Following the Clues: Experiments on Person Re-ID using Cross-Modal Intelligence

TL;DR

This paper introduces cRID, a cross-modal framework that combines vision-language models and graph attention to detect and leverage PII clues in datasets, improving person re-identification while addressing privacy concerns.

Contribution

The paper presents a novel cross-modal approach integrating vision-language models and graph attention networks for detecting PII clues in person Re-ID datasets, enhancing privacy-aware identification.

Findings

Improved cross-dataset Re-ID performance from Market-1501 to CUHK03-np.

Effective detection of semantically meaningful PII beyond appearance cues.

Systematic evaluation of PII presence in person image datasets.

Abstract

The collection and release of street-level recordings as Open Data play a vital role in advancing autonomous driving systems and AI research. However, these datasets pose significant privacy risks, particularly for pedestrians, due to the presence of Personally Identifiable Information (PII) that extends beyond biometric traits such as faces. In this paper, we present cRID, a novel cross-modal framework combining Large Vision-Language Models, Graph Attention Networks, and representation learning to detect textual describable clues of PII and enhance person re-identification (Re-ID). Our approach focuses on identifying and leveraging interpretable features, enabling the detection of semantically meaningful PII beyond low-level appearance cues. We conduct a systematic evaluation of PII presence in person image datasets. Our experiments show improved performance in practical cross-dataset Re-ID scenarios, notably from Market-1501 to CUHK03-np (detected), highlighting the framework's practical utility. Code is available at https://github.com/RAufschlaeger/cRID.