基于LLaVA-Video的多目标跟踪检索：MOT25-StAG挑战赛的免训练解决方案
Multi-Object Tracking Retrieval with LLaVA-Video: A Training-Free Solution to MOT25-StAG Challenge
AI总结：
本文提出一种结合FastTracker与LLaVA-Video的两阶段零样本视频检索方法，用于MOT25-StAG多目标语言查询跟踪任务，在测试集上以m-HIoU 20.68、HOTA 10.73获得挑战赛第二名。
摘要：
在本报告中，我们介绍了针对MOT25-时空动作定位（MOT25-StAG）挑战赛的解决方案。该挑战赛的目标是，以复杂真实场景的视频数据为输入，准确定位并跟踪与特定自由形式语言查询相匹配的多个目标。我们将底层任务建模为视频检索问题，并提出了一种两阶段、零样本的方法，结合了当前最优跟踪模型FastTracker和多模态大语言模型LLaVA-Video的优势。在MOT25-StAG测试集上，我们的方法分别取得了20.68的m-HIoU和10.73的HOTA分数，在挑战赛中获得第二名。
英文摘要：
In this report, we present our solution to the MOT25-Spatiotemporal Action Grounding (MOT25-StAG) Challenge. The aim of this challenge is to accurately localize and track multiple objects that match specific and free-form language queries, using video data of complex real-world scenes as input. We model the underlying task as a video retrieval problem and present a two-stage, zero-shot approach, combining the advantages of the SOTA tracking model FastTracker and Multi-modal Large Language Model LLaVA-Video. On the MOT25-StAG test set, our method achieves m-HIoU and HOTA scores of 20.68 and 10.73 respectively, which won second place in the challenge.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
