# Video Person Re-identification by Temporal Residual Learning

arXiv: https://arxiv.org/abs/1802.07918 · HTML: https://mlsanity.com/paper/1802.07918/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Feb 2018.

## Built on by (most cited first, 19 of 19)

- [Watching You: Global-guided Reciprocal Learning for Video-based Person Re-identification](https://mlsanity.com/paper/2103.04337/) (2021)
- [TF-CLIP: Learning Text-free CLIP for Video-based Person Re-Identification](https://mlsanity.com/paper/2312.09627/) (2023)
- [Magic Tokens: Select Diverse Tokens for Multi-modal Object Re-Identification](https://mlsanity.com/paper/2403.10254/) (2024)
- [A Video Is Worth Three Views: Trigeminal Transformers for Video-based Person Re-identification](https://mlsanity.com/paper/2104.01745/) (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)
- [Person Re-identification: A Retrospective on Domain Specific Open Challenges and Future Trends](https://mlsanity.com/paper/2202.13121/) (2022)
- [Video-based Person Re-identification with Long Short-Term Representation Learning](https://mlsanity.com/paper/2308.03703/) (2023)
- [ShARc: Shape and Appearance Recognition for Person Identification In-the-wild](https://mlsanity.com/paper/2310.15946/) (2023)
- [HAMoBE: Hierarchical and Adaptive Mixture of Biometric Experts for Video-based Person ReID](https://mlsanity.com/paper/2508.05038/) (2025)
- [Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey](https://mlsanity.com/paper/2205.10766/) (2022)
- [Activity-Biometrics: Person Identification from Daily Activities](https://mlsanity.com/paper/2403.17360/) (2024)
- [Features Reconstruction Disentanglement Cloth-Changing Person Re-Identification](https://mlsanity.com/paper/2407.10694/) (2024)
- [SAS-VPReID: A Scale-Adaptive Framework with Shape Priors for Video-based Person Re-Identification at Extreme Far Distances](https://mlsanity.com/paper/2601.05535/) (2026)
- [Dynamic Patch-aware Enrichment Transformer for Occluded Person Re-Identification](https://mlsanity.com/paper/2402.10435/) (2024)
- [A hierarchical residual network with compact triplet-center loss for sketch recognition](https://mlsanity.com/paper/2109.13536/) (2021)
- [TVPR: Text-to-Video Person Retrieval and a New Benchmark](https://mlsanity.com/paper/2307.07184/) (2023)
- [Skeletons Speak Louder than Text: A Motion-Aware Pretraining Paradigm for Video-Based Person Re-Identification](https://mlsanity.com/paper/2511.13150/) (2025)
- [Beyond Pedestrians: Caption-Guided CLIP Framework for High-Difficulty Video-based Person Re-Identification](https://mlsanity.com/paper/2604.07740/) (2026)

## Abstract (arXiv)

In this paper, we propose a novel feature learning framework for video person re-identification (re-ID). The proposed framework largely aims to exploit the adequate temporal information of video sequences and tackle the poor spatial alignment of moving pedestrians. More specifically, for exploiting the temporal information, we design a temporal residual learning (TRL) module to simultaneously extract the generic and specific features of consecutive frames. The TRL module is equipped with two bi-directional LSTM (BiLSTM), which are respectively responsible to describe a moving person in different aspects, providing complementary information for better feature representations. To deal with the poor spatial alignment in video re-ID datasets, we propose a spatial-temporal transformer network (ST^2N) module. Transformation parameters in the ST^2N module are learned by leveraging the high-level semantic information of the current frame as well as the temporal context knowledge from other frames. The proposed ST^2N module with less learnable parameters allows effective person alignments under significant appearance changes. Extensive experimental results on the large-scale MARS, PRID2011, ILIDS-VID and SDU-VID datasets demonstrate that the proposed method achieves consistently superior performance and outperforms most of the very recent state-of-the-art methods.