Abstract: Open-vocabulary multi-object tracking (OVMOT) is a cutting research direction within the multi-object tracking field. It employs large multi-modal models to effectively address the challenge ...

In deep space environment, some objects may split into several small fragments during movement, and these deep space objects often appear as points in satellite images. In this paper, we conduct ...

ReferGPT introduces a novel approach to language-guided 3D multi-object tracking by integrating CLIP vision-language understanding, Large Language Models (LLMs), and Vision-Language Models (VLMs) for ...

Abstract: The objective in aerial object tracking with the goal of accurately capturing and tracking the dynamic and variable characteristics of objects in various complex environments. However, ...