STORM：视频中的端到端提及多目标跟踪
STORM: End-to-End Referring Multi-Object Tracking in Videos
AI总结：
STORM通过统一框架联合执行目标定位与跟踪，提升数据效率并构建新数据集，实现多目标跟踪的先进性能。
摘要：
提及多目标跟踪（RMOT）是将视频中语义匹配给定文本查询的目标关联起来的任务。现有RMOT方法将目标定位和跟踪分解为独立模块，由于训练视频稀缺、注释模糊和领域受限，性能有限。本文引入STORM，一种端到端的MLLM，统一框架内联合执行定位与跟踪，消除外部检测器，实现外观、运动和语言的连贯推理。为提高数据效率，我们提出任务组合学习（TCL）策略，将RMOT分解为图像定位和目标跟踪，使STORM能够利用数据丰富的子任务并学习结构化的时空推理。我们进一步构建STORM-Bench，一个包含准确轨迹和多样、无歧义提及表达的新RMOT数据集，通过自下而上的注释流程生成。大量实验表明，STORM在图像定位、单目标跟踪和RMOT基准测试中均取得最佳性能，证明了其在复杂现实场景中的强大泛化能力和鲁棒的时空定位能力。STORM-Bench在https://github.com/amazon-science/storm-referring-multi-object-grounding发布。
英文摘要：
Referring multi-object tracking (RMOT) is a task of associating all the objects in a video that semantically match with given textual queries or referring expressions. Existing RMOT approaches decompose object grounding and tracking into separated modules and exhibit limited performance due to the scarcity of training videos, ambiguous annotations, and restricted domains. In this work, we introduce STORM, an end-to-end MLLM that jointly performs grounding and tracking within a unified framework, eliminating external detectors and enabling coherent reasoning over appearance, motion, and language. To improve data efficiency, we propose a task-composition learning (TCL) strategy that decomposes RMOT into image grounding and object tracking, allowing STORM to leverage data-rich sub-tasks and learn structured spatial--temporal reasoning. We further construct STORM-Bench, a new RMOT dataset with accurate trajectories and diverse, unambiguous referring expressions generated through a bottom-up annotation pipeline. Extensive experiments show that STORM achieves state-of-the-art performance on image grounding, single-object tracking, and RMOT benchmarks, demonstrating strong generalization and robust spatial--temporal grounding in complex real-world scenarios. STORM-Bench is released at https://github.com/amazon-science/storm-referring-multi-object-grounding.
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。
