# Decoupled Cross-Modal Alignment Network for Text-RGBT Person Retrieval and A High-Quality Benchmark

arXiv: https://arxiv.org/abs/2503.07950 · HTML: https://mlsanity.com/paper/2503.07950/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 56 references that are in the map.
- First posted on arXiv 11 Mar 2025.

## Builds on (most cited first, 30 of 30)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [VILA: On Pre-training for Visual Language Models](https://mlsanity.com/paper/2312.07533/) (2023)
- [A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model](https://mlsanity.com/paper/2112.14757/) (2021)
- [Drone-based RGB-Infrared Cross-Modality Vehicle Detection via Uncertainty-Aware Learning](https://mlsanity.com/paper/2003.02437/) (2020)
- [Person Search with Natural Language Description](https://mlsanity.com/paper/1702.05729/) (2017)
- [Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval](https://mlsanity.com/paper/2303.12501/) (2023)
- [RGB-T Object Tracking:Benchmark and Baseline](https://mlsanity.com/paper/1805.08982/) (2018)
- [CAMP: Cross-Modal Adaptive Message Passing for Text-Image Retrieval](https://mlsanity.com/paper/1909.05506/) (2019)
- [LasHeR: A Large-scale High-diversity Benchmark for RGBT Tracking](https://mlsanity.com/paper/2104.13202/) (2021)
- [Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark](https://mlsanity.com/paper/2306.02898/) (2023)
- [RGBT Salient Object Detection: A Large-scale Dataset and Benchmark](https://mlsanity.com/paper/2007.03262/) (2020)
- [Adversarial Representation Learning for Text-to-Image Matching](https://mlsanity.com/paper/1908.10534/) (2019)
- [Improving Description-based Person Re-identification by Multi-granularity Image-text Alignments](https://mlsanity.com/paper/1906.09610/) (2019)
- [Contextual Non-Local Alignment over Full-Scale Representation for Text-Based Person Search](https://mlsanity.com/paper/2101.03036/) (2021)
- [Learning Granularity-Unified Representations for Text-to-Image Person Re-identification](https://mlsanity.com/paper/2207.07802/) (2022)
- [TIPCB: A Simple but Effective Part-based Convolutional Baseline for Text-based Person Search](https://mlsanity.com/paper/2105.11628/) (2021)
- [Noisy-Correspondence Learning for Text-to-Image Person Re-identification](https://mlsanity.com/paper/2308.09911/) (2023)
- [Text-Based Person Search with Limited Data](https://mlsanity.com/paper/2110.10807/) (2021)
- [Pose-Guided Multi-Granularity Attention Network for Text-Based Person Search](https://mlsanity.com/paper/1809.08440/) (2018)
- [Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting](https://mlsanity.com/paper/2012.04529/) (2020)
- [Translation, Scale and Rotation: Cross-Modal Alignment Meets RGB-Infrared Vehicle Detection](https://mlsanity.com/paper/2209.13801/) (2022)
- [PLIP: Language-Image Pre-training for Person Representation Learning](https://mlsanity.com/paper/2305.08386/) (2023)
- [Edge-aware Guidance Fusion Network for RGB Thermal Scene Parsing](https://mlsanity.com/paper/2112.05144/) (2021)
- [An Empirical Study of CLIP for Text-based Person Search](https://mlsanity.com/paper/2308.10045/) (2023)
- [UFineBench: Towards Text-based Person Retrieval with Ultra-fine Granularity](https://mlsanity.com/paper/2312.03441/) (2023)
- [Alignment-Free RGBT Salient Object Detection: Semantics-guided Asymmetric Correlation Network and A Unified Benchmark](https://mlsanity.com/paper/2406.00917/) (2024)
- [X2-VLM: All-In-One Pre-trained Model For Vision-Language Tasks](https://mlsanity.com/paper/2211.12402/) (2022)
- [HumanVLM: Foundation for Human-Scene Vision-Language Model](https://mlsanity.com/paper/2411.03034/) (2024)
- [Structural Information Guided Multimodal Pre-training for Vehicle-centric Perception](https://mlsanity.com/paper/2312.09812/) (2023)
- [From Attributes to Natural Language: A Survey and Foresight on Text-based Person Re-identification](https://mlsanity.com/paper/2408.00096/) (2024)

## Built on by (most cited first, 1 of 1)

- [Physics-Constrained Cross-Resolution Enhancement Network for Optics-Guided Thermal UAV Image Super-Resolution](https://mlsanity.com/paper/2601.03526/) (2026)

## Abstract (arXiv)

The performance of traditional text-image person retrieval task is easily affected by lighting variations due to imaging limitations of visible spectrum sensors. In recent years, cross-modal information fusion has emerged as an effective strategy to enhance retrieval robustness. By integrating complementary information from different spectral modalities, it becomes possible to achieve more stable person recognition and matching under complex real-world conditions. Motivated by this, we introduce a novel task: Text-RGBT Person Retrieval, which incorporates cross-spectrum information fusion by combining the complementary cues from visible and thermal modalities for robust person retrieval in challenging environments. The key challenge of Text-RGBT person retrieval lies in aligning text with multi-modal visual features. However, the inherent heterogeneity between visible and thermal modalities may interfere with the alignment between vision and language. To handle this problem, we propose a Decoupled Cross-modal Alignment network (DCAlign), which sufficiently mines the relationships between modality-specific and modality-collaborative visual with the text, for Text-RGBT person retrieval. To promote the research and development of this field, we create a high-quality Text-RGBT person retrieval dataset, RGBT-PEDES. RGBT-PEDES contains 1,822 identities from different age groups and genders with 4,723 pairs of calibrated RGB and T images, and covers high-diverse scenes from both daytime and nighttime with a various of challenges such as occlusion, weak alignment and adverse lighting conditions. Additionally, we carefully annotate 7,987 fine-grained textual descriptions for all RGBT person image pairs. Extensive experiments on RGBT-PEDES demonstrate that our method outperforms existing text-image person retrieval methods.