Computer Vision

Graph-Based Analysis of Attentional Fidelity in Brain-To-Image Reconstruction

Brain-Grasp: Graph-Based Saliency Priors for Improved FMRI-Based Visual Brain Decoding

Recent progress in brain-guided image generation has improved the quality of fMRI-based reconstructions; however, fundamental challenges remain in preserving object-level structure …

Graph-Based Evaluation of Visual Brain Decoding from fMRI Data

Despite progress in visual reconstruction from fMRI signals, evaluating reconstruction quality remains challenging due to noisy, low-resolution data and semantic ambiguity. …

How Well is Human Attention Preserved in fMRI-Based VisualBrain Decoding?

This paper investigates the preservation of human visual attention in brain activity patterns captured through fMRI during visual decoding tasks. We explore how well attention …

What is Wrong with Visual Brain Decoding? A Saliency-based Investigation

Recent advancements in diffusion-based image generation and large vision/language models have revolutionized visual brain decoding (VBD), driving progress in neuroscience and …

Saliency Matters: From Nodes to Objects

Due to their intrinsic capabilities in capturing, modeling, and representing relationships between pieces of information, graphs have been used in a wide variety of application …