You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perception

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Jin, Sheng, Li, Shuhuai, Li, Tong, Liu, Wentao, Qian, Chen, Luo, Ping
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913429377253376
author Jin, Sheng
Li, Shuhuai
Li, Tong
Liu, Wentao
Qian, Chen
Luo, Ping
author_facet Jin, Sheng
Li, Shuhuai
Li, Tong
Liu, Wentao
Qian, Chen
Luo, Ping
contents Human-centric perception (e.g. detection, segmentation, pose estimation, and attribute analysis) is a long-standing problem for computer vision. This paper introduces a unified and versatile framework (HQNet) for single-stage multi-person multi-task human-centric perception (HCP). Our approach centers on learning a unified human query representation, denoted as Human Query, which captures intricate instance-level features for individual persons and disentangles complex multi-person scenarios. Although different HCP tasks have been well-studied individually, single-stage multi-task learning of HCP tasks has not been fully exploited in the literature due to the absence of a comprehensive benchmark dataset. To address this gap, we propose COCO-UniHuman benchmark to enable model development and comprehensive evaluation. Experimental results demonstrate the proposed method's state-of-the-art performance among multi-task HCP models and its competitive performance compared to task-specific HCP models. Moreover, our experiments underscore Human Query's adaptability to new HCP tasks, thus demonstrating its robust generalization capability. Codes and data are available at https://github.com/lishuhuai527/COCO-UniHuman.
format Preprint
id arxiv_https___arxiv_org_abs_2312_05525
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perception
Jin, Sheng
Li, Shuhuai
Li, Tong
Liu, Wentao
Qian, Chen
Luo, Ping
Computer Vision and Pattern Recognition
Human-centric perception (e.g. detection, segmentation, pose estimation, and attribute analysis) is a long-standing problem for computer vision. This paper introduces a unified and versatile framework (HQNet) for single-stage multi-person multi-task human-centric perception (HCP). Our approach centers on learning a unified human query representation, denoted as Human Query, which captures intricate instance-level features for individual persons and disentangles complex multi-person scenarios. Although different HCP tasks have been well-studied individually, single-stage multi-task learning of HCP tasks has not been fully exploited in the literature due to the absence of a comprehensive benchmark dataset. To address this gap, we propose COCO-UniHuman benchmark to enable model development and comprehensive evaluation. Experimental results demonstrate the proposed method's state-of-the-art performance among multi-task HCP models and its competitive performance compared to task-specific HCP models. Moreover, our experiments underscore Human Query's adaptability to new HCP tasks, thus demonstrating its robust generalization capability. Codes and data are available at https://github.com/lishuhuai527/COCO-UniHuman.
title You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perception
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.05525