Person detection and Re-identification are two well-defined support tasks for practically relevant tasks such as Person Search and Multiple Person Tracking. Person Search aims to find and locate all instances with the same identity as the query person in a set of panoramic gallery images. Similarly, Multiple Person Tracking, especially when using the tracking-by-detection pipeline, requires to detect and associate all appeared persons in consecutive video frames. One major challenge shared by the two tasks comes from the contradictory goals of detection and re-identification, i.e, person detection focuses on finding the commonness of all persons while person re-ID handles the differences among multiple identities. Therefore, it is crucial to reconcile the relationship between the two support tasks in a joint model. To this end, we present a novel approach called Norm-Aware Embedding to disentangle the person embedding into norm and angle for detection and re-ID respectively, allowing for both effective and efficient multi-task training. We further extend the proposal-level person embedding to pixel-level, whose discrimination ability is less affected by misalignment. Our Norm-Aware Embedding achieves remarkable performance on both person search and multiple person tracking benchmarks, with the merit of being easy to train and resource-friendly.

人员检测和重新识别是实际相关任务（例如人员搜索和多人跟踪）的两个定义明确的支持任务。人物搜索旨在在一组全景图库图像中查找和定位与查询人物具有相同身份的所有实例。类似地，多人跟踪，尤其是在使用逐检测跟踪管道时，需要检测和关联连续视频帧中所有出现的人。这两个任务共有的一个主要挑战来自检测和重新识别的矛盾目标，即人员检测侧重于发现所有人的共同点，而人员重新识别处理多个身份之间的差异。因此，协调联合模型中两个支持任务之间的关系至关重要。为此，我们提出了一种称为 Norm-Aware Embedding 的新方法，分别将人嵌入到范数和角度中以进行检测和重新识别，从而实现有效和高效的多任务训练。我们进一步将提案级别的人嵌入扩展到像素级别，其识别能力受错位影响较小。我们的 Norm-Aware Embedding 在人员搜索和多人跟踪基准测试中都取得了卓越的性能，具有易于训练和资源友好的优点。