DHRNet: A Dual-Path Hierarchical Relation Network for Multi-Person Pose Estimation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929329749884928 |
|---|---|
| author | Dang, Yonghao Yin, Jianqin Liu, Liyuan Ding, Pengxiang Sun, Yuan Hu, Yanzhu |
| author_facet | Dang, Yonghao Yin, Jianqin Liu, Liyuan Ding, Pengxiang Sun, Yuan Hu, Yanzhu |
| contents | Multi-person pose estimation (MPPE) presents a formidable yet crucial challenge in computer vision. Most existing methods predominantly concentrate on isolated interaction either between instances or joints, which is inadequate for scenarios demanding concurrent localization of both instances and joints. This paper introduces a novel CNN-based single-stage method, named Dual-path Hierarchical Relation Network (DHRNet), to extract instance-to-joint and joint-to-instance interactions concurrently. Specifically, we design a dual-path interaction modeling module (DIM) that strategically organizes cross-instance and cross-joint interaction modeling modules in two complementary orders, enriching interaction information by integrating merits from different correlation modeling branches. Notably, DHRNet excels in joint localization by leveraging information from other instances and joints. Extensive evaluations on challenging datasets, including COCO, CrowdPose, and OCHuman datasets, showcase DHRNet's state-of-the-art performance. The code will be released at https://github.com/YHDang/dhrnet-multi-pose-estimation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_14025 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DHRNet: A Dual-Path Hierarchical Relation Network for Multi-Person Pose Estimation Dang, Yonghao Yin, Jianqin Liu, Liyuan Ding, Pengxiang Sun, Yuan Hu, Yanzhu Computer Vision and Pattern Recognition Multi-person pose estimation (MPPE) presents a formidable yet crucial challenge in computer vision. Most existing methods predominantly concentrate on isolated interaction either between instances or joints, which is inadequate for scenarios demanding concurrent localization of both instances and joints. This paper introduces a novel CNN-based single-stage method, named Dual-path Hierarchical Relation Network (DHRNet), to extract instance-to-joint and joint-to-instance interactions concurrently. Specifically, we design a dual-path interaction modeling module (DIM) that strategically organizes cross-instance and cross-joint interaction modeling modules in two complementary orders, enriching interaction information by integrating merits from different correlation modeling branches. Notably, DHRNet excels in joint localization by leveraging information from other instances and joints. Extensive evaluations on challenging datasets, including COCO, CrowdPose, and OCHuman datasets, showcase DHRNet's state-of-the-art performance. The code will be released at https://github.com/YHDang/dhrnet-multi-pose-estimation. |
| title | DHRNet: A Dual-Path Hierarchical Relation Network for Multi-Person Pose Estimation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.14025 |