Viktoriia Sharmanska

You will be redirected to my new home page shortly

 

IST Austria

PhD Student
Lampert Group
firstname.lastname (at) ist.ac.at



About Me

I am often asked why I have two i's in my name. Ironically, i's is spelled in the same way as "two eyes":) I was born in Ukraine, and this is the way my name (which essentially should be Victoria) was translated from cyrillic to latin. This question always makes me smile :)
I got my Masters degree in Applied Mathematics at Kiev National University, Ukraine, and now I am doing my PhD in Computer Vision at IST Austria in Vienna, Austria. I am working with Christoph Lampert at Computer Vision and Machine Learning Group, and I closely collaborate with Novi Quadrianto at the SMiLe CLiNiC, University of Sussex.
I am particularly interested in designing a computer vision system that can learn new objects and object categories just as humans do. Currently I am actively involved in learning efficient and discriminative image representations. My data consist of images and videos of a variety of different objects, e.g. existing available databases, or data from the Web. The topic of my thesis is Learning with attributes for object recognition: parametric and non-parametric views.

Publications

Anastasia Pentina, Viktoriia Sharmanska, Christoph H. Lampert.
Curriculum Learning of Multiple Tasks. IEEE Conference on Computer Vision and Pattern Recognition CVPR, Boston, USA, 2015.
[PDF] [Supplementary] [Poster]

Daniel Hernandez-Lobato, Viktoriia Sharmanska, Kristian Kersting, Christoph H. Lampert, Novi Quadrianto.
Mind the Nuisance: Gaussian Process Classification using Privileged Noise. Conference on Neural Information Processing Systems NIPS, Montreal, Canada, 2014.
[PDF] [Poster]

Viktoriia Sharmanska, Novi Quadrianto, Christoph H. Lampert.
Learning to Rank Using Privileged Information. International Conference on Computer Vision ICCV, Sydney, Australia, 2013.
[PDF] [Supplementary] [Bibtex] [Poster]

Viktoriia Sharmanska, Novi Quadrianto, Christoph H. Lampert.
Learning to Transfer Privileged Information. Under journal review.
[arXiv] [Data Annotation] [Bibtex]

Novi Quadrianto, Viktoriia Sharmanska, David A. Knowles, Zoubin Ghahramani.
The Supervised IBP: Neighbourhood Preserving Infinite Latent Feature Models. Conference on Uncertainty in Artificial Intelligence UAI, Bellevue, Washington, USA, 2013.
[PDF] [Bibtex] [Poster]

Viktoriia Sharmanska, Novi Quadrianto, Christoph H. Lampert.
Augmented Attribute Representations. European Conference on Computer Vision ECCV, Firenze, Italy, 2012.
[PDF] [Bibtex] [Poster]