• People
  • Research
  • Projects
  • Publications
  • Resources
ViCoS Lab

Josip Šarić

Researcher
josip.saric@fri.uni-lj.si

About me

I am a postdoctoral researcher supervised by prof. Matej Kristan and supported by the SMASH postdoctoral program. Prior to this, I completed my PhD and two-year postdoc at the Faculty of Electrical Engineering and Computing, University of Zagreb, where I was part of prof. Siniša Šegvić research group.

My research interests focus on computer vision and deep learning, with a particular emphasis on topics such as panoptic segmentation, open-vocabulary recognition, label-efficient learning, and related areas.

Publications

This is a list of my publications, which you can also find on google scholar.

  • MC-PanDA: Mask Confidence for Panoptic Domain Adaptation. Ivan Martinović, Josip Šarić, Siniša Šegvić. ECCV 2024.
  • Weakly Supervised Training of Universal Visual Concepts for Multi-domain Semantic Segmentation. Petra Bevandić, Marin Oršić, Josip Šarić, Ivan Grubišić, Siniša Šegvić. IJCV 2024.
  • Panoptic SwiftNet: Pyramidal Fusion for Real-Time Panoptic Segmentation. Josip Šarić, Marin Oršić, Siniša Šegvić. Remote Sensing 2023.
  • On Advantages of Mask-Level Recognition for Outlier-Aware Segmentation. Matej Grcić, Josip Šarić, Siniša Šegvić. CVPRW (VAND) 2023.
  • Dense Semantic Forecasting with Multi-Level Feature Warping. Iva Sović, Josip Šarić, Siniša Šegvić. Applied Sciences 2022.
  • Multi-Domain Semantic Segmentation With Overlapping Labels. Petra Bevandić, Marin Oršić, Ivan Grubišić, Josip Šarić, Siniša Šegvić. WACV 2022.
  • Dense Semantic Forecasting in Video by Joint Regression of Features and Feature Motion. Josip Šarić, Sacha Vražić, Siniša Šegvić. IEEE TNNLS 2021.
  • Multimodal Semantic Forecasting Based on Conditional Generation of Future Features. Kristijan Fugošić, Josip Šarić, Siniša Šegvić. GCPR 2020.
  • Warp to the Future: Joint Forecasting of Features and Feature Motion. Josip Šarić, Marin Oršić, Tonći Antunović, Sacha Vražić, Siniša Šegvić. CVPR 2020.
  • Single Level Feature-to-Feature Forecasting with Deformable Convolutions. Josip Šarić, Marin Oršić, Tonći Antunović, Sacha Vražić, Siniša Šegvić. GCPR 2019.
Faculty of Computer and Information Science

Visual Cognitive Systems Laboratory

University of Ljubljana

Faculty of Computer and Information Science

Večna pot 113
SI-1000 Ljubljana
Slovenia
Tel.: +386 1 479 8245