no code implementations • 12 Apr 2024 • Patrik Vacek, David Hurych, Tomáš Svoboda, Karel Zimmermann
We identified the structural constraints and the use of large and strict rigid clusters as the main pitfall of the current approaches and we propose a novel clustering approach that allows for combination of overlapping soft clusters as well as non-overlapping rigid clusters representation.
no code implementations • 28 Nov 2023 • Tomáš Svoboda, Tomáš Raček, Josef Handl, Jozef Sabo, Adrián Rošinec, Łukasz Opioła, Wojciech Jesionek, Milan Ešner, Markéta Pernisová, Natallia Madzia Valasevich, Aleš Křenek, Radka Svobodová
The solutions mainly fall into one of the two groups: general data management systems (e. g. Onedata, iRODS, B2SHARE, CERNBox) or very specialised data management solutions (e. g. solutions for biomolecular simulation data, biological imaging data, genomic data).
1 code implementation • 15 Sep 2023 • Awet Haileslassie Gebrehiwot, David Hurych, Karel Zimmermann, Patrick Pérez, Tomáš Svoboda
Deep perception models have to reliably cope with an open-world setting of domain shifts induced by different geographic regions, sensor properties, mounting positions, and several other reasons.
1 code implementation • 13 Jul 2022 • Awet Haileslassie Gebrehiwot, Patrik Vacek, David Hurych, Karel Zimmermann, Patrick Perez, Tomáš Svoboda
We propose to leverage sequences of point clouds to boost the pseudolabeling technique in a teacher-student setup via training multiple teachers, each with access to different temporal information.
1 code implementation • 15 Jun 2022 • Petr Šebek, Šimon Pokorný, Patrik Vacek, Tomáš Svoboda
Object detection and semantic segmentation with the 3D lidar point cloud data require expensive annotation.
no code implementations • 8 Dec 2016 • Martin Pecka, Karel Zimmermann, Michal Reinštein, Tomáš Svoboda
Mobile robots with complex morphology are essential for traversing rough terrains in Urban Search & Rescue missions (USAR).