Filtrer vos résultats
- 46
- 9
- 24
- 19
- 8
- 3
- 1
- 1
- 35
- 34
- 6
- 5
- 2
- 1
- 2
- 2
- 4
- 1
- 4
- 2
- 2
- 2
- 3
- 2
- 5
- 2
- 5
- 6
- 5
- 4
- 3
- 1
- 48
- 7
- 39
- 17
- 12
- 6
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 55
- 18
- 9
- 4
- 4
- 4
- 4
- 4
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
55 résultats
|
|
triés par
|
|
Une méthode de réduction exacte pour la segmentation par graph cuts2011
Pré-publication, Document de travail
hal-00558895v2
|
||
|
A Non-Heuristic Reduction Method For Graph Cut Optimization2012
Rapport
hal-00692464v3
|
||
|
Spatially Varying Blur Recovery - Diagonal Approximations in the Wavelet DomainInternational Conference on Pattern Recognition Applications and Methods, Feb 2013, Barcelona, France. pp.222-228, ⟨10.5220/0004308202220228⟩
Communication dans un congrès
hal-02996809v1
|
||
|
On the identifiability and stable recovery of deep/multi-layer structured matrix factorizationInformation Theory Workshop, 2016, Cambridge, United Kingdom
Communication dans un congrès
hal-01287708v1
|
||
|
Existence, Stability and Scalability of Orthogonal Convolutional Neural NetworksJournal of Machine Learning Research, 2022, 23 (347), pp.1--56
Article dans une revue
hal-03315801v3
|
||
|
Non-heuristic reduction of the graph in graph-cut optimizationNCMIP, 2012, Cachan, France. pp.012002
Communication dans un congrès
hal-00670091v1
|
||
|
Average performance of the sparsest approximation in a dictionarySPARS'09 - Signal Processing with Adaptive Sparse Structured Representations, Inria Rennes - Bretagne Atlantique, Apr 2009, Saint Malo, France
Communication dans un congrès
inria-00369478v1
|
||
Réduction de graphes et flot maximum pour la segmentation et le débruitage d'imagesROADEF'2011: 12ème congrès de la Société Française de Recherche Opérationnelle et d'Aide à la Décision, Mar 2011, Saint-Etienne, France
Communication dans un congrès
hal-00596011v1
|
|||
|
Numerical study of an optimization problem for mosaic active imaging2014 IEEE International Conference on Image Processing (ICIP), Oct 2014, Paris, France. pp.1723-1727, ⟨10.1109/ICIP.2014.7025345⟩
Communication dans un congrès
hal-00935725v3
|
||
|
Stable recovery of the factors from a deep matrix product Signal Processing with Adaptive Sparse Structured Representations (SPARS) , 2017, Lisbonne, Portugal
Communication dans un congrès
hal-01417943v2
|
||
|
Bayesian image restoration for mosaic active imagingInverse Problems and Imaging , 2014, 8 (3), pp.733-760
Article dans une revue
hal-00758753v3
|
||
|
Local Identifiability of Deep ReLU Neural Networks: the TheoryAdvances in Neural Information Processing Systems, Nov 2022, New Orleans, United States
Communication dans un congrès
hal-03687395v2
|
||
|
Direct physical modelling and scene reconstruction in order to assess the performance from a new concept of active imaging: Mosaic active imaging system10th International IR Target and background modeling & simulation workshop, 2014, Ettlingen, Germany
Communication dans un congrès
hal-01486854v1
|
||
|
Simultaneous Segmentation and Filtering via Reduced Graph CutsACIVS, 2012, Brno, Czech Republic. pp.201 - 212, ⟨10.1007/978-3-642-33140-4_18⟩
Communication dans un congrès
hal-01486861v1
|
||
|
A Reduction Method For Graph Cut OptimizationPattern Analysis and Applications, 2014, 17 (2), pp.361-378. ⟨10.1007/s10044-013-0337-7⟩
Article dans une revue
hal-01486804v5
|
||
|
Geometry-induced Implicit Regularization in Deep ReLU Neural Networks2024
Pré-publication, Document de travail
hal-04452356v1
|
||
|
Semi-automatic segmentation of whole-body images in longitudinal studiesBiomedical Physics & Engineering Express, 2020, 7, pp.015014. ⟨10.1088/2057-1976/abce16⟩
Article dans une revue
hal-03234347v1
|
||
Regularized Multi-Label Fast Marching and Application to Whole-Body Image SegmentationIEEE International Symposium on Biomedical Imaging (ISBI'18), Apr 2018, Washington DC, United States
Communication dans un congrès
hal-01702039v1
|
|||
|
Convolutional Trees for Fast Transform LearningSPARS, 2015, Cambridge, United Kingdom
Communication dans un congrès
hal-01486832v1
|
||
|
On the stable recovery of deep structured linear networks under sparsity constraintsMathematical and Scientific Machine Learning, Jul 2020, Princeton, United States
Communication dans un congrès
hal-01526083v3
|
||
|
Matching Pursuit Shrinkage in Hilbert SpacesSignal Processing, 2011, 91 (12), pp.2754-2766. ⟨10.1016/j.sigpro.2011.04.010⟩
Article dans une revue
hal-00638380v1
|
||
|
Reduced graphs for min-cut/max-flow approaches in image segmentationLAGOS'11 : VI Latin-American Algorithms, Graphs, and Optimization Symposium, Mar 2011, Bariloche, Argentina. 6 p
Communication dans un congrès
hal-00596000v1
|
||
|
Loss functions for denoising compressed images: a comparative studyEUSIPCO, Sep 2019, Coruna, Spain
Communication dans un congrès
hal-02952604v2
|
||
|
SPATIALLY VARYING BLUR RECOVERY. Diagonal Approximations in the Wavelet Domain2012
Rapport
hal-00733194v2
|
||
Learning optimal shape representations for multi-modal image registrationISBI, Apr 2020, Iowa city, United States
Communication dans un congrès
hal-02431201v1
|
|||
|
Average performance of the sparsest approximation using a general dictionaryNumerical Functional Analysis and Optimization, 2011, 32 (7), pp.768-805. ⟨10.1080/01630563.2011.580876⟩
Article dans une revue
hal-00260707v1
|
||
Report on CIMI Thematic Trimester: Machine Learning[Rapport de recherche] IRIT : Institut de Recherche en Informatique de Toulouse. 2016
Rapport
hal-03155046v1
|
|||
|
Quantized Approximately Orthogonal Recurrent Neural Networks2024
Pré-publication, Document de travail
hal-04434011v1
|
||
|
Parameter identifiability of a deep feedforward ReLU neural networkMachine Learning, 2023, 112, pp.4431-4493
Article dans une revue
hal-03501784v2
|
||
|
A Predual Proximal Point Algorithm solving a Non Negative Basis Pursuit Denoising modelInternational Journal of Computer Vision, 2009, 83 (3), pp.294-311
Article dans une revue
hal-00133050v1
|
- 1
- 2