<-- Icons -->
  • People
  • Research
  • Projects
  • Publications
  • Resources
ViCoS Lab

Jer Pelhan, MSc

Researcher, teaching assistant
  jer.pelhan@fri.uni-lj.si

About

I am a teaching assistant and a researcher at the Visual Cognitive Systems Lab, part of the University of Ljubljana, Faculty of Computer and Information Science. My research, supervised by Prof. Matej Kristan, PhD, is focused on object counting and detection using few-shot learning approaches.

I have a diverse range of research interest, such as object detection, object counting, semantic segmentation, few-shot learning, visual object tracking, and the broader domains of computer vision and deep learning.

I am engaged in both research and industry projects, where I apply computer vision and deep learning techniques to address real-world problems, applications, and diverse challenges.


Research

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).

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.

Awards

  • 2025: Faculty Research Award for PhD Students (UL-FRI)
  • 2025: Outstanding reviewer award at ICCV2025 (~3% among ~1k reviewers)
  • 2024: University Prešeren award from UNI-LJ for masters thesis
  • 2024 Excellent research achievements in 2024 award by the Slovenian Research Agency for our work on few-shot counting ARIS.
  • 2024 received Uroš Seljak award for best student research paper at UL (DAVE paper).
  • 2023 Best paper award at ERK 2023 Pattern recognition section
  • 2023 Dean award for Student academic excellence

Teaching

I am actively involved in teaching at the University of Ljubljana, Faculty of Computer and Information Science as a teaching assistant at:

  • Machine Perception (Umetno zaznavanje) – ongoing
  • Multimedia Systems (Multimedijski sistemi) – 2023–2024
  • Advanced Computer Vision Methods (Napredne metode računalniškega vida) – 2022–2023

Publications

First author of papers published at CVPR, NeurIPS, AAAI, serving reviewer for CVPR, NeurIPS, WACV, ICCV, AAAI. Full list of publications is available at Google Scholar page.

  •  
    A Detect-and-Verify Paradigm for Low-Shot Counting - DAVE
    Jer Pelhan, Alan Lukežič, Vitjan Zavrtanik and Matej Kristan
    IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2024
  •  
    A Novel Unified Architecture for Low-Shot Counting by Detection and Segmentation
    Jer Pelhan, Alan Lukežič, Vitjan Zavrtanik and Matej Kristan
    The Thirty-Eighth Annual Conference on Neural Information Processing Systems, NeurIPS2024, 2024
  • Guided Video Object Segmentation by Tracking
    Jer Pelhan, Matej Kristan, Alan Lukežič, Jiri Matas and Luka Čehovin Zajc
    Elektrotehniški vestnik, Journal of Electrical Engineering and Computer Science, 2023
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