activity
20242026
collaborators
Showing cs.CVShow all

8 papers · 1 filter

cs.CV2026

Human-AI Perceptual Alignment by Playing Hues and Cues

Nuria Alabau-Bosque, Jorge Vila-Tomás, Paula Daudén-Oliver +3

Evaluating the perceptual alignment between Contrastive Vision-Language Models (CVLMs) and humans is typically constrained by traditional benchmarks that overlook fine-grained sema…

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…

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…