While efforts have been made to explain computer vision models, these approaches often fall short of providing direct and human-understandable explanations.

Vision Language Models (VLMs) have demonstrated remarkable performance in 2D vision and language tasks. However, their ability to reason about spatial arrangements remains limited. In this work, we introduce Spatial Region GPT (SpatialRGPT) to enhance VLMs' spatial perception and reasoning capabilities.

Membership Inference Attacks (MIA) aim to infer whether a target data record has been utilized for model training or not.

The traditional approach of pixel-level alignment is ineffective for diffusion-processed frames because of iterative disruptions.

Multi-person pose estimation and tracking have been actively researched by the computer vision community due to their practical applicability. However, existing human pose estimation and tracking datasets have only been successful in typical scenarios, such as those without motion blur or with well-lit conditions.