PhD student
Member THOTH Team, INRIA Rhone-Alpes, Grenoble, France
|
INRIA Rhone-Alpes 655 Avenue de l'Europe 38330 Montbonnot France |
Phone Fax Office |
: : : : |
- - H115 firstname.lastname@inria.fr |
I am currently a PhD student under Dr. Cordelia Schmid's supervision. I'm studying applications of memory-augmented networks in computer vision and ways to mitigate catastrophic forgetting in various scenarios (for example, object detection).
Software and data
- BlitzNet: A Real-Time Deep Network for Scene Understanding
You can find the original implementation and pretrained weights by following the project web page.
Publications
-
- titre
- Adaptive Density Estimation for Generative Models
- auteur
- Thomas Lucas, Konstantin Shmelkov, Cordelia Schmid, Karteek Alahari, Jakob Verbeek
- article
- NeurIPS 2019 - Thirty-third Conference on Neural Information Processing Systems, Dec 2019, Vancouver, Canada. pp.11993-12003
- Accès au texte intégral et bibtex
-
-
- titre
- How good is my GAN?
- auteur
- Konstantin Shmelkov, Cordelia Schmid, Karteek Alahari
- article
- ECCV 2018 - European Conference on Computer Vision, Sep 2018, Munich, Germany. pp.218-234, ⟨10.1007/978-3-030-01216-8_14⟩
- Accès au texte intégral et bibtex
-
-
- titre
- BlitzNet: A Real-Time Deep Network for Scene Understanding
- auteur
- Nikita Dvornik, Konstantin Shmelkov, Julien Mairal, Cordelia Schmid
- article
- ICCV 2017 - International Conference on Computer Vision, Oct 2017, Venise, Italy. pp.4174-4182, ⟨10.1109/ICCV.2017.447⟩
- Accès au texte intégral et bibtex
-
-
- titre
- Incremental Learning of Object Detectors without Catastrophic Forgetting
- auteur
- Konstantin Shmelkov, Cordelia Schmid, Karteek Alahari
- article
- ICCV - IEEE International Conference on Computer Vision, Oct 2017, Venice, Italy. pp.3420-3429, ⟨10.1109/ICCV.2017.368⟩
- Accès au texte intégral et bibtex
-
