# Spatially and Temporally Efficient Non-local Attention Network for Video-based Person Re-Identification

arXiv: https://arxiv.org/abs/1908.01683 · HTML: https://mlsanity.com/paper/1908.01683/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Aug 2019.

## Built on by (most cited first, 23 of 23)

- [Video Transformers: A Survey](https://mlsanity.com/paper/2201.05991/) (2022)
- [Video-based Person Re-identification with Spatial and Temporal Memory Networks](https://mlsanity.com/paper/2108.09039/) (2021)
- [Dense Interaction Learning for Video-based Person Re-identification](https://mlsanity.com/paper/2103.09013/) (2021)
- [Deeply-Coupled Convolution-Transformer with Spatial-temporal Complementary Learning for Video-based Person Re-identification](https://mlsanity.com/paper/2304.14122/) (2023)
- [Spatiotemporal Transformer for Video-based Person Re-identification](https://mlsanity.com/paper/2103.16469/) (2021)
- [ShARc: Shape and Appearance Recognition for Person Identification In-the-wild](https://mlsanity.com/paper/2310.15946/) (2023)
- [Graph Convolution Based Efficient Re-Ranking for Visual Retrieval](https://mlsanity.com/paper/2306.08792/) (2023)
- [Keypoint Message Passing for Video-based Person Re-Identification](https://mlsanity.com/paper/2111.08279/) (2021)
- [Video Person Re-identification using Attribute-enhanced Features](https://mlsanity.com/paper/2108.06946/) (2021)
- [Activity-Biometrics: Person Identification from Daily Activities](https://mlsanity.com/paper/2403.17360/) (2024)
- [Graph Convolution for Re-ranking in Person Re-identification](https://mlsanity.com/paper/2107.02220/) (2021)
- [Poly-NL: Linear Complexity Non-local Layers with Polynomials](https://mlsanity.com/paper/2107.02859/) (2021)
- [Multi-Stage Spatio-Temporal Aggregation Transformer for Video Person Re-identification](https://mlsanity.com/paper/2301.00531/) (2023)
- [MovingFashion: a Benchmark for the Video-to-Shop Challenge](https://mlsanity.com/paper/2110.02627/) (2021)
- [Video-based Person Re-identification without Bells and Whistles](https://mlsanity.com/paper/2105.10678/) (2021)
- [Deep Learning for Video-based Person Re-Identification: A Survey](https://mlsanity.com/paper/2303.11332/) (2023)
- [Cross-view Semantic Alignment for Livestreaming Product Recognition](https://mlsanity.com/paper/2308.04912/) (2023)
- [Attention-based Shape and Gait Representations Learning for Video-based Cloth-Changing Person Re-Identification](https://mlsanity.com/paper/2402.03716/) (2024)
- [Stronger Baseline for Person Re-Identification](https://mlsanity.com/paper/2112.01059/) (2021)
- [Spatiotemporal Graph Guided Multi-modal Network for Livestreaming Product Retrieval](https://mlsanity.com/paper/2407.16248/) (2024)
- [CityGuard: Graph-Aware Private Descriptors for Bias-Resilient Identity Search Across Urban Cameras](https://mlsanity.com/paper/2602.18047/) (2026)
- [Person Re-identification based on Robust Features in Open-world](https://mlsanity.com/paper/2102.10798/) (2021)
- [Spatial-Temporal Expert Learning for Video-based Person Re-identification](https://mlsanity.com/paper/2607.01353/) (2026)

## Abstract (arXiv)

Video-based person re-identification (Re-ID) aims at matching video sequences of pedestrians across non-overlapping cameras. It is a practical yet challenging task of how to embed spatial and temporal information of a video into its feature representation. While most existing methods learn the video characteristics by aggregating image-wise features and designing attention mechanisms in Neural Networks, they only explore the correlation between frames at high-level features. In this work, we target at refining the intermediate features as well as high-level features with non-local attention operations and make two contributions. (i) We propose a Non-local Video Attention Network (NVAN) to incorporate video characteristics into the representation at multiple feature levels. (ii) We further introduce a Spatially and Temporally Efficient Non-local Video Attention Network (STE-NVAN) to reduce the computation complexity by exploring spatial and temporal redundancy presented in pedestrian videos. Extensive experiments show that our NVAN outperforms state-of-the-arts by 3.8% in rank-1 accuracy on MARS dataset and confirms our STE-NVAN displays a much superior computation footprint compared to existing methods.