# Person Search by Multi-Scale Matching

arXiv: https://arxiv.org/abs/1807.08582 · HTML: https://mlsanity.com/paper/1807.08582/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jul 2018.

## Built on by (most cited first, 30 of 36)

- [Anchor-Free Person Search](https://mlsanity.com/paper/2103.11617/) (2021)
- [Sequential End-to-end Network for Efficient Person Search](https://mlsanity.com/paper/2103.10148/) (2021)
- [Cascade Transformers for End-to-End Person Search](https://mlsanity.com/paper/2203.09642/) (2022)
- [PSTR: End-to-End One-Step Person Search With Transformers](https://mlsanity.com/paper/2204.03340/) (2022)
- [Decoupled and Memory-Reinforced Networks: Towards Effective Feature Learning for One-Step Person Search](https://mlsanity.com/paper/2102.10795/) (2021)
- [Exploring Visual Context for Weakly Supervised Person Search](https://mlsanity.com/paper/2106.10506/) (2021)
- [Weakly Supervised Person Search with Region Siamese Networks](https://mlsanity.com/paper/2109.06109/) (2021)
- [OIMNet++: Prototypical Normalization and Localization-aware Learning for Person Search](https://mlsanity.com/paper/2207.10320/) (2022)
- [ASMR: Learning Attribute-Based Person Search with Adaptive Semantic Margin Regularizer](https://mlsanity.com/paper/2108.04533/) (2021)
- [Text-based Person Search in Full Images via Semantic-Driven Proposal Generation](https://mlsanity.com/paper/2109.12965/) (2021)
- [Ground-to-Aerial Person Search: Benchmark Dataset and Approach](https://mlsanity.com/paper/2308.12712/) (2023)
- [Gallery Filter Network for Person Search](https://mlsanity.com/paper/2210.12903/) (2022)
- [Self-similarity Driven Scale-invariant Learning for Weakly Supervised Person Search](https://mlsanity.com/paper/2302.12986/) (2023)
- [Person Search Challenges and Solutions: A Survey](https://mlsanity.com/paper/2105.01605/) (2021)
- [Efficient Person Search: An Anchor-Free Approach](https://mlsanity.com/paper/2109.00211/) (2021)
- [MovieNet-PS: A Large-Scale Person Search Dataset in the Wild](https://mlsanity.com/paper/2112.02500/) (2021)
- [Deep Intra-Image Contrastive Learning for Weakly Supervised One-Step Person Search](https://mlsanity.com/paper/2302.04607/) (2023)
- [Making Person Search Enjoy the Merits of Person Re-identification](https://mlsanity.com/paper/2108.10536/) (2021)
- [CGUA: Context-Guided and Unpaired-Assisted Weakly Supervised Person Search](https://mlsanity.com/paper/2203.14307/) (2022)
- [Prompting Continual Person Search](https://mlsanity.com/paper/2410.19239/) (2024)
- [Head and Body: Unified Detector and Graph Network for Person Search in Media](https://mlsanity.com/paper/2111.13888/) (2021)
- [Learning Context-Aware Embedding for Person Search](https://mlsanity.com/paper/2111.14316/) (2021)
- [Grouped Adaptive Loss Weighting for Person Search](https://mlsanity.com/paper/2209.11492/) (2022)
- [PS-ARM: An End-to-End Attention-aware Relation Mixer Network for Person Search](https://mlsanity.com/paper/2210.03433/) (2022)
- [Sequential Transformer for End-to-End Person Search](https://mlsanity.com/paper/2211.04323/) (2022)
- [LEAPS: End-to-End One-Step Person Search With Learnable Proposals](https://mlsanity.com/paper/2303.11859/) (2023)
- [DDAM-PS: Diligent Domain Adaptive Mixer for Person Search](https://mlsanity.com/paper/2310.20706/) (2023)
- [Fast One-Stage Unsupervised Domain Adaptive Person Search](https://mlsanity.com/paper/2405.02832/) (2024)
- [Multi-Attribute Enhancement Network for Person Search](https://mlsanity.com/paper/2102.07968/) (2021)
- [Subtask-dominated Transfer Learning for Long-tail Person Search](https://mlsanity.com/paper/2112.00527/) (2021)

## Abstract (arXiv)

We consider the problem of person search in unconstrained scene images. Existing methods usually focus on improving the person detection accuracy to mitigate negative effects imposed by misalignment, mis-detections, and false alarms resulted from noisy people auto-detection. In contrast to previous studies, we show that sufficiently reliable person instance cropping is achievable by slightly improved state-of-the-art deep learning object detectors (e.g. Faster-RCNN), and the under-studied multi-scale matching problem in person search is a more severe barrier. In this work, we address this multi-scale person search challenge by proposing a Cross-Level Semantic Alignment (CLSA) deep learning approach capable of learning more discriminative identity feature representations in a unified end-to-end model. This is realised by exploiting the in-network feature pyramid structure of a deep neural network enhanced by a novel cross pyramid-level semantic alignment loss function. This favourably eliminates the need for constructing a computationally expensive image pyramid and a complex multi-branch network architecture. Extensive experiments show the modelling advantages and performance superiority of CLSA over the state-of-the-art person search and multi-scale matching methods on two large person search benchmarking datasets: CUHK-SYSU and PRW.