97 citations · 120 across the 18 of their papers we have counts for
19 papers
Point-Based 3D Reconstruction from Sparse Views under Known Illumination
Magnus Kaufmann Gjerde, Joakim Bruslund Haurum, Jeppe Revall Frisvad +3
Sparse view 3D reconstruction is commonly addressed with neural implicit surfaces or dense point-based representations such as Gaussian splatting. Surface-aware splatting methods i…
From Pixels to Privacy: Temporally Consistent Video Anonymization via Token Pruning for Privacy Preserving Action Recognition
Nazia Aslam, Abhisek Ray, Joakim Bruslund Haurum +2
Recent advances in large-scale video models have significantly improved video understanding across domains such as surveillance, healthcare, and entertainment. However, these model…
How to Sample High Quality 3D Fractals for Action Recognition Pre-Training?
Marko Putak, Thomas B. Moeslund, Joakim Bruslund Haurum
Synthetic datasets are being recognized in the deep learning realm as a valuable alternative to exhaustively labeled real data. One such synthetic data generation method is Formula…
Comparing Euclidean and Hyperbolic K-Means for Generalized Category Discovery
Mohamad Dalal, Thomas B. Moeslund, Joakim Bruslund Haurum
Hyperbolic representation learning has been widely used to extract implicit hierarchies within data, and recently it has found its way to the open-world classification task of Gene…
Hyperbolic Multimodal Representation Learning for Biological Taxonomies
ZeMing Gong, Chuanqi Tang, Xiaoliang Huo +6
Taxonomic classification in biodiversity research involves organizing biological specimens into structured hierarchies based on evidence, which can come from multiple modalities su…
Point Cloud Segmentation of Agricultural Vehicles using 3D Gaussian Splatting
Alfred T. Christiansen, Andreas H. Højrup, Morten K. Stephansen +6
Training neural networks for tasks such as 3D point cloud semantic segmentation demands extensive datasets, yet obtaining and annotating real-world point clouds is costly and labor…
Generating Synthetic Stereo Datasets using 3D Gaussian Splatting and Expert Knowledge Transfer
Filip Slezak, Magnus K. Gjerde, Joakim B. Haurum +3
In this paper, we introduce a 3D Gaussian Splatting (3DGS)-based pipeline for stereo dataset generation, offering an efficient alternative to Neural Radiance Fields (NeRF)-based me…
Agglomerative Token Clustering
Joakim Bruslund Haurum, Sergio Escalera, Graham W. Taylor +1
We present Agglomerative Token Clustering (ATC), a novel token merging method that consistently outperforms previous token merging and pruning methods across image classification,…
BIOSCAN-5M: A Multimodal Dataset for Insect Biodiversity
Zahra Gharaee, Scott C. Lowe, ZeMing Gong +10
As part of an ongoing worldwide effort to comprehend and monitor insect biodiversity, this paper presents the BIOSCAN-5M Insect dataset to the machine learning community and establ…
An Empirical Study into Clustering of Unseen Datasets with Self-Supervised Encoders
Scott C. Lowe, Joakim Bruslund Haurum, Sageev Oore +2
Can pretrained models generalize to new datasets without any retraining? We deploy pretrained image models on datasets they were not trained for, and investigate whether their embe…
CLIBD: Bridging Vision and Genomics for Biodiversity Monitoring at Scale
ZeMing Gong, Austin T. Wang, Xiaoliang Huo +4
Measuring biodiversity is crucial for understanding ecosystem health. While prior works have developed machine learning models for taxonomic classification of photographic images a…
BarcodeBERT: Transformers for Biodiversity Analysis
Pablo Millan Arias, Niousha Sadjadi, Monireh Safari +9
In the global challenge of understanding and characterizing biodiversity, short species-specific genomic sequences known as DNA barcodes play a critical role, enabling fine-grained…
Which Tokens to Use? Investigating Token Reduction in Vision Transformers
Joakim Bruslund Haurum, Sergio Escalera, Graham W. Taylor +1
Since the introduction of the Vision Transformer (ViT), researchers have sought to make ViTs more efficient by removing redundant information in the processed tokens. While differe…
A Step Towards Worldwide Biodiversity Assessment: The BIOSCAN-1M Insect Dataset
Zahra Gharaee, ZeMing Gong, Nicholas Pellegrino +13
In an effort to catalog insect biodiversity, we propose a new large dataset of hand-labelled insect images, the BIOSCAN-Insect Dataset. Each record is taxonomically classified by a…
MOTCOM: The Multi-Object Tracking Dataset Complexity Metric
Malte Pedersen, Joakim Bruslund Haurum, Patrick Dendorfer +1
There exists no comprehensive metric for describing the complexity of Multi-Object Tracking (MOT) sequences. This lack of metrics decreases explainability, complicates comparison o…
Multi-Task Classification of Sewer Pipe Defects and Properties using a Cross-Task Graph Neural Network Decoder
Joakim Bruslund Haurum, Meysam Madadi, Sergio Escalera +1
The sewerage infrastructure is one of the most important and expensive infrastructures in modern society. In order to efficiently manage the sewerage infrastructure, automated sewe…
Sewer-ML: A Multi-Label Sewer Defect Classification Dataset and Benchmark
Joakim Bruslund Haurum, Thomas B. Moeslund
Perhaps surprisingly sewerage infrastructure is one of the most costly infrastructures in modern society. Sewer pipes are manually inspected to determine whether the pipes are defe…
3D-ZeF: A 3D Zebrafish Tracking Benchmark Dataset
Malte Pedersen, Joakim Bruslund Haurum, Stefan Hein Bengtson +1
In this work we present a novel publicly available stereo based 3D RGB dataset for multi-object zebrafish tracking, called 3D-ZeF. Zebrafish is an increasingly popular model organi…
Is it Raining Outside? Detection of Rainfall using General-Purpose Surveillance Cameras
Joakim Bruslund Haurum, Chris H. Bahnsen, Thomas B. Moeslund
In integrated surveillance systems based on visual cameras, the mitigation of adverse weather conditions is an active research topic. Within this field, rain removal algorithms hav…