Abstract
Traditional text-based person ReID assumes that person descriptions from witnesses are complete and provided at once. However, in real-world scenarios, such descriptions are often partial or vague. To address this limitation, we introduce a new task called interactive person re-identification (Inter-ReID). Inter-ReID is a dialogue-based retrieval task that iteratively refines initial descriptions through ongoing interactions with the witnesses. To facilitate the study of this new task, we construct a dialogue dataset that incorporates multiple types of questions by decomposing fine-grained attributes of individuals. We further propose LLaVA-ReID, a question model that generates targeted questions based on visual and textual contexts to elicit additional details about the target person. Leveraging a looking-forward strategy, we prioritize the most informative questions as supervision during training. Experimental results on both Inter-ReID and text-based ReID benchmarks demonstrate that LLaVA-ReID significantly outperforms baselines.
Abstract (translated)
传统的基于文本的人再识别（ReID）任务假设目击者提供的描述是完整且一次性给出的。然而，在现实场景中，这些描述往往不完整或模糊不清。为了解决这一局限性，我们引入了一个新的任务——互动式人再识别（Inter-ReID）。Inter-ReID 是一种基于对话的检索任务，通过与目击者的持续交互来逐步完善初始描述。 为了促进这项新任务的研究，我们构建了一个包含多种类型问题的对话数据集，这些问题通过对个体进行细粒度属性分解而生成。此外，我们还提出了一种名为LLaVA-ReID的问题模型，该模型基于视觉和文本上下文生成有针对性的问题，以获取关于目标人物的额外信息。通过采用面向未来的策略，在训练过程中优先选择最具有信息量的问题作为监督。 在交互式ReID和传统基于文本的ReID基准测试上的实验结果表明，LLaVA-ReID显著优于现有基线方法。
URL
https://arxiv.org/abs/2504.10174
