About

I received my PhD degree at the Faculty of Computer and Information Science, University of Ljubljana in 2021 under the supervision of prof. Matej Kristan, PhD.

My research interests are visual object tracking, video object segmentation, deep learning, pattern recognition and machine learning. In the past I was working on the industrial project for surface quality inspection.

I am a teaching assistant at the Advanced Computer Vision Methods course.

Google Scholar | GitHub

Research

Discriminative correlation filter tracking

We explore online learning of target visual models via discriminative correlation filters. The research spans hand-crafted features and optimization techniques for CPU-based tracking as well as deep learning variants with discriminative feature adaptation and online segmentation.

Tracking transparent objects

We develop new algorithms for tracking transparent objects like glasses, cups or jars.

Visual object tracking performance evaluation

One of the problems of visual tracking evaluation is a lack of a consistent evaluation methodology. This is hampering the cross-paper tracker comparison and faster advancement of the field. In our research we investigate different aspects of tracking evaluation. A continuous effort that is a part of our work is also the Visual Object Tracking Challenge (VOT).

Apparent motion patterns

We propose to go beyond pre-recorded benchmarks with post-hoc annotations by presenting an approach that utilizes omnidirectional videos to generate realistic, consistently annotated, short-term tracking scenarios with exactly parameterized motion patterns..

Drone tracking

The tracking algorithms we developed can be applied to autonomous robots like drones. Here are some results from this research application.

Dense object counting in underwater imagery

The main goal of this research is development of computer-vision-based automated counters applicable underwater imagery. Such counters are crucial for processing extremely large datasets, vastly reducing the required manual labor and facilitating census orders of magnitude grater than what is possible with standard techniques. The methods leverage learning on specific type of images to maximize a task-specific detection performance.

Low-shot counting

The main goal of this research is development of computer-vision-based automated counters that do not require large training datasets, but are adapted to a previously unseen category by using only a few training examples (few-shot), no training examples (zero-shot) or text-based prompts (text-prompt-based).

Current projects

COMETAdvanced Computer Vision for Understanding Complex Object Motion in Dynamic Environments

January 2025 - December 2027

This project aims to develop a novel motion understanding paradigm, centered on automatically determining the minimal scene understanding required to track one or multiple objects throughout a video. It tackles three core challenges: developing a few-shot object detector capable of identifying all objects in a category based on limited examples, tracking individual objects amid distractors, and extending this to track transformable objects in complex environments.

Computer Vision

January 2019 - December 2027

Computer vision is becoming a focal problem area of artificial intelligence. On the wings of deep learning it has become very powerful tool for solving various problems involving processing of visual information. In the framework of this programme we are addressing several research questions ranging from visual tracking to visual learning for autonomous robots, with a special emphasis on going beyond supervised deep learning.

Awards

• Excellent research achievements in 2023 award by the Slovenian Research Agency for our work on few-shot counting ARIS.
• Award for excellent research achievement in 2024 at FRI-UL.
• dr. Ana Mayer Kansky University award for the Phd thesis.
• Best paper award at ERK 2023 Pattern recognition section (co-author)
• BMVC2022 best paper award for our work on transparent object tracking
• Excellent research achievements in 2021 award by the Slovenian Research Agency for our work on segmentation tracking
• Research excellence award by University of Ljubljana for our work on segmentation tracking (2022)
• Plaque of excellence for the outstanding scientific paper: Discriminative Correlation Filter Tracker with Channel and Spatial Reliability, awarded by Slovenian Pattern Recognition Society in 2021
• Golden plaque award for outstanding scientific achievements of a research group awarded by University of Ljubljana
• A special award for research work in 2020 for the publication: Performance evaluation methodology for long-term single-object tracking, published at IEEE Transactions on Cybernetics
• A special award for research work for PhD students for three conference publications in 2019:
  • CDTB: A Color and Depth Visual Object Tracking Dataset and Benchmark (ICCV)
  • FuCoLoT – A Fully-Correlational Long-Term Tracker. Asian Conference on Computer Vision (ACCV)
  • Object Tracking by Reconstruction with View-Specific Discriminative Correlation Filters (CVPR)
• A special award for research work for PhD students for the work: Discriminative Correlation Filter Tracker with Channel and Spatial Reliability, published at International Journal of Computer Vision (2018)
• A special award for research work for PhD students for the work: Deformable Parts Correlation Filters for Robust Visual Tracking, published at IEEE Transactions on Cybernetics (2017)
• Faculty’s Prešeren award for the master’s thesis (2015)
• Dean’s recognition for excellent ultimate success in completing their studies (2015)

Publications