# STNReID : Deep Convolutional Networks with Pairwise Spatial Transformer Networks for Partial Person Re-identification

arXiv: https://arxiv.org/abs/1903.07072 · HTML: https://mlsanity.com/paper/1903.07072/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Mar 2019.

## Built on by (most cited first, 23 of 23)

- [Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer](https://mlsanity.com/paper/2106.04095/) (2021)
- [Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification](https://mlsanity.com/paper/2205.02151/) (2022)
- [Learning Disentangled Representation Implicitly via Transformer for Occluded Person Re-Identification](https://mlsanity.com/paper/2107.02380/) (2021)
- [Cascade Transformers for End-to-End Person Search](https://mlsanity.com/paper/2203.09642/) (2022)
- [Region Generation and Assessment Network for Occluded Person Re-Identification](https://mlsanity.com/paper/2309.03558/) (2023)
- [Pose-Guided Feature Learning with Knowledge Distillation for Occluded Person Re-Identification](https://mlsanity.com/paper/2108.00139/) (2021)
- [Quality-aware Part Models for Occluded Person Re-identification](https://mlsanity.com/paper/2201.00107/) (2022)
- [Person Re-identification: A Retrospective on Domain Specific Open Challenges and Future Trends](https://mlsanity.com/paper/2202.13121/) (2022)
- [A Versatile Framework for Multi-scene Person Re-identification](https://mlsanity.com/paper/2403.11121/) (2024)
- [Automated data processing and feature engineering for deep learning and big data applications: a survey](https://mlsanity.com/paper/2403.11395/) (2024)
- [Multigranular Visual-Semantic Embedding for Cloth-Changing Person Re-identification](https://mlsanity.com/paper/2108.04527/) (2021)
- [Deep Learning-based Occluded Person Re-identification: A Survey](https://mlsanity.com/paper/2207.14452/) (2022)
- [Learning Feature Recovery Transformer for Occluded Person Re-identification](https://mlsanity.com/paper/2301.01879/) (2023)
- [Dual-Tuning: Joint Prototype Transfer and Structure Regularization for Compatible Feature Learning](https://mlsanity.com/paper/2108.02959/) (2021)
- [A Survey of the Self Supervised Learning Mechanisms for Vision Transformers](https://mlsanity.com/paper/2408.17059/) (2024)
- [Attention Disturbance and Dual-Path Constraint Network for Occluded Person Re-identification](https://mlsanity.com/paper/2303.10976/) (2023)
- [Transformers Meet Visual Learning Understanding: A Comprehensive Review](https://mlsanity.com/paper/2203.12944/) (2022)
- [A Novel end-to-end Framework for Occluded Pixel Reconstruction with Spatio-temporal Features for Improved Person Re-identification](https://mlsanity.com/paper/2304.07721/) (2023)
- [Dynamic Template Initialization for Part-Aware Person Re-ID](https://mlsanity.com/paper/2208.11440/) (2022)
- [DaliID: Distortion-Adaptive Learned Invariance for Identification Models](https://mlsanity.com/paper/2302.05753/) (2023)
- [Attention Map Guided Transformer Pruning for Edge Device](https://mlsanity.com/paper/2304.01452/) (2023)
- [DDRN:a Data Distribution Reconstruction Network for Occluded Person Re-Identification](https://mlsanity.com/paper/2410.06600/) (2024)
- [Cross-Spectral Body Recognition with Side Information Embedding: Benchmarks on LLCM and Analyzing Range-Induced Occlusions on IJB-MDF](https://mlsanity.com/paper/2506.08953/) (2025)

## Abstract (arXiv)

Partial person re-identification (ReID) is a challenging task because only partial information of person images is available for matching target persons. Few studies, especially on deep learning, have focused on matching partial person images with holistic person images. This study presents a novel deep partial ReID framework based on pairwise spatial transformer networks (STNReID), which can be trained on existing holistic person datasets. STNReID includes a spatial transformer network (STN) module and a ReID module. The STN module samples an affined image (a semantically corresponding patch) from the holistic image to match the partial image. The ReID module extracts the features of the holistic, partial, and affined images. Competition (or confrontation) is observed between the STN module and the ReID module, and two-stage training is applied to acquire a strong STNReID for partial ReID. Experimental results show that our STNReID obtains 66.7% and 54.6% rank-1 accuracies on partial ReID and partial iLIDS datasets, respectively. These values are at par with those obtained with state-of-the-art methods.