Zobrazeno 1 - 10
of 307
pro vyhledávání: '"Poklukar, A."'
A $k$-rainbow dominating function ($k$RDF) of $G$ is a function that assigns subsets of $ \{1,2,...,k\}$ to the vertices of $G$ such that for vertices $v$ with $f(v)=\emptyset $ we have $\bigcup\nolimits_{u\in N(v)}f(u)=\{1,2,...,k\}$. The weight $w(
Externí odkaz:
http://arxiv.org/abs/2409.18510
Autor:
Medbouhi, Aniss Aiman, Marchetti, Giovanni Luca, Polianskii, Vladislav, Kravberg, Alexander, Poklukar, Petra, Varava, Anastasia, Kragic, Danica
Hyperbolic machine learning is an emerging field aimed at representing data with a hierarchical structure. However, there is a lack of tools for evaluation and analysis of the resulting hyperbolic data representations. To this end, we propose Hyperbo
Externí odkaz:
http://arxiv.org/abs/2404.08608
Autor:
Kar, Oğuzhan Fatih, Tonioni, Alessio, Poklukar, Petra, Kulshrestha, Achin, Zamir, Amir, Tombari, Federico
Vision-language models (VLMs) are typically composed of a vision encoder, e.g. CLIP, and a language model (LM) that interprets the encoded features to solve downstream tasks. Despite remarkable progress, VLMs are subject to several shortcomings due t
Externí odkaz:
http://arxiv.org/abs/2404.07204
Autor:
Škrlep, Martin1 (AUTHOR) martin.skrlep@kis.si, Poklukar, Klavdija1 (AUTHOR) klavdija.poklukar@kis.si, Vrecl, Milka2 (AUTHOR) milka.vrecl@vf.uni-lj.si, Brankovič, Jana2 (AUTHOR) jana.brankovic@vf.uni-lj.si, Čandek-Potokar, Marjeta1,3 (AUTHOR) meta.candek-potokar@kis.si
Publikováno v:
Animals (2076-2615). Nov2024, Vol. 14 Issue 22, p3331. 19p.
Autor:
Klavdija Poklukar, Anja Erbežnik, Gregor Fazarinc, Kevin Kress, Nina Batorek-Lukač, Martin Škrlep, Volker Stefanski, Marjeta Čandek-Potokar, Milka Vrecl
Publikováno v:
Veterinary and Animal Science, Vol 25, Iss , Pp 100383- (2024)
This study examined the effects of immunocastration and surgical castration on the histomorphometric and transcriptome traits of the porcine skeletal muscle. We hypothesized that the differences in duration of androgen deprivation resulting from diff
Externí odkaz:
https://doaj.org/article/45a146b5a5bc4c8dae1259d626a0ac2b
Autor:
Ghadirzadeh, Ali, Poklukar, Petra, Arndt, Karol, Finn, Chelsea, Kyrki, Ville, Kragic, Danica, Björkman, Mårten
We present a data-efficient framework for solving sequential decision-making problems which exploits the combination of reinforcement learning (RL) and latent variable generative models. The framework, called GenRL, trains deep policies by introducin
Externí odkaz:
http://arxiv.org/abs/2204.08573
Visual action planning particularly excels in applications where the state of the system cannot be computed explicitly, such as manipulation of deformable objects, as it enables planning directly from raw images. Even though the field has been signif
Externí odkaz:
http://arxiv.org/abs/2203.13034
Advanced representation learning techniques require reliable and general evaluation methods. Recently, several algorithms based on the common idea of geometric and topological analysis of a manifold approximated from the learned data representations
Externí odkaz:
http://arxiv.org/abs/2202.06866
Autor:
Ceylan, Ciwan, Poklukar, Petra, Hultin, Hanna, Kravchenko, Alexander, Varava, Anastasia, Kragic, Danica
We argue that when comparing two graphs, the distribution of node structural features is more informative than global graph statistics which are often used in practice, especially to evaluate graph generative models. Thus, we present GraphDCA - a fra
Externí odkaz:
http://arxiv.org/abs/2202.03884
Learning representations of multimodal data that are both informative and robust to missing modalities at test time remains a challenging problem due to the inherent heterogeneity of data obtained from different channels. To address it, we present a
Externí odkaz:
http://arxiv.org/abs/2202.03390