# IAUnet: Global Context-Aware Feature Learning for Person Re-Identification

arXiv: https://arxiv.org/abs/2009.01035 · HTML: https://mlsanity.com/paper/2009.01035/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Sep 2020.

## Built on by (most cited first, 10 of 10)

- [Clothes-Changing Person Re-identification with RGB Modality Only](https://mlsanity.com/paper/2204.06890/) (2022)
- [BiCnet-TKS: Learning Efficient Spatial-Temporal Representation for Video Person Re-Identification](https://mlsanity.com/paper/2104.14783/) (2021)
- [MCUa: Multi-level Context and Uncertainty aware Dynamic Deep Ensemble for Breast Cancer Histology Image Classification](https://mlsanity.com/paper/2108.10709/) (2021)
- [A Novel Mix-normalization Method for Generalizable Multi-source Person Re-identification](https://mlsanity.com/paper/2201.09846/) (2022)
- [A Semantic-aware Attention and Visual Shielding Network for Cloth-changing Person Re-identification](https://mlsanity.com/paper/2207.08387/) (2022)
- [Clothes-Changing Person Re-Identification with Feasibility-Aware Intermediary Matching](https://mlsanity.com/paper/2404.09507/) (2024)
- [Tran-GCN: A Transformer-Enhanced Graph Convolutional Network for Person Re-Identification in Monitoring Videos](https://mlsanity.com/paper/2409.09391/) (2024)
- [Joint Counting, Detection and Re-Identification for Multi-Object Tracking](https://mlsanity.com/paper/2212.05861/) (2022)
- [Attribute Guided Sparse Tensor-Based Model for Person Re-Identification](https://mlsanity.com/paper/2108.04352/) (2021)
- [Benchmarking Attention Mechanisms and Consistency Regularization Semi-Supervised Learning for Post-Flood Building Damage Assessment in Satellite Images](https://mlsanity.com/paper/2412.03015/) (2024)

## Abstract (arXiv)

Person re-identification (reID) by CNNs based networks has achieved favorable performance in recent years. However, most of existing CNNs based methods do not take full advantage of spatial-temporal context modeling. In fact, the global spatial-temporal context can greatly clarify local distractions to enhance the target feature representation. To comprehensively leverage the spatial-temporal context information, in this work, we present a novel block, Interaction-Aggregation-Update (IAU), for high-performance person reID. Firstly, Spatial-Temporal IAU (STIAU) module is introduced. STIAU jointly incorporates two types of contextual interactions into a CNN framework for target feature learning. Here the spatial interactions learn to compute the contextual dependencies between different body parts of a single frame. While the temporal interactions are used to capture the contextual dependencies between the same body parts across all frames. Furthermore, a Channel IAU (CIAU) module is designed to model the semantic contextual interactions between channel features to enhance the feature representation, especially for small-scale visual cues and body parts. Therefore, the IAU block enables the feature to incorporate the globally spatial, temporal, and channel context. It is lightweight, end-to-end trainable, and can be easily plugged into existing CNNs to form IAUnet. The experiments show that IAUnet performs favorably against state-of-the-art on both image and video reID tasks and achieves compelling results on a general object categorization task. The source code is available at https://github.com/blue-blue272/ImgReID-IAnet.