From the 1 of 5.5k papers with an AI index.
29.3k citations
- Centre National de la Recherche ScientifiqueFR1.7k papers
- Centre Inria de SaclayFR364 papers
- École PolytechniqueFR306 papers
- Laboratoire Lorrain de Recherche en Informatique et ses ApplicationsFR300 papers
- École Normale Supérieure - PSLFR292 papers
- Sorbonne UniversitéFR291 papers
- École Normale Supérieure de LyonFR233 papers
- Centre Inria de l'Université Grenoble AlpesFR216 papers
- Université Paris-SaclayFR208 papers
- Université Grenoble AlpesFR204 papers
- Lyon 1 UniversitéFR191 papers
- Centre Inria d'Université Côte d'AzurFR183 papers
7 papers · 2 filters
Describing Textures in the Wild
Mircea Cimpoi, Subhransu Maji, Iasonas Kokkinos +2
Patterns and textures are defining characteristics of many natural objects: a shirt can be striped, the wings of a butterfly can be veined, and the skin of an animal can be scaly.…
Second order scattering descriptors predict fMRI activity due to visual textures
Michael Eickenberg, Fabian Pedregosa, Senoussi Mehdi +2
Second layer scattering descriptors are known to provide good classification performance on natural quasi-stationary processes such as visual textures due to their sensitivity to h…
Discriminative Parameter Estimation for Random Walks Segmentation
Pierre-Yves Baudin, Danny Goodman, Puneet Kumar +4
The Random Walks (RW) algorithm is one of the most e - cient and easy-to-use probabilistic segmentation methods. By combining contrast terms with prior terms, it provides accurate…
Regularized Spherical Polar Fourier Diffusion MRI with Optimal Dictionary Learning
Jian Cheng, Tianzi Jiang, Rachid Deriche +2
Compressed Sensing (CS) takes advantage of signal sparsity or compressibility and allows superb signal reconstruction from relatively few measurements. Based on CS theory, a suitab…
Discriminative Parameter Estimation for Random Walks Segmentation: Technical Report
Pierre-Yves Baudin, Danny Goodman, Puneet Kumar +4
The Random Walks (RW) algorithm is one of the most e - cient and easy-to-use probabilistic segmentation methods. By combining contrast terms with prior terms, it provides accurate…
Automatic Parameter Adaptation for Multi-object Tracking
Duc Phu Chau, Monique Thonnat, François Bremond
Object tracking quality usually depends on video context (e.g. object occlusion level, object density). In order to decrease this dependency, this paper presents a learning approac…