Georgios Tzimiropoulos

7

Papers

26

Total Citations

Papers (7)

VladVA: Discriminative Fine-tuning of LVLMs

Multiscale Vision Transformers Meet Bipartite Matching for Efficient Single-stage Action Localization

FAM Diffusion: Frequency and Attention Modulation for High-Resolution Image Generation with Stable Diffusion

Efficient Unsupervised Visual Representation Learning with Explicit Cluster Balancing

LAFS: Landmark-based Facial Self-supervised Learning for Face Recognition

Edge-SD-SR: Low Latency and Parameter Efficient On-device Super-Resolution with Stable Diffusion via Bidirectional Conditioning

FFF: Fixing Flawed Foundations in Contrastive Pre-Training Results in Very Strong Vision-Language Models