Related papers: Beyond Prediction Accuracy: Target-Space Recovery …

Visual error metrics play a fundamental role in the quantification of perceived image similarity. Most recently, use cases for them in real-time applications have emerged, such as content-adaptive shading and shading reuse to increase…

Understanding how the brain encodes visual information is a central challenge in neuroscience and machine learning. A promising approach is to reconstruct visual stimuli, essentially images, from functional Magnetic Resonance Imaging (fMRI)…

Recent studies have demonstrated that the representations of artificial neural networks (ANNs) can exhibit notable similarities to cortical representations when subjected to identical auditory sensory inputs. In these studies, the ability…

Deep predictive models of neuronal activity have recently enabled several new discoveries about the selectivity and invariance of neurons in the visual cortex. These models learn a shared set of nonlinear basis functions, which are linearly…

Learning to simultaneously handle face alignment of arbitrary views, e.g. frontal and profile views, appears to be more challenging than we thought. The difficulties lay in i) accommodating the complex appearance-shape relations exhibited…

Articulation-centric 2D/3D pose supervision forms the core training objective in most existing 3D human pose estimation techniques. Except for synthetic source environments, acquiring such rich supervision for each real target domain at…

An essential problem in artificial intelligence is whether LLMs can simulate human cognition or merely imitate surface-level behaviors, while existing datasets suffer from either synthetic reasoning traces or population-level aggregation,…

Many AI models trained on natural images develop representations that resemble those of the human brain. However, the factors that drive this brain-model similarity remain poorly understood. To disentangle how the model, training and data…

The goal of self-supervised visual representation learning is to learn strong, transferable image representations, with the majority of research focusing on object or scene level. On the other hand, representation learning at part level has…

Determining the similarities and differences between humans and artificial intelligence (AI) is an important goal both in computational cognitive neuroscience and machine learning, promising a deeper understanding of human cognition and…

Reconstructions of visual perception from brain activity have improved tremendously, but the practical utility of such methods has been limited. This is because such models are trained independently per subject where each subject requires…

Face Recognition (FR) tasks have made significant progress with the advent of Deep Neural Networks, particularly through margin-based triplet losses that embed facial images into high-dimensional feature spaces. During training, these…

Large vision models based in deep learning architectures have been consistently advancing the state-of-the-art in biometric recognition. However, three weaknesses are commonly reported for such kind of approaches: 1) their extreme demands…

Human-in-the-loop validation is essential in safety-critical clinical AI, yet the transition between initial model inference and expert correction is rarely analyzed as a structured signal. We introduce a diagnostic alignment framework in…

Unsupervised anomaly detection in brain imaging is challenging. In this paper, we propose self-supervised masked mesh learning for unsupervised anomaly detection on 3D cortical surfaces. Our framework leverages the intrinsic geometry of the…

We consider the problem of obese human mesh recovery, i.e., fitting a parametric human mesh to images of obese people. Despite obese person mesh fitting being an important problem with numerous applications (e.g., healthcare), much recent…

The main goal of this study is to extract a set of brain networks in multiple time-resolutions to analyze the connectivity patterns among the anatomic regions for a given cognitive task. We suggest a deep architecture which learns the…

The global dimensionality of a neural representation manifold provides rich insight into the computational process underlying both artificial and biological neural networks. However, all existing measures of global dimensionality are…

The impressive linguistic abilities of large language models (LLMs) have recommended them as models of human sentence processing, with some conjecturing a positive 'quality-power' relationship (Wilcox et al., 2023), in which language…

Brain imaging classification is commonly approached from two perspectives: modeling the full image volume to capture global anatomical context, or constructing ROI-based graphs to encode localized and topological interactions. Although both…