Malte Pedersen

Postdoctoral Researcher in the Visual Analysis and Perception Lab at Aalborg University, and affiliated with the Pioneer Centre for Artificial Intelligence.
My research focuses on computer vision problems in marine environments.

Email  /  Google Scholar  /  GitHub  /  LinkedIn

profile photo

What's New

[Dec25] Attended a kick-off meeting for an upcoming CETPartnership project in Gothenburg, Sweden
[Nov25] Attended the Danish Conference on Marine Restoration in Aalborg, Denmark
Our paper Towards Visual Re-Identification of Fish using Fine-Grained Classification for Electronic Monitoring in Fisheries has been accepted at the Northern Lights Deep Learning Conference (NLDL) in Tromsø, Norway
Attended the AI in Science Summit in Copenhagen, Denmark
[Oct25] Organized the Joint Workshop on Marine Vision at ICCV in Honolulu, USA
Attended the DanFish International conference in Aalborg, Denmark
[Sep25] Gave an oral presentation and participated in a panel debate at The Alan Turing Institute–Nordics AI Workshop:
Maritime, Security & Arctic Research in Oslo, Norway
[Jul25] This page is alive.

Highlighted Publications

AUTOFISH teaser
AutoFish: Dataset and Benchmark for Fine-grained Analysis of Fish
WACVW, 2025
Stefan H. Bengtson, Daniel Lehotský, Vasiliki Ismiroglou, Niels Madsen, Thomas B. Moeslund, Malte Pedersen
project / arXiv / dataset

We propose a publicly available, fully annotated instance segmentation and re-identification dataset of similarly looking fish.

MOTCOM teaser
MOTCOM: The Multi-Object Tracking Dataset Complexity Metric
ECCV, 2022
Malte Pedersen, Joakim Bruslund Haurum, Patrick Dendorfer, Thomas B. Moeslund
project / arXiv / code

We propose a set of metrics to determine the complexity of Multi-Object Tracking datasets along three axes: Motion, Appearance, and Occlusion.

3D-ZeF teaser
3D-ZeF: A 3D Zebrafish Tracking Benchmark Dataset
CVPR, 2020
Malte Pedersen*, Joakim Bruslund Haurum*, Stefan Hein Bengtson, Thomas B. Moeslund
project / arXiv / code / dataset

We present a dataset for 3D multi-object tracking of zebrafish, captured using an off-the-shelf setup.

Brackish dataset teaser
Detection of Marine Animals in a New Underwater Dataset with Varying Visibility
CVPR Workshops, 2019
Malte Pedersen, Joakim Bruslund Haurum, Rikke Gade, Thomas B. Moeslund, Niels Madsen
dataset

We present a publicly available underwater dataset with annotated image sequences of fish, crabs, and starfish captured in brackish water with varying visibility.