activity
20222026
collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV2025

SIS-Challenge: Event-based Spatio-temporal Instance Segmentation Challenge at the CVPR 2025 Event-based Vision Workshop

Friedhelm Hamann, Emil Mededovic, Fabian Gülhan +21

We present an overview of the Spatio-temporal Instance Segmentation (SIS) challenge held in conjunction with the CVPR 2025 Event-based Vision Workshop. The task is to predict accur…

cs.CV2025

Eye on the Target: Eye Tracking Meets Rodent Tracking

Emil Mededovic, Yuli Wu, Henning Konermann +4

Analyzing animal behavior from video recordings is crucial for scientific research, yet manual annotation remains labor-intensive and prone to subjectivity. Efficient segmentation…

cs.CV2025

No Free Lunch in Annotation either: An objective evaluation of foundation models for streamlining annotation in animal tracking

Emil Mededovic, Valdy Laurentius, Yuli Wu +5

We analyze the capabilities of foundation models addressing the tedious task of generating annotations for animal tracking. Annotating a large amount of data is vital and can be a…

cs.CV2025

A Pragmatic Note on Evaluating Generative Models with Fréchet Inception Distance for Retinal Image Synthesis

Yuli Wu, Fucheng Liu, Rüveyda Yilmaz +3

Fréchet Inception Distance (FID), computed with an ImageNet pretrained Inception-v3 network, is widely used as a state-of-the-art evaluation metric for generative models. It assume…

cs.CV2024

Cascaded Diffusion Models for 2D and 3D Microscopy Image Synthesis to Enhance Cell Segmentation

Rüveyda Yilmaz, Kaan Keven, Yuli Wu +1

Automated cell segmentation in microscopy images is essential for biomedical research, yet conventional methods are labor-intensive and prone to error. While deep learning-based ap…

cs.CV2024

Visual Fixation-Based Retinal Prosthetic Simulation

Yuli Wu, Do Dinh Tan Nguyen, Henning Konermann +3

This study proposes a retinal prosthetic simulation framework driven by visual fixations, inspired by the saccade mechanism, and assesses performance improvements through end-to-en…