# Video-based Person Re-identification via 3D Convolutional Networks and Non-local Attention

arXiv: https://arxiv.org/abs/1807.05073 · HTML: https://mlsanity.com/paper/1807.05073/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jul 2018.

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

- [LambdaNetworks: Modeling Long-Range Interactions Without Attention](https://mlsanity.com/paper/2102.08602/) (2021)
- [Attention, please! A survey of Neural Attention Models in Deep Learning](https://mlsanity.com/paper/2103.16775/) (2021)
- [BiCnet-TKS: Learning Efficient Spatial-Temporal Representation for Video Person Re-Identification](https://mlsanity.com/paper/2104.14783/) (2021)
- [Feature Completion for Occluded Person Re-Identification](https://mlsanity.com/paper/2106.12733/) (2021)
- [Spatio-Temporal Representation Factorization for Video-based Person Re-Identification](https://mlsanity.com/paper/2107.11878/) (2021)
- [Deep learning-based person re-identification methods: A survey and outlook of recent works](https://mlsanity.com/paper/2110.04764/) (2021)
- [Multi-Stage Spatio-Temporal Aggregation Transformer for Video Person Re-identification](https://mlsanity.com/paper/2301.00531/) (2023)
- [Seq-Masks: Bridging the gap between appearance and gait modeling for video-based person re-identification](https://mlsanity.com/paper/2112.05626/) (2021)
- [Clothes-Changing Person Re-identification Based On Skeleton Dynamics](https://mlsanity.com/paper/2503.10759/) (2025)
- [Human Activity Recognition Using 3D Orthogonally-projected EfficientNet on Radar Time-Range-Doppler Signature](https://mlsanity.com/paper/2111.12375/) (2021)
- [Machine vision detection to daily facial fatigue with a nonlocal 3D attention network](https://mlsanity.com/paper/2104.10420/) (2021)
- [Using Auxiliary Information for Person Re-Identification -- A Tutorial Overview](https://mlsanity.com/paper/2211.08565/) (2022)
- [Revisiting the Role of Texture in 3D Person Re-identification](https://mlsanity.com/paper/2410.00348/) (2024)
- [Causality and "In-the-Wild" Video-Based Person Re-ID: A Survey](https://mlsanity.com/paper/2505.20540/) (2025)

## Abstract (arXiv)

Video-based person re-identification (ReID) is a challenging problem, where some video tracks of people across non-overlapping cameras are available for matching. Feature aggregation from a video track is a key step for video-based person ReID. Many existing methods tackle this problem by average/maximum temporal pooling or RNNs with attention. However, these methods cannot deal with temporal dependency and spatial misalignment problems at the same time. We are inspired by video action recognition that involves the identification of different actions from video tracks. Firstly, we use 3D convolutions on video volume, instead of using 2D convolutions across frames, to extract spatial and temporal features simultaneously. Secondly, we use a non-local block to tackle the misalignment problem and capture spatial-temporal long-range dependencies. As a result, the network can learn useful spatial-temporal information as a weighted sum of the features in all space and temporal positions in the input feature map. Experimental results on three datasets show that our framework outperforms state-of-the-art approaches by a large margin on multiple metrics.