no code implementations • 2 Feb 2024 • Aleksandar Armacki, Dragana Bajović, Dušan Jakovetić, Soummya Kar
The proposed family, termed Distributed Gradient Clustering (DGC-$\mathcal{F}_\rho$), is parametrized by $\rho \geq 1$, controling the proximity of users' center estimates, with $\mathcal{F}$ determining the clustering loss.
no code implementations • 11 Mar 2023 • Stevo Racković, Cláudia Soares, Dušan Jakovetić
The method applies to an arbitrary clustering of the face.
no code implementations • 9 Feb 2023 • Stevo Racković, Cláudia Soares, Dušan Jakovetić, Zoranka Desnica
We propose a method to fit arbitrarily accurate blendshape rig models by solving the inverse rig problem in realistic human face animation.
no code implementations • 5 Oct 2021 • Stevo Racković, Cláudia Soares, Dušan Jakovetić, Zoranka Desnica, Relja Ljubobratović
We present a novel approach for learning the inverse rig parameters at increased accuracy and decreased computational cost at the same time.
no code implementations • 25 Feb 2021 • Miloš Savić, Jasna Atanasijević, Dušan Jakovetić, Nataša Krejić
In contrast to previous methods proposed in the literature, the HUNOD method combines two outlier detection approaches based on two different machine learning designs (i. e, clustering and representational learning) to detect and internally validate outliers in a given tax dataset.