# G2DA: Geometry-Guided Dual-Alignment Learning for RGB-Infrared Person Re-Identification arXiv: https://arxiv.org/abs/2106.07853 ยท HTML: https://mlsanity.com/paper/2106.07853/ ## Key facts - Cited by 8 papers in the map (data through 14 Oct 2026). - Builds on 43 of its 88 references that are in the map. - First posted on arXiv 15 Jun 2021. ## Builds on (most cited first, 30 of 43) - [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017) - [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015) - [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014) - [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016) - [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017) - [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019) - [Computational Optimal Transport](https://mlsanity.com/paper/1803.00567/) (2018) - [Deep Learning for Person Re-identification: A Survey and Outlook](https://mlsanity.com/paper/2001.04193/) (2020) - [Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)](https://mlsanity.com/paper/1711.09349/) (2017) - [Optimal Transport for Domain Adaptation](https://mlsanity.com/paper/1507.00504/) (2015) - [Bag of Tricks and A Strong Baseline for Deep Person Re-identification](https://mlsanity.com/paper/1903.07071/) (2019) - [Contrastive Adaptation Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1901.00976/) (2019) - [UNITER: UNiversal Image-TExt Representation Learning](https://mlsanity.com/paper/1909.11740/) (2019) - [DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1803.10081/) (2018) - [Style Normalization and Restitution for Generalizable Person Re-identification](https://mlsanity.com/paper/2005.11037/) (2020) - [Large-Scale Optimal Transport and Mapping Estimation](https://mlsanity.com/paper/1711.02283/) (2017) - [Deep Multimodal Fusion by Channel Exchanging](https://mlsanity.com/paper/2011.05005/) (2020) - [Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2007.09314/) (2020) - [High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification](https://mlsanity.com/paper/2003.08177/) (2020) - [Scalable Gromov-Wasserstein Learning for Graph Partitioning and Matching](https://mlsanity.com/paper/1905.07645/) (2019) - [Graph Optimal Transport for Cross-Domain Alignment](https://mlsanity.com/paper/2006.14744/) (2020) - [RGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignment](https://mlsanity.com/paper/1910.05839/) (2019) - [DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model](https://mlsanity.com/paper/1605.03170/) (2016) - [Cross-modality Person re-identification with Shared-Specific Feature Transfer](https://mlsanity.com/paper/2002.12489/) (2020) - [Cross-Modality Paired-Images Generation for RGB-Infrared Person Re-Identification](https://mlsanity.com/paper/2002.04114/) (2020) - [Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/1912.01230/) (2019) - [Signed Graph Attention Networks](https://mlsanity.com/paper/1906.10958/) (2019) - [AANet: Attribute Attention Network for Person Re-Identifications](https://mlsanity.com/paper/1912.09021/) (2019) - [Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification](https://mlsanity.com/paper/1710.06555/) (2017) - [Attention-Aware Compositional Network for Person Re-identification](https://mlsanity.com/paper/1805.03344/) (2018) ## Built on by (most cited first, 8 of 8) - [Modality-Adaptive Mixup and Invariant Decomposition for RGB-Infrared Person Re-Identification](https://mlsanity.com/paper/2203.01735/) (2022) - [Shape-centered Representation Learning for Visible-Infrared Person Re-identification](https://mlsanity.com/paper/2310.17952/) (2023) - [Visible-Infrared Person Re-Identification via Patch-Mixed Cross-Modality Learning](https://mlsanity.com/paper/2302.08212/) (2023) - [Adaptive Generation of Privileged Intermediate Information for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2307.03240/) (2023) - [Homogeneous and Heterogeneous Relational Graph for Visible-infrared Person Re-identification](https://mlsanity.com/paper/2109.08811/) (2021) - [MSCMNet: Multi-scale Semantic Correlation Mining for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2311.14395/) (2023) - [Bidirectional Multi-Step Domain Generalization for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2403.10782/) (2024) - [LASFNet: A Lightweight Attention-Guided Self-Modulation Feature Fusion Network for Multimodal Object Detection](https://mlsanity.com/paper/2506.21018/) (2025) ## Abstract (arXiv) RGB-Infrared (IR) person re-identification aims to retrieve person-of-interest from heterogeneous cameras, easily suffering from large image modality discrepancy caused by different sensing wavelength ranges. Existing work usually minimizes such discrepancy by aligning domain distribution of global features, while neglecting the intra-modality structural relations between semantic parts. This could result in the network overly focusing on local cues, without considering long-range body part dependencies, leading to meaningless region representations. In this paper, we propose a graph-enabled distribution matching solution, dubbed Geometry-Guided Dual-Alignment (G2DA) learning, for RGB-IR ReID. It can jointly encourage the cross-modal consistency between part semantics and structural relations for fine-grained modality alignment by solving a graph matching task within a multi-scale skeleton graph that embeds human topology information. Specifically, we propose to build a semantic-aligned complete graph into which all cross-modality images can be mapped via a pose-adaptive graph construction mechanism. This graph represents extracted whole-part features by nodes and expresses the node-wise similarities with associated edges. To achieve the graph-based dual-alignment learning, an Optimal Transport (OT) based structured metric is further introduced to simultaneously measure point-wise relations and group-wise structural similarities across modalities. By minimizing the cost of an inter-modality transport plan, G2DA can learn a consistent and discriminative feature subspace for cross-modality image retrieval. Furthermore, we advance a Message Fusion Attention (MFA) mechanism to adaptively reweight the information flow of semantic propagation, effectively strengthening the discriminability of extracted semantic features.