collaborators

6 papers

cs.CV2025

Hues and Cues: Human vs. CLIP

Nuria Alabau-Bosque, Jorge Vila-Tomás, Paula Daudén-Oliver +4

Playing games is inherently human, and a lot of games are created to challenge different human characteristics. However, these tasks are often left out when evaluating the human-li…

cs.CV2025

Do Vision Transformers See Like Humans? Evaluating their Perceptual Alignment

Pablo Hernández-Cámara, Jose Manuel Jaén-Lorites, Jorge Vila-Tomás +2

Vision Transformers (ViTs) achieve remarkable performance in image recognition tasks, yet their alignment with human perception remains largely unexplored. This study systematicall…

cs.CV2025

Contrast Sensitivity in Multimodal Large Language Models: A Psychophysics-Inspired Evaluation

Pablo Hernández-Cámara, Alexandra Gomez-Villa, Jose Manuel Jaén-Lorites +3

Understanding how Multimodal Large Language Models (MLLMs) process low-level visual features is critical for evaluating their perceptual abilities and has not been systematically c…

cs.CV2025

On the dynamic evolution of CLIP texture-shape bias and its relationship to human alignment and model robustness

Pablo Hernández-Cámara, Jose Manuel Jaén-Lorites, Alexandra Gómez-Villa +3

Contrastive language-image models such as CLIP have demonstrated remarkable generalization capabilities. However, how their internal visual representations evolve during training a…

q-bio.NC2025

A Turing Test for Artificial Nets devoted to model Human Vision

Jorge Vila-Tomás, Pablo Hernández-Cámara, Qiang Li +2

In our invited talk at the AI Evaluation Workshop of the University of Bristol back in June 2022 we argued that, despite claims about successful modeling of the visual brain using…

cs.CV2024

Parametric PerceptNet: A bio-inspired deep-net trained for Image Quality Assessment

Jorge Vila-Tomás, Pablo Hernández-Cámara, Valero Laparra +1

Human vision models are at the core of image processing. For instance, classical approaches to the problem of image quality are based on models that include knowledge about human v…