# Dynamic Token Selection for Aerial-Ground Person Re-Identification

arXiv: https://arxiv.org/abs/2412.00433 · HTML: https://mlsanity.com/paper/2412.00433/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 27 references that are in the map.
- First posted on arXiv 30 Nov 2024.

## Builds on (most cited first, 5 of 5)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)](https://mlsanity.com/paper/1711.09349/) (2017)
- [Self-supervised Image-specific Prototype Exploration for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.02909/) (2022)
- [Dissecting Person Re-identification from the Viewpoint of Viewpoint](https://mlsanity.com/paper/1812.02162/) (2018)
- [Camera-Driven Representation Learning for Unsupervised Domain Adaptive Person Re-identification](https://mlsanity.com/paper/2308.11901/) (2023)

## Built on by (most cited first, 5 of 5)

- [GSAlign: Geometric and Semantic Alignment Network for Aerial-Ground Person Re-Identification](https://mlsanity.com/paper/2510.22268/) (2025)
- [Person Recognition in Aerial Surveillance: A Decade Survey](https://mlsanity.com/paper/2511.17674/) (2025)
- [View-Aware Semantic Alignment for Aerial-Ground Person Re-Identification](https://mlsanity.com/paper/2605.18192/) (2026)
- [Rectifying Geometry-Induced Similarity Distortions for Real-World Aerial-Ground Person Re-Identification](https://mlsanity.com/paper/2601.21405/) (2026)
- [HiHR: Hierarchical Hyperbolic Representation for Aerial-Ground Person Re-Identification](https://mlsanity.com/paper/2607.09186/) (2026)

## Abstract (arXiv)

Aerial-Ground Person Re-identification (AGPReID) holds significant practical value but faces unique challenges due to pronounced variations in viewing angles, lighting conditions, and background interference. Traditional methods, often involving a global analysis of the entire image, frequently lead to inefficiencies and susceptibility to irrelevant data. In this paper, we propose a novel Dynamic Token Selective Transformer (DTST) tailored for AGPReID, which dynamically selects pivotal tokens to concentrate on pertinent regions. Specifically, we segment the input image into multiple tokens, with each token representing a unique region or feature within the image. Using a Top-k strategy, we extract the k most significant tokens that contain vital information essential for identity recognition. Subsequently, an attention mechanism is employed to discern interrelations among diverse tokens, thereby enhancing the representation of identity features. Extensive experiments on benchmark datasets showcases the superiority of our method over existing works. Notably, on the CARGO dataset, our proposed method gains 1.18% mAP improvements when compared to the second place. In addition, we comprehensively analyze the impact of different numbers of tokens, token insertion positions, and numbers of heads on model performance.