Josef Kittler

Object-Centric Refinement for Enhanced Zero-Shot Segmentation

MergeTune: Continued Fine-Tuning of Vision-Language Models

Sparse but Sharp: Saliency-guided Black-box Attacks Reveal Vulnerabilities in Skeleton-based Human Action Recognition

Consistent Region-Informed Self-supervised Pretraining

Can Models Learn From Arbitrary Pairs?

Diff-ID: Identity-Consistent Facial Image Generation and Morphing via Diffusion Models

CG-SSL: Concept-Guided Self-Supervised Learning

A PATCH LEVEL PERSPECTIVE OF PROMPT TUNING

Hybrid Batch Normalisation: Resolving the Dilemma of Batch Normalisation in Federated Learning

SymCL: Riemannian Contrastive Learning on the Symmetric Positive Definite Manifold for Visual Classification