papers

Publications (14)

cs.CV2026

ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understanding

Jovana Kondic, Pengyuan Li, Dhiraj Joshi +24

Understanding charts requires models to jointly reason over geometric visual patterns, structured numerical data, and natural language -- a capability where current vision-language…

cs.CV2024

MAEDAY: MAE for few and zero shot AnomalY-Detection

Eli Schwartz, Assaf Arbelle, Leonid Karlinsky +4

We propose using Masked Auto-Encoder (MAE), a transformer model self-supervisedly trained on image inpainting, for anomaly detection (AD). Assuming anomalous regions are harder to…

q-fin.CP2019

PAGAN: Portfolio Analysis with Generative Adversarial Networks

Giovanni Mariani, Yada Zhu, Jianbo Li +4

Since decades, the data science community tries to propose prediction models of financial time series. Yet, driven by the rapid development of information technology and machine in…

cs.CV2023

Counterfactual Image Generation for adversarially robust and interpretable Classifiers

Rafael Bischof, Florian Scheidegger, Michael A. Kraus +1

Neural Image Classifiers are effective but inherently hard to interpret and susceptible to adversarial attacks. Solutions to both problems exist, among others, in the form of count…

cs.CV2018

BAGAN: Data Augmentation with Balancing GAN

Giovanni Mariani, Florian Scheidegger, Roxana Istrate +2

Image classification datasets are often imbalanced, characteristic that negatively affects the accuracy of deep-learning classifiers. In this work we propose balancing GAN (BAGAN)…

eess.IV2017

Hydra: An Accelerator for Real-Time Edge-Aware Permeability Filtering in 65nm CMOS

Manuel Eggimann, Christelle Gloor, Florian Scheidegger +4

Many modern video processing pipelines rely on edge-aware (EA) filtering methods. However, recent high-quality methods are challenging to run in real-time on embedded hardware due…