# Moving Towards Centers: Re-ranking with Attention and Memory for Re-identification

arXiv: https://arxiv.org/abs/2105.01447 · HTML: https://mlsanity.com/paper/2105.01447/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 53 references that are in the map.
- First posted on arXiv 4 May 2021.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [Image Transformer](https://mlsanity.com/paper/1802.05751/) (2018)
- [Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking](https://mlsanity.com/paper/1609.01775/) (2016)
- [Fine-tuning CNN Image Retrieval with No Human Annotation](https://mlsanity.com/paper/1711.02512/) (2017)
- [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017)
- [Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)](https://mlsanity.com/paper/1711.09349/) (2017)
- [TransReID: Transformer-based Object Re-Identification](https://mlsanity.com/paper/2102.04378/) (2021)
- [Re-ranking Person Re-identification with k-reciprocal Encoding](https://mlsanity.com/paper/1701.08398/) (2017)
- [Person Re-identification in the Wild](https://mlsanity.com/paper/1604.02531/) (2016)
- [A Strong Baseline and Batch Normalization Neck for Deep Person Re-identification](https://mlsanity.com/paper/1906.08332/) (2019)
- [A Pose-Sensitive Embedding for Person Re-Identification with Expanded Cross Neighborhood Re-Ranking](https://mlsanity.com/paper/1711.10378/) (2017)
- [Multi-Level Factorisation Net for Person Re-Identification](https://mlsanity.com/paper/1803.09132/) (2018)
- [Multi-scale Deep Learning Architectures for Person Re-identification](https://mlsanity.com/paper/1709.05165/) (2017)
- [VehicleNet: Learning Robust Visual Representation for Vehicle Re-identification](https://mlsanity.com/paper/2004.06305/) (2020)
- [The Devil is in the Details: Self-Supervised Attention for Vehicle Re-Identification](https://mlsanity.com/paper/2004.06271/) (2020)
- [Understanding Image Retrieval Re-Ranking: A Graph Neural Network Perspective](https://mlsanity.com/paper/2012.07620/) (2020)
- [Resource Aware Person Re-identification across Multiple Resolutions](https://mlsanity.com/paper/1805.08805/) (2018)
- [Attribute-guided Feature Learning Network for Vehicle Re-identification](https://mlsanity.com/paper/2001.03872/) (2020)
- [Visual Tracking via Dynamic Memory Networks](https://mlsanity.com/paper/1907.07613/) (2019)
- [Divide and Fuse: A Re-ranking Approach for Person Re-identification](https://mlsanity.com/paper/1708.04169/) (2017)
- [Memory-Augmented Temporal Dynamic Learning for Action Recognition](https://mlsanity.com/paper/1904.13080/) (2019)

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

- [Adaptive Split-Fusion Transformer](https://mlsanity.com/paper/2204.12196/) (2022)
- [OccluTrack: Rethinking Awareness of Occlusion for Enhancing Multiple Pedestrian Tracking](https://mlsanity.com/paper/2309.10360/) (2023)
- [CarGait: Cross-Attention based Re-ranking for Gait recognition](https://mlsanity.com/paper/2503.03501/) (2025)
- [Weakly-supervised Part-Attention and Mentored Networks for Vehicle Re-Identification](https://mlsanity.com/paper/2107.08228/) (2021)
- [Homogeneous and Heterogeneous Consistency progressive Re-ranking for Visible-Infrared Person Re-identification](https://mlsanity.com/paper/2603.16165/) (2026)

## Abstract (arXiv)

Re-ranking utilizes contextual information to optimize the initial ranking list of person or vehicle re-identification (re-ID), which boosts the retrieval performance at post-processing steps. This paper proposes a re-ranking network to predict the correlations between the probe and top-ranked neighbor samples. Specifically, all the feature embeddings of query and gallery images are expanded and enhanced by a linear combination of their neighbors, with the correlation prediction serving as discriminative combination weights. The combination process is equivalent to moving independent embeddings toward the identity centers, improving cluster compactness. For correlation prediction, we first aggregate the contextual information for probe's k-nearest neighbors via the Transformer encoder. Then, we distill and refine the probe-related features into the Contextual Memory cell via attention mechanism. Like humans that retrieve images by not only considering probe images but also memorizing the retrieved ones, the Contextual Memory produces multi-view descriptions for each instance. Finally, the neighbors are reconstructed with features fetched from the Contextual Memory, and a binary classifier predicts their correlations with the probe. Experiments on six widely-used person and vehicle re-ID benchmarks demonstrate the effectiveness of the proposed method. Especially, our method surpasses the state-of-the-art re-ranking approaches on large-scale datasets by a significant margin, i.e., with an average 4.83% CMC@1 and 14.83% mAP improvements on VERI-Wild, MSMT17, and VehicleID datasets.