Go Back

Photo of Josef Sivic

Josef Sivic Computer scientist

Josef Sivic’s research is in computer vision – a field of computer science and engineering that aims to automatically extract information from images and videos. He develops learnable image representations for automatic visual search and recognition applied to large image and video collections.


ERC Starting Grant, 2013.

Sullivan Doctoral Thesis Prize, British Machine Vision Association, 2007.

Relevant Publications

M. Oquab et al, “Learning and Transferring Mid-Level Image Representations using Convolutional Neural Networks,” IEEE Conference on Computer Vision and Pattern Recognition, 2014.

M. Oquab et al, “Is object localization for free? – Weakly-supervised learning with convolutional neural networks,” IEEE Conference on Computer Vision and Pattern Recognition, 2015.

J. Sivic and A. Zisserman, "Video Google: A text retrieval approach to object matching in videos," Computer Vision, 2003. Proceedings Ninth IEEE International Conference on Computer Vision, vol. 2, pp. 1470-1744, Oct. 2003.



Senior Fellow Learning in Machines & Brains


InriaÉcole normale supérieure


PhD (Engineering Science) University of Oxford

MSc (Electrical Engineering) Czech Technical University in Prague



No Assets Found

Sorry, we did not find any assets matching these filters.