Research

Our publications database  contains scientific papers and technical reports written by our scientists for over the last two decades.

If the document you are looking for cannot be downloaded in PDF or Postscript format, please contact us specifying the title, author(s) and reference. Any document downloaded from this database may be used for non-commercial purposes only.

LABS publications (Korean website, publications in English)

Capturing the Geometry of Object Categories from Video Supervision​
David Novotny, Diane Larlus, Andrea Vedaldi

Pattern Analysis and Machine Intelligence

Semi-convolutional Operators for Instance Segmentation
David Novotny, Samuel Albanie, Diane Larlus, Andrea Vedaldi

ECCV, Munich, Germany, 08 - 14 September 2018

Self-supervised Learning of Geometrically Stable Features Through Probabilistic Introspection
David Novotny, Samuel Albanie, Diane Larlus, Andrea Vedaldi

CVPR 2018, Salt Lake City, USA, 18 - 22 June 2018

Learning 3D Object Categories by Looking Around Them
David Novotny, Diane Larlus, Andrea Vedaldi

International Conference on Computer Vision, Venice, Italy, 22 - 29 October 2017

AnchorNet: A Weakly Supervised Network to Learn Geometry-sensitive Features For Semantic Matching
David Novotny, Diane Larlus, Andrea Vedaldi

CVPR 17, Honolulu, US, 22 - 25 July 2017

Learning the semantic structure of objects from Web supervision
David Novotny, Diane Larlus, Andrea Vedaldi

ECCV Workshops, Amsterdam, The Netherlands, October 11-14, 2016.

Deep Image Retrieval: Learning Global Representations for Image Search
Albert Gordo, Jon Almazan, Jérôme Revaud, Diane Larlus

ECCV, Amsterdam, The Netherlands, October 11-14, 2016.

I Have Seen Enough: Transferring Parts Across Categories
David Novotny, Diane Larlus, Andrea Vedaldi

BMVC, York, UK, 19-22 September, 2016.

Data-Driven Detection of Prominent Objects
José A. Rodriguez, Diane Larlus, Zhenwen Dai

Published on IEEE Transactions on Pattern Analysis and Machine Intelligence.
Full paper available on IEEE Xplore digital library: http://www.ieeeexplore.ws