# CDPM: Convolutional Deformable Part Models for Semantically Aligned Person Re-identification

arXiv: https://arxiv.org/abs/1906.04976 · HTML: https://mlsanity.com/paper/1906.04976/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jun 2019.

## Built on by (most cited first, 8 of 8)

- [AAformer: Auto-Aligned Transformer for Person Re-Identification](https://mlsanity.com/paper/2104.00921/) (2021)
- [Person Re-identification: A Retrospective on Domain Specific Open Challenges and Future Trends](https://mlsanity.com/paper/2202.13121/) (2022)
- [Deep High-Resolution Representation Learning for Cross-Resolution Person Re-identification](https://mlsanity.com/paper/2105.11722/) (2021)
- [Attention-guided Progressive Mapping for Profile Face Recognition](https://mlsanity.com/paper/2106.14124/) (2021)
- [Unified Batch All Triplet Loss for Visible-Infrared Person Re-identification](https://mlsanity.com/paper/2103.04607/) (2021)
- [Weakly-supervised Part-Attention and Mentored Networks for Vehicle Re-Identification](https://mlsanity.com/paper/2107.08228/) (2021)
- [Context Sensing Attention Network for Video-based Person Re-identification](https://mlsanity.com/paper/2207.02631/) (2022)
- [End-to-End Context-Aided Unicity Matching for Person Re-identification](https://mlsanity.com/paper/2210.12008/) (2022)

## Abstract (arXiv)

Part-level representations are essential for robust person re-identification. However, common errors that arise during pedestrian detection frequently result in severe misalignment problems for body parts, which degrade the quality of part representations. Accordingly, to deal with this problem, we propose a novel model named Convolutional Deformable Part Models (CDPM). CDPM works by decoupling the complex part alignment procedure into two easier steps: first, a vertical alignment step detects each body part in the vertical direction, with the help of a multi-task learning model; second, a horizontal refinement step based on attention suppresses the background information around each detected body part. Since these two steps are performed orthogonally and sequentially, the difficulty of part alignment is significantly reduced. In the testing stage, CDPM is able to accurately align flexible body parts without any need for outside information. Extensive experimental results demonstrate the effectiveness of the proposed CDPM for part alignment. Most impressively, CDPM achieves state-of-the-art performance on three large-scale datasets: Market-1501, DukeMTMC-ReID,and CUHK03.