# Pedestrian Alignment Network for Large-scale Person Re-identification

arXiv: https://arxiv.org/abs/1707.00408 · HTML: https://mlsanity.com/paper/1707.00408/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jul 2017.

## Built on by (most cited first, 26 of 26)

- [Attention Mechanisms in Computer Vision: A Survey](https://mlsanity.com/paper/2111.07624/) (2021)
- [A Transformer-Based Feature Segmentation and Region Alignment Method For UAV-View Geo-Localization](https://mlsanity.com/paper/2201.09206/) (2022)
- [Attention, please! A survey of Neural Attention Models in Deep Learning](https://mlsanity.com/paper/2103.16775/) (2021)
- [Behavioral Intention Prediction in Driving Scenes: A Survey](https://mlsanity.com/paper/2211.00385/) (2022)
- [Person Re-identification: A Retrospective on Domain Specific Open Challenges and Future Trends](https://mlsanity.com/paper/2202.13121/) (2022)
- [Multigranular Visual-Semantic Embedding for Cloth-Changing Person Re-identification](https://mlsanity.com/paper/2108.04527/) (2021)
- [RealGait: Gait Recognition for Person Re-Identification](https://mlsanity.com/paper/2201.04806/) (2022)
- [StepNet: Spatial-temporal Part-aware Network for Isolated Sign Language Recognition](https://mlsanity.com/paper/2212.12857/) (2022)
- [Approaching Outside: Scaling Unsupervised 3D Object Detection from 2D Scene](https://mlsanity.com/paper/2407.08569/) (2024)
- [Exploring Modality-shared Appearance Features and Modality-invariant Relation Features for Cross-modality Person Re-Identification](https://mlsanity.com/paper/2104.11539/) (2021)
- [MDFM: Multi-Decision Fusing Model for Few-Shot Learning](https://mlsanity.com/paper/2112.00690/) (2021)
- [GCT: Graph Co-Training for Semi-Supervised Few-Shot Learning](https://mlsanity.com/paper/2203.07738/) (2022)
- [Exploring Shape Embedding for Cloth-Changing Person Re-Identification via 2D-3D Correspondences](https://mlsanity.com/paper/2310.18438/) (2023)
- [Deep Miner: A Deep and Multi-branch Network which Mines Rich and Diverse Features for Person Re-identification](https://mlsanity.com/paper/2102.09321/) (2021)
- [Towards Efficient Object Re-Identification with A Novel Cloud-Edge Collaborative Framework](https://mlsanity.com/paper/2401.02041/) (2024)
- [Video-based Person Re-identification without Bells and Whistles](https://mlsanity.com/paper/2105.10678/) (2021)
- [A Semantic-aware Attention and Visual Shielding Network for Cloth-changing Person Re-identification](https://mlsanity.com/paper/2207.08387/) (2022)
- [Pose Invariant Person Re-Identification using Robust Pose-transformation GAN](https://mlsanity.com/paper/2105.00930/) (2021)
- [PSDiff: Diffusion Model for Person Search with Iterative and Collaborative Refinement](https://mlsanity.com/paper/2309.11125/) (2023)
- [Tran-GCN: A Transformer-Enhanced Graph Convolutional Network for Person Re-Identification in Monitoring Videos](https://mlsanity.com/paper/2409.09391/) (2024)
- [Self-Paced Uncertainty Estimation for One-shot Person Re-Identification](https://mlsanity.com/paper/2104.09152/) (2021)
- [Weakly-supervised Part-Attention and Mentored Networks for Vehicle Re-Identification](https://mlsanity.com/paper/2107.08228/) (2021)
- [Dual-level Interaction for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2307.07972/) (2023)
- [FADE: A Dataset for Detecting Falling Objects around Buildings in Video](https://mlsanity.com/paper/2408.05750/) (2024)
- [Attribute Guided Sparse Tensor-Based Model for Person Re-Identification](https://mlsanity.com/paper/2108.04352/) (2021)
- [Adaptive Template Enhancement for Improved Person Recognition using Small Datasets](https://mlsanity.com/paper/2201.01218/) (2022)

## Abstract (arXiv)

Person re-identification (person re-ID) is mostly viewed as an image retrieval problem. This task aims to search a query person in a large image pool. In practice, person re-ID usually adopts automatic detectors to obtain cropped pedestrian images. However, this process suffers from two types of detector errors: excessive background and part missing. Both errors deteriorate the quality of pedestrian alignment and may compromise pedestrian matching due to the position and scale variances. To address the misalignment problem, we propose that alignment can be learned from an identification procedure. We introduce the pedestrian alignment network (PAN) which allows discriminative embedding learning and pedestrian alignment without extra annotations. Our key observation is that when the convolutional neural network (CNN) learns to discriminate between different identities, the learned feature maps usually exhibit strong activations on the human body rather than the background. The proposed network thus takes advantage of this attention mechanism to adaptively locate and align pedestrians within a bounding box. Visual examples show that pedestrians are better aligned with PAN. Experiments on three large-scale re-ID datasets confirm that PAN improves the discriminative ability of the feature embeddings and yields competitive accuracy with the state-of-the-art methods.