# Where-and-When to Look: Deep Siamese Attention Networks for Video-based Person Re-identification

arXiv: https://arxiv.org/abs/1808.01911 · HTML: https://mlsanity.com/paper/1808.01911/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Aug 2018.

## Built on by (most cited first, 14 of 14)

- [Accelerating DETR Convergence via Semantic-Aligned Matching](https://mlsanity.com/paper/2203.06883/) (2022)
- [Graph Convolution Based Efficient Re-Ranking for Visual Retrieval](https://mlsanity.com/paper/2306.08792/) (2023)
- [Exploring the Quality of GAN Generated Images for Person Re-Identification](https://mlsanity.com/paper/2108.09977/) (2021)
- [Video Person Re-identification using Attribute-enhanced Features](https://mlsanity.com/paper/2108.06946/) (2021)
- [Semantic-Aligned Matching for Enhanced DETR Convergence and Multi-Scale Feature Fusion](https://mlsanity.com/paper/2207.14172/) (2022)
- [Color Prompting for Data-Free Continual Unsupervised Domain Adaptive Person Re-Identification](https://mlsanity.com/paper/2308.10716/) (2023)
- [Multi-Stage Spatio-Temporal Aggregation Transformer for Video Person Re-identification](https://mlsanity.com/paper/2301.00531/) (2023)
- [Intra-class Adaptive Augmentation with Neighbor Correction for Deep Metric Learning](https://mlsanity.com/paper/2211.16264/) (2022)
- [Generalizable Metric Network for Cross-domain Person Re-identification](https://mlsanity.com/paper/2306.11991/) (2023)
- [Self-Paced Uncertainty Estimation for One-shot Person Re-Identification](https://mlsanity.com/paper/2104.09152/) (2021)
- [Cross-Camera Trajectories Help Person Retrieval in a Camera Network](https://mlsanity.com/paper/2204.12900/) (2022)
- [Person detection and re-identification in open-world settings of retail stores and public spaces](https://mlsanity.com/paper/2505.00772/) (2025)
- [Causality and "In-the-Wild" Video-Based Person Re-ID: A Survey](https://mlsanity.com/paper/2505.20540/) (2025)
- [AI-T2I: Aggregating-and-Isolating Cross-Attention to Diffusion Models for Text-to-Image Synthesis](https://mlsanity.com/paper/2605.25763/) (2026)

## Abstract (arXiv)

Video-based person re-identification (re-id) is a central application in surveillance systems with significant concern in security. Matching persons across disjoint camera views in their video fragments is inherently challenging due to the large visual variations and uncontrolled frame rates. There are two steps crucial to person re-id, namely discriminative feature learning and metric learning. However, existing approaches consider the two steps independently, and they do not make full use of the temporal and spatial information in videos. In this paper, we propose a Siamese attention architecture that jointly learns spatiotemporal video representations and their similarity metrics. The network extracts local convolutional features from regions of each frame, and enhance their discriminative capability by focusing on distinct regions when measuring the similarity with another pedestrian video. The attention mechanism is embedded into spatial gated recurrent units to selectively propagate relevant features and memorize their spatial dependencies through the network. The model essentially learns which parts (where) from which frames (when) are relevant and distinctive for matching persons and attaches higher importance therein. The proposed Siamese model is end-to-end trainable to jointly learn comparable hidden representations for paired pedestrian videos and their similarity value. Extensive experiments on three benchmark datasets show the effectiveness of each component of the proposed deep network while outperforming state-of-the-art methods.