collaborators

5 papers

cs.CV2025

Training-Free Generation of Diverse and High-Fidelity Images via Prompt Semantic Space Optimization

Debin Meng, Chen Jin, Zheng Gao +3

Image diversity remains a fundamental challenge for text-to-image diffusion models. Low-diversity models tend to generate repetitive outputs, increasing sampling redundancy and hin…

cs.CV2025

VLLMs Provide Better Context for Emotion Understanding Through Common Sense Reasoning

Alexandros Xenos, Niki Maria Foteinopoulou, Ioanna Ntinou +2

Recognising emotions in context involves identifying an individual's apparent emotions while considering contextual cues from the surrounding scene. Previous approaches to this tas…

cs.CV2025

DiffusionAct: Controllable Diffusion Autoencoder for One-shot Face Reenactment

Stella Bounareli, Christos Tzelepis, Vasileios Argyriou +2

Video-driven neural face reenactment aims to synthesize realistic facial images that successfully preserve the identity and appearance of a source face, while transferring the targ…

cs.CV2024

CemiFace: Center-based Semi-hard Synthetic Face Generation for Face Recognition

Zhonglin Sun, Siyang Song, Ioannis Patras +1

Privacy issue is a main concern in developing face recognition techniques. Although synthetic face images can partially mitigate potential legal risks while maintaining effective f…

cs.CV2024

Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization

James Oldfield, Markos Georgopoulos, Grigorios G. Chrysos +5

The Mixture of Experts (MoE) paradigm provides a powerful way to decompose dense layers into smaller, modular computations often more amenable to human interpretation, debugging, a…