Abstract: Road object detection is pivotal in autonomous vehicles, traffic management, and safety. Traditional methods have limitations in complex real-world road scenarios. Deep learning, with its ...

This repository contains a refactoring of the code used in the paper "Learning Latent Graph Structures and Their Uncertainty" (ICML 2025). The code is designed to be modular and easy to use, allowing ...

Visual (Single) Object Tracking aims to continuously localize and estimate the scale of a target in subsequent video frames, given only its initial state in the first frame. This task can be ...

Abstract: Human-Object Interaction (HOI) detection, as a foundational task in human-centric understanding, aims to detect interactive triplets in real-world scenarios. To better distinguish diverse ...