{"type":"ScholarlyArticle","title":"Multi-Granularity Graph-Convolution-Based Method for Weakly Supervised Person Search","authors":[{"name":"Haichun Tai","slug":"haichun-tai","given":"Haichun","family":"Tai","affiliation":""},{"name":"De Cheng","slug":"de-cheng","given":"De","family":"Cheng","affiliation":""},{"name":"Jie Li","slug":"jie-li","given":"Jie","family":"Li","affiliation":""},{"name":"Nannan Wang","slug":"nannan-wang","given":"Nannan","family":"Wang","affiliation":""},{"name":"Xinbo Gao","slug":"xinbo-gao","given":"Xinbo","family":"Gao","affiliation":""}],"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.","doi":"10.24963/ijcai.2024/147","url":"https://ijcai.org/proceedings/2024/147","pdf":"https://ijcai.org/proceedings/2024/0147.pdf","markdown":"https://ijcai.org/proceedings/2024/147.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/147","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Computer Vision","track":"Main Track","number":147,"pages":{"first":1326,"last":1334},"keywords":["Computer Vision: CV: Representation learning","Computer Vision: CV: Recognition (object detection, categorization)","Computer Vision: CV: Image and video retrieval"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}