no code implementations • 9 Nov 2022 • Kristian Fenech, Ádám Fodor, Sean P. Bergeron, Rachid R. Saboundji, Catharine Oertel, András Lőrincz
Using this model we analyse the estimated perceived personality traits of individuals performing tasks in small groups and dyads.
no code implementations • 5 May 2022 • Dávid Szeghy, Mahmoud Aslan, Áron Fóthi, Balázs Mészáros, Zoltán Ádám Milacski, András Lőrincz
While deep neural networks are sensitive to adversarial noise, sparse coding using the Basis Pursuit (BP) method is robust against such attacks, including its multi-layer extensions.
1 code implementation • 5 Mar 2021 • Viktor Varga, András Lőrincz
Interactive video object segmentation aims to utilize automatic methods to speed up the process and reduce the workload of the annotators.
Ranked #5 on Interactive Video Object Segmentation on DAVIS 2017
no code implementations • 18 Feb 2021 • Ellák Somfai, Benjámin Baffy, Kristian Fenech, Changlu Guo, Rita Hosszú, Dorina Korózs, Fabrizio Nunnari, Marcell Pólik, Daniel Sonntag, Attila Ulbert, András Lőrincz
Our goal is to bridge human and machine intelligence in melanoma detection.
1 code implementation • 11 Apr 2019 • Márton Véges, András Lőrincz
Unlike previous methods, our network works in a single step without any post-processing.
Ranked #1 on 3D Multi-Person Pose Estimation (absolute) on MuPoTS-3D (MPJPE metric)
1 code implementation • 19 Sep 2018 • Márton Véges, Viktor Varga, András Lőrincz
In monocular 3D human pose estimation a common setup is to first detect 2D positions and then lift the detection into 3D coordinates.
Ranked #250 on 3D Human Pose Estimation on Human3.6M
1 code implementation • 5 Sep 2017 • Daniel Sonntag, Michael Barz, Jan Zacharias, Sven Stauden, Vahid Rahmani, Áron Fóthi, András Lőrincz
Fine-tuning of a deep convolutional neural network (CNN) is often desired.
no code implementations • 2 Dec 2016 • András Lőrincz, Máté Csákvári, Áron Fóthi, Zoltán Ádám Milacski, András Sárkány, Zoltán Tősér
The success is mostly due to advances in deep learning.