karasev, V. and Banks, M.}, title = {Temporal presentation protocols in stereoscopic displays: flicker visibility, perceived motion, and perceived depth}, booktitle = {Journal of the Society for Information Display}, year = {2011} } We studied how different 3D display presentation methods affect flicker, motion artifacts, and errors in perceived depth.
	High resolution fMRI using compressed sensing 2011 details / pdf This was my MS project. Compressed sensing in dynamic MRI is normally used to improve temporal resolution. Here we used it to improve spatial resolution. Reconstruction used the simplest possible TV regularization.