17 papers
CIFA: Contextual-Intersectional Fairness Auditing for Hidden Subgroup Discovery in Face Analysis
Nazia Aslam, Khalid Adnan Alsayed, Thomas B. Moeslund +1
Fairness evaluation in computer vision commonly relies on aggregate accuracy and demographic subgroup analysis. However, visual models are also sensitive to contextual factors such…
A Hyperbolic Perspective on Hierarchical Structure in Object-Centric Scene Representations
Neelu Madan, Ãlex Pujol, Andreas Møgelmose +4
Slot attention has emerged as a powerful framework for unsupervised object-centric learning, decomposing visual scenes into a small set of compact vector representations called \em…
Only Whats Necessary: Pareto Optimal Data Minimization for Privacy Preserving Video Anomaly Detection
Nazia Aslam, Abhisek Ray, Thomas B. Moeslund +1
Video anomaly detection (VAD) systems are increasingly deployed in safety critical environments and require a large amount of data for accurate detection. However, such data may co…
AdaSpot: Spend Resolution Where It Matters for Precise Event Spotting
Artur Xarles, Sergio Escalera, Thomas B. Moeslund +1
Precise Event Spotting aims to localize fast-paced actions or events in videos with high temporal precision, a key task for applications in sports analytics, robotics, and autonomo…
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…