# Keypoint-Aligned Embeddings for Image Retrieval and Re-identification

arXiv: https://arxiv.org/abs/2008.11368 · HTML: https://mlsanity.com/paper/2008.11368/

## Key facts

- Cited by 15 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 26 Aug 2020.

## Built on by (most cited first, 15 of 15)

- [Shape Preserving Facial Landmarks with Graph Attention Networks](https://mlsanity.com/paper/2210.07233/) (2022)
- [Semi-supervised Keypoint Localization](https://mlsanity.com/paper/2101.07988/) (2021)
- [Fine-grained Retrieval Prompt Tuning](https://mlsanity.com/paper/2207.14465/) (2022)
- [DVF: Advancing Robust and Accurate Fine-Grained Image Retrieval with Retrieval Guidelines](https://mlsanity.com/paper/2404.15771/) (2024)
- [NORPPA: NOvel Ringed seal re-identification by Pelage Pattern Aggregation](https://mlsanity.com/paper/2206.02498/) (2022)
- [Multi-query Vehicle Re-identification: Viewpoint-conditioned Network, Unified Dataset and New Metric](https://mlsanity.com/paper/2305.15764/) (2023)
- [Understanding the Impact of Training Set Size on Animal Re-identification](https://mlsanity.com/paper/2405.15976/) (2024)
- [Fine-grained Image Retrieval via Dual-Vision Adaptation](https://mlsanity.com/paper/2506.16273/) (2025)
- [Language-driven Fine-grained Retrieval](https://mlsanity.com/paper/2512.06255/) (2025)
- [Going Deeper into Semi-supervised Person Re-identification](https://mlsanity.com/paper/2107.11566/) (2021)
- [Variable Rate Neural Compression for Sparse Detector Data](https://mlsanity.com/paper/2411.11942/) (2024)
- [Adversarial Reconstruction Feedback for Robust Fine-grained Generalization](https://mlsanity.com/paper/2507.21742/) (2025)
- [Dual Prompt Learning for Adapting Vision-Language Models to Downstream Image-Text Retrieval](https://mlsanity.com/paper/2508.04028/) (2025)
- [Learning to Align Generative Appearance Priors for Fine-grained Image Retrieval](https://mlsanity.com/paper/2605.09859/) (2026)
- [Spotted: Location-informed Reidentification of Hyenas and Leopards in Camera Trap Surveys](https://mlsanity.com/paper/2607.00804/) (2026)

## Abstract (arXiv)

Learning embeddings that are invariant to the pose of the object is crucial in visual image retrieval and re-identification. The existing approaches for person, vehicle, or animal re-identification tasks suffer from high intra-class variance due to deformable shapes and different camera viewpoints. To overcome this limitation, we propose to align the image embedding with a predefined order of the keypoints. The proposed keypoint aligned embeddings model (KAE-Net) learns part-level features via multi-task learning which is guided by keypoint locations. More specifically, KAE-Net extracts channels from a feature map activated by a specific keypoint through learning the auxiliary task of heatmap reconstruction for this keypoint. The KAE-Net is compact, generic and conceptually simple. It achieves state of the art performance on the benchmark datasets of CUB-200-2011, Cars196 and VeRi-776 for retrieval and re-identification tasks.