# A Multi-task Deep Network for Person Re-identification

arXiv: https://arxiv.org/abs/1607.05369 · HTML: https://mlsanity.com/paper/1607.05369/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2016.

## Built on by (most cited first, 9 of 9)

- [Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks](https://mlsanity.com/paper/2303.17602/) (2023)
- [AAformer: Auto-Aligned Transformer for Person Re-Identification](https://mlsanity.com/paper/2104.00921/) (2021)
- [Learning Domain Invariant Representations for Generalizable Person Re-Identification](https://mlsanity.com/paper/2103.15890/) (2021)
- [Graph Convolution Based Efficient Re-Ranking for Visual Retrieval](https://mlsanity.com/paper/2306.08792/) (2023)
- [Learning Instance-level Spatial-Temporal Patterns for Person Re-identification](https://mlsanity.com/paper/2108.00171/) (2021)
- [Graph Convolution for Re-ranking in Person Re-identification](https://mlsanity.com/paper/2107.02220/) (2021)
- [Semantic Consistency and Identity Mapping Multi-Component Generative Adversarial Network for Person Re-Identification](https://mlsanity.com/paper/2104.13780/) (2021)
- [AdaTriplet-RA: Domain Matching via Adaptive Triplet and Reinforced Attention for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2211.08894/) (2022)
- [Attribute Guided Sparse Tensor-Based Model for Person Re-Identification](https://mlsanity.com/paper/2108.04352/) (2021)

## Abstract (arXiv)

Person re-identification (ReID) focuses on identifying people across different scenes in video surveillance, which is usually formulated as a binary classification task or a ranking task in current person ReID approaches. In this paper, we take both tasks into account and propose a multi-task deep network (MTDnet) that makes use of their own advantages and jointly optimize the two tasks simultaneously for person ReID. To the best of our knowledge, we are the first to integrate both tasks in one network to solve the person ReID. We show that our proposed architecture significantly boosts the performance. Furthermore, deep architecture in general requires a sufficient dataset for training, which is usually not met in person ReID. To cope with this situation, we further extend the MTDnet and propose a cross-domain architecture that is capable of using an auxiliary set to assist training on small target sets. In the experiments, our approach outperforms most of existing person ReID algorithms on representative datasets including CUHK03, CUHK01, VIPeR, iLIDS and PRID2011, which clearly demonstrates the effectiveness of the proposed approach.