---
title: "Multi-Granularity Graph-Convolution-Based Method for Weakly Supervised Person Search"
authors:
  - "Haichun Tai"
  - "De Cheng"
  - "Jie Li"
  - "Nannan Wang"
  - "Xinbo Gao"
doi: "10.24963/ijcai.2024/147"
url: "https://ijcai.org/proceedings/2024/147"
pdf: "https://ijcai.org/proceedings/2024/0147.pdf"
venue: "Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence"
year: 2024
pages: "1326-1334"
track: "Main Track"
keywords:
  - "Computer Vision: CV: Representation learning"
  - "Computer Vision: CV: Recognition (object detection, categorization)"
  - "Computer Vision: CV: Image and video retrieval"
---

# Multi-Granularity Graph-Convolution-Based Method for Weakly Supervised Person Search

Haichun Tai, De Cheng, Jie Li, Nannan Wang, Xinbo Gao

*Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence*, pages 1326-1334. DOI: [10.24963/ijcai.2024/147](https://doi.org/10.24963/ijcai.2024/147)

## Abstract

One-step Weakly Supervised Person Search (WSPS) jointly performs pedestrian detection and person Re-IDentification (ReID) only with bounding box annotations, which makes the traditional person ReID problem more suitable and efficient for real-world applications. However, this task is very challenging due to the following reasons: 1) large feature gap between person ReID and general object detection tasks when learning shared representations; 2) difficult pseudo identity estimation for each person image with unrefined raw detection and dramatic scale changes. To address above issues, we propose a multi-granularity graph convolution framework to jointly optimize the aligned task features, as well as to assist the pseudo label estimation. Specifically, the multi-granularity feature alignment module (MFA) in the designed two-branch framework, employs cluster-level bi-directional interaction of various granularity information to narrow down the large feature gap. Further, upon the MFA module, we introduce the multi-granularity graph-convolution-based pseudo-label estimation module, to enhance feature representations for distinguishing diverse identities. Extensive experimental results demonstrate the effectiveness of the proposed method, and show superior performances to state-of-the art methods by a large margin on CUHK-SYSU and PRW datasets.