Multi-modal object re-identification (ReID) aims to retrieve specific targets by leveraging complementary cues from different sensing modalities. Despite recent progress, two key challenges remain: (1) the limited ability to jointly address both modality and viewpoint discrepancies, and (2) the difficulty of effectively leveraging reliable target-domain data to improve generalization. To address these challenges, we propose Proxy-driven Test-Time Training (ProxyTTT), a unified framework that enhances both multi-modal identity representation learning and model generalization. During training, we propose a Multi-Proxy Learning (MPL) mechanism to address the representation bias across different views and modalities. MPL disentangles fine-grained modality-specific and modality-common identity proxies as semantic anchors to align identity features across diverse perspectives and sensing modalities. This alignment strategy enables the model to learn robust and discriminative global identity representations under heterogeneous modality conditions. At test time, to reliably exploit target domain data, we propose Proxy-guided Entropy-based Selective Adaptation (PESA) for test-time training. Specifically, PESA leverages the semantic structure encoded by identity proxies to estimate prediction uncertainty via entropy, and selectively adapts the model using only high-confidence samples. This selective adaptation effectively mitigates the domain shift between training and deployment environments, improving the model’s generalization in real-world scenarios. Extensive experiments on four public multi-modal ReID benchmarks (RGBNT201, RGBNT100, MSVR310, and WMVeID863) demonstrate the effectiveness of ProxyTTT.

Information sensor can realize the ubiquitous connection between objects and humans by the distributed fiber-optic sensor array, i.e., emerging infrastructure for Internet of Things, in which optical frequency domain reflectometry (OFDR) with its high spatial resolution plays an important role in achieving intelligent perception and identification of the objects. However, given a certain fiber length, there are tradeoffs among the processing speed, the spatial resolution, and the strain measurement range. In this article, a time optimization interpolation method and a distance domain compensation method are reported and experimentally verified to break the aforementioned tradeoffs for the first time. First, a full theoretical analysis on how to reduce the interpolation number and the reason why it is difficult to achieve high spatial resolution and large strain measurement and how to resolve it is made. Second in the proof-of-concept experiment, measurements of large strains up to 10 000$\boldsymbol{\mu } \boldsymbol{\varepsilon }$are realized along the sensing fiber with a spatial resolution of 2 mm using a conventional OFDR system. Also, the processing time is shortened by 76 times compared with the traditional processing method. This article makes a significant step toward high-performance OFDR system with fast processing, high spatial resolution, and wide strain measurement.