Natural Language (NL) descriptions can be the most convenient or the only way to interact with systems built to understand and detect city scale traffic patterns and vehicle-related events. In this paper, we extend the widely adopted CityFlow Benchmark with natural language descriptions for vehicle targets and introduce the CityFlow-NL Benchmark. The CityFlow-NL contains more than 5,000 unique and precise NL descriptions of vehicle targets, making it the largest-scale tracking with NL descriptions dataset to our knowledge. Moreover, the dataset facilitates research at the intersection of multi-object tracking, retrieval by NL descriptions, and temporal localization of events.

翻译：自然语言描述(NL)可能是与为理解和探测城市规模交通模式和与车辆有关的事件而建立的系统进行互动的最方便或唯一的方法。在本文件中,我们扩展了广泛采用、具有车辆目标自然语言描述的城市灯塔基准,并引入了CityFlow-NL基准。CityFlow-NL包含5 000多条独特和精确的车辆目标描述,使其成为我们所了解的最大规模跟踪与NL描述数据集的NL数据。此外,数据集便于在多弹道跟踪、NL描述检索和事件时间定位的交叉点进行研究。