Related papers: Visual Validation versus Visual Estimation: A Stud…
Estimating 3D human pose and shape from 2D images is a crucial yet challenging task. While prior methods with model-based representations can perform reasonably well on whole-body images, they often fail when parts of the body are occluded…
Modern neural networks (NNs) often achieve high predictive accuracy but are poorly calibrated, producing overconfident predictions even when wrong. This miscalibration poses serious challenges in applications where reliable uncertainty…
Visual similarities discovery (VSD) is an important task with broad e-commerce applications. Given an image of a certain object, the goal of VSD is to retrieve images of different objects with high perceptual visual similarity. Although…
Humans excel at visual social inference, the ability to infer hidden elements of a scene from subtle behavioral cues such as other people's gaze, pose, and orientation. This ability drives everyday social reasoning in humans and is critical…
Human visual attention is a complex phenomenon. A computational modeling of this phenomenon must take into account where people look in order to evaluate which are the salient locations (spatial distribution of the fixations), when they…
The recent progress in Vision-Language Models (VLMs) has broadened the scope of multimodal applications. However, evaluations often remain limited to functional tasks, neglecting abstract dimensions such as personality traits and human…
As AI systems advance beyond human capabilities, scalable oversight becomes critical: how can we supervise AI that exceeds our abilities? A key challenge is that human evaluators may form incorrect beliefs about AI behavior in complex…
Recent years have shown an increased development of methods for justifying the predictions of neural networks through visual explanations. These explanations usually take the form of heatmaps which assign a saliency (or relevance) value to…
We address the problem of estimating image difficulty defined as the human response time for solving a visual search task. We collect human annotations of image difficulty for the PASCAL VOC 2012 data set through a crowd-sourcing platform.…
We present results from a preregistered and crowdsourced user study where we asked members of the general population to determine whether two samples represented using different forms of data visualizations are drawn from the same or…
Is basic visual understanding really solved in state-of-the-art VLMs? We present VisualOverload, a slightly different visual question answering (VQA) benchmark comprising 2,720 question-answer pairs, with privately held ground-truth…
Vision-Language Models (VLMs) have emerged as the dominant approach for zero-shot recognition, adept at handling diverse scenarios and significant distribution changes. However, their deployment in risk-sensitive areas requires a deeper…
Virality of online content on social networking websites is an important but esoteric phenomenon often studied in fields like marketing, psychology and data mining. In this paper we study viral images from a computer vision perspective. We…
Segmenting visual stimuli into distinct groups of features and visual objects is central to visual function. Classical psychophysical methods have helped uncover many rules of human perceptual segmentation, and recent progress in machine…
Model validity is key to the accurate and safe behavior of autonomous vehicles. Using invalid vehicle models in the different plan and control vehicle frameworks puts the stability of the vehicle, and thus its safety at stake. In this work,…
A criterion is proposed for testing hypothesis about the nature of the error variance in the dependent variable in linear model, which separates correctly and incorrectly specified models. In the former only measurement errors determine the…
Visual Grounding (VG) methods in Visual Question Answering (VQA) attempt to improve VQA performance by strengthening a model's reliance on question-relevant visual information. The presence of such relevant information in the visual input…
We propose a novel probabilistic model for visual question answering (Visual QA). The key idea is to infer two sets of embeddings: one for the image and the question jointly and the other for the answers. The learning objective is to learn…
Model alignment is currently applied in a vacuum, evaluated primarily through standardised benchmark performance. The purpose of this study is to examine the effects of alignment on populations of models through time. We focus on the…
Psychophysical experiments remain the most reliable approach for perceptual image quality assessment (IQA), yet their cost and limited scalability encourage automated approaches. We investigate whether Vision Language Models (VLMs) can…