3k citations
- Max Planck SocietyDE367 papers
- University of StuttgartDE363 papers
- ETH ZurichCH78 papers
- University of TübingenDE76 papers
- Centre National de la Recherche ScientifiqueFR63 papers
- Polish Academy of SciencesPL41 papers
- Heidelberg UniversityDE38 papers
- Institute of Physical ChemistryPL33 papers
- Max Planck Institute for Biological CyberneticsDE30 papers
- Paul Scherrer InstituteCH30 papers
- University of CambridgeGB30 papers
- Johannes Gutenberg University MainzDE29 papers
87 papers · 1 filter
Nematic liquid crystal boojums with handles on colloidal handlebodies
Qingkun Liu, Bohdan Senyuk, Mykola Tasinkevych +1
Topological defects that form on surfaces of ordered media, dubbed boojums, are ubiquitous in superfluids, liquid crystals (LCs), Langmuir monolayers, and Bose-Einstein condensates…
Colloidal spirals in nematic liquid crystals
Bohdan Senyuk, Manoj B. Pandey, Qingkun Liu +2
One of the central experimental efforts in nematic colloids research aims to explore how the interplay between the geometry of particles along with the accompanying nematic directo…
Video Propagation Networks
Varun Jampani, Raghudeep Gadde, Peter V. Gehler
We propose a technique that propagates information forward through video data. The method is conceptually simple and can be applied to tasks that require the propagation of structu…
Coupling Adaptive Batch Sizes with Learning Rates
Lukas Balles, Javier Romero, Philipp Hennig
Mini-batch stochastic gradient descent and variants thereof have become standard for large-scale empirical risk minimization like the training of neural networks. These methods are…
Reflectance Adaptive Filtering Improves Intrinsic Image Estimation
Thomas Nestmeyer, Peter V. Gehler
Separating an image into reflectance and shading layers poses a challenge for learning approaches because no large corpus of precise and realistic ground truth decompositions exist…
ArtTrack: Articulated Multi-person Tracking in the Wild
Eldar Insafutdinov, Mykhaylo Andriluka, Leonid Pishchulin +4
In this paper we propose an approach for articulated tracking of multiple people in unconstrained videos. Our starting point is a model that resembles existing architectures for si…