# Gated Siamese Convolutional Neural Network Architecture for Human Re-Identification

arXiv: https://arxiv.org/abs/1607.08378 · HTML: https://mlsanity.com/paper/1607.08378/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jul 2016.

## Built on by (most cited first, 30 of 34)

- [Simple Cues Lead to a Strong Multi-Object Tracker](https://mlsanity.com/paper/2206.04656/) (2022)
- [Eliminate Deviation with Deviation for Data Augmentation and a General Multi-modal Data Learning Method](https://mlsanity.com/paper/2101.08533/) (2021)
- [Simple, Effective and General: A New Backbone for Cross-view Image Geo-localization](https://mlsanity.com/paper/2302.01572/) (2023)
- [Deep learning-based person re-identification methods: A survey and outlook of recent works](https://mlsanity.com/paper/2110.04764/) (2021)
- [Less is More: Learning from Synthetic Data with Fine-grained Attributes for Person Re-Identification](https://mlsanity.com/paper/2109.10498/) (2021)
- [MSO: Multi-Feature Space Joint Optimization Network for RGB-Infrared Person Re-Identification](https://mlsanity.com/paper/2110.11264/) (2021)
- [Pose-driven Attention-guided Image Generation for Person Re-Identification](https://mlsanity.com/paper/2104.13773/) (2021)
- [Holistic Guidance for Occluded Person Re-Identification](https://mlsanity.com/paper/2104.06524/) (2021)
- [Online and Real-Time Tracking in a Surveillance Scenario](https://mlsanity.com/paper/2106.01153/) (2021)
- [Unsupervised Person Re-identification with Stochastic Training Strategy](https://mlsanity.com/paper/2108.06938/) (2021)
- [Video Person Re-identification using Attribute-enhanced Features](https://mlsanity.com/paper/2108.06946/) (2021)
- [Rethinking Person Re-Identification via Semantic-Based Pretraining](https://mlsanity.com/paper/2110.05074/) (2021)
- [The Group Loss++: A deeper look into group loss for deep metric learning](https://mlsanity.com/paper/2204.01509/) (2022)
- [Multi-Stage Spatio-Temporal Aggregation Transformer for Video Person Re-identification](https://mlsanity.com/paper/2301.00531/) (2023)
- [SHD360: A Benchmark Dataset for Salient Human Detection in 360deg Videos](https://mlsanity.com/paper/2105.11578/) (2021)
- [Domain Adaptive Egocentric Person Re-identification](https://mlsanity.com/paper/2103.04870/) (2021)
- [Adaptive Affinity for Associations in Multi-Target Multi-Camera Tracking](https://mlsanity.com/paper/2112.07664/) (2021)
- [Towards Homogeneous Modality Learning and Multi-Granularity Information Exploration for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2204.04842/) (2022)
- [Pose Invariant Person Re-Identification using Robust Pose-transformation GAN](https://mlsanity.com/paper/2105.00930/) (2021)
- [TAGPerson: A Target-Aware Generation Pipeline for Person Re-identification](https://mlsanity.com/paper/2112.14239/) (2021)
- [InstantGroup: Instant Template Generation for Scalable Group of Brain MRI Registration](https://mlsanity.com/paper/2211.05622/) (2022)
- [Semantic Consistency and Identity Mapping Multi-Component Generative Adversarial Network for Person Re-Identification](https://mlsanity.com/paper/2104.13780/) (2021)
- [Unsupervised Domain Adaptive Person Re-id with Local-enhance and Prototype Dictionary Learning](https://mlsanity.com/paper/2201.03803/) (2022)
- [TDT: Teaching Detectors to Track without Fully Annotated Videos](https://mlsanity.com/paper/2205.05583/) (2022)
- [Unsupervised Person Re-identification via Multi-Label Prediction and Classification based on Graph-Structural Insight](https://mlsanity.com/paper/2106.08798/) (2021)
- [Learning Deep Optimal Embeddings with Sinkhorn Divergences](https://mlsanity.com/paper/2209.06469/) (2022)
- [Deep learning-based stereo camera multi-video synchronization](https://mlsanity.com/paper/2303.12916/) (2023)
- [Learning Scene Flow With Skeleton Guidance For 3D Action Recognition](https://mlsanity.com/paper/2306.13285/) (2023)
- [Automatic nodule identification and differentiation in ultrasound videos to facilitate per-nodule examination](https://mlsanity.com/paper/2310.06339/) (2023)
- [When the Few Outweigh the Many: Illicit Content Recognition with Few-Shot Learning](https://mlsanity.com/paper/2311.17026/) (2023)

## Abstract (arXiv)

Matching pedestrians across multiple camera views, known as human re-identification, is a challenging research problem that has numerous applications in visual surveillance. With the resurgence of Convolutional Neural Networks (CNNs), several end-to-end deep Siamese CNN architectures have been proposed for human re-identification with the objective of projecting the images of similar pairs (i.e. same identity) to be closer to each other and those of dissimilar pairs to be distant from each other. However, current networks extract fixed representations for each image regardless of other images which are paired with it and the comparison with other images is done only at the final level. In this setting, the network is at risk of failing to extract finer local patterns that may be essential to distinguish positive pairs from hard negative pairs. In this paper, we propose a gating function to selectively emphasize such fine common local patterns by comparing the mid-level features across pairs of images. This produces flexible representations for the same image according to the images they are paired with. We conduct experiments on the CUHK03, Market-1501 and VIPeR datasets and demonstrate improved performance compared to a baseline Siamese CNN architecture.