MLS-Track: Multilevel Semantic Interaction in RMOT

arXiv:2404.12031v1 Announce Type: new
Abstract: The new trend in multi-object tracking task is to track objects of interest using natural language. However, the scarcity of paired prompt-instance data hinders its progress. To address this challenge, we propose a high-quality yet low-cost data generation method base on Unreal Engine 5 and construct a brand-new benchmark dataset, named Refer-UE-City, which primarily includes scenes from intersection surveillance videos, detailing the appearance and actions of people and vehicles. Specifically, it provides 14 videos with …

abstract arxiv benchmark brand challenge construct cost cs.cv data however instance language low mls natural natural language object objects progress prompt quality semantic tracking trend type unreal unreal engine unreal engine 5