TP-GMOT：基于文本提示与运动-外观代价（MAC）SORT的通用多目标跟踪
TP-GMOT: Tracking Generic Multiple Object by Textual Prompt with Motion-Appearance Cost (MAC) SORT
AI总结：
本文提出TP-GMOT框架，通过文本提示驱动开放词汇检测与融合运动-外观代价的MAC-SORT关联方法，在零训练样本下实现高相似度通用多目标跟踪，并构建Refer-GMOT数据集进行验证。
摘要：
尽管多目标跟踪（MOT）已取得显著进展，但它仍受限于对先验知识的严重依赖，并且仅限于预定义类别。相比之下，通用多目标跟踪（GMOT）旨在跟踪外观相似的多个目标，对目标的先验信息需求较少，但面临视角、光照、遮挡和分辨率等变化带来的挑战。我们的贡献首先包括引入Refer-GMOT数据集，这是一个视频集合，每个视频都配有对其属性的细粒度文本描述。随后，我们提出了一种新颖的基于文本提示的开放词汇GMOT框架，称为TP-GMOT，它能够在零训练样本的情况下跟踪从未见过的目标类别。在TP-GMOT框架内，我们引入了两个新组件：（i）TP-OD，一种通过文本提示进行的目标检测方法，用于准确检测具有特定特征的未见目标；（ii）Motion-Appearance Cost SORT（MAC-SORT），一种新颖的目标关联方法，它巧妙地融合了基于运动和基于外观的匹配策略，以应对跟踪多个高相似度通用目标的复杂任务。我们的贡献在Refer-GMOT数据集上针对GMOT任务进行了基准测试。此外，为了评估所提出的TP-GMOT框架的泛化能力以及MAC-SORT跟踪器的有效性，我们在DanceTrack和MOT20数据集上针对MOT任务进行了消融研究。我们的数据集、代码和模型将在https://fsoft-aic.github.io/TP-GMOT上公开提供。
英文摘要：
While Multi-Object Tracking (MOT) has made substantial advancements, it is limited by heavy reliance on prior knowledge and limited to predefined categories. In contrast, Generic Multiple Object Tracking (GMOT), tracking multiple objects with similar appearance, requires less prior information about the targets but faces challenges with variants like viewpoint, lighting, occlusion, and resolution. Our contributions commence with the introduction of the \textbf{\text{Refer-GMOT dataset}} a collection of videos, each accompanied by fine-grained textual descriptions of their attributes. Subsequently, we introduce a novel text prompt-based open-vocabulary GMOT framework, called \textbf{\text{TP-GMOT}}, which can track never-seen object categories with zero training examples. Within \text{TP-GMOT} framework, we introduce two novel components: (i) {\textbf{\text{TP-OD}}, an object detection by a textual prompt}, for accurately detecting unseen objects with specific characteristics. (ii) Motion-Appearance Cost SORT \textbf{\text{MAC-SORT}}, a novel object association approach that adeptly integrates motion and appearance-based matching strategies to tackle the complex task of tracking multiple generic objects with high similarity. Our contributions are benchmarked on the \text{Refer-GMOT} dataset for GMOT task. Additionally, to assess the generalizability of the proposed \text{TP-GMOT} framework and the effectiveness of \text{MAC-SORT} tracker, we conduct ablation studies on the DanceTrack and MOT20 datasets for the MOT task. Our dataset, code, and models will be publicly available at: https://fsoft-aic.github.io/TP-GMOT
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。
