Hierarchical Contrastive Consistency for Human Pose Estimation in Images and Videos
- 25 August 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (2) , 1837-1847
Abstract
Human pose estimation (HPE) is an invaluable task in computer vision with various practical applications. This paper proposes a novel Hierarchical Contrastive Consistensy constraint (HICCON) to improve the HPE in both images and videos, which describes the input into multi-granular representations at spatial and temporal domain and performs multi-level feature consistency by exploring the characteristic of human structure and time sequence. The hierarchical contrast is conducted at four levels: keypoint-level, part-level, instance-level and clip-level. In spatial, we consider keypoint-level and part-level consistency across instances within frame to enhance the fine-grained keypoint robustness. The former conducts the single keypoint feature contrast across instances to improve the category-specific keypoint features. The latter explores the specific pair-wise features for preserving the instructive relation. In temporal, we develop the instance-level and clip-level feature consistency across frames to capture more discriminative temporal representations. The former discriminates instance features across frames within the same video, whereas the clip-level constraint aims to discriminate consistent features from different videos in order to capture more distinctive temporal features. Extensive experiments on kinds of architectures across datasets i.e, PoseTrack2017, PoseTrack2018 and PoseTrack2021 show the HICCON achieves about 1.5% improvement than baseline. Besides, the proposed method unleashes the potential of the contrastive learning in HPE field.Keywords
Funding Information
- National Science and Technology Major Project from Ministry of Science and Technology, China, (2021ZD0201403)
- Natural Science Foundation of Shanghai Municipality (24ZR1476900)
- Program of Shanghai Academic Research Leader (22XD1424500)
This publication has 37 references indexed in Scilit:
- A comprehensive survey on contrastive learningNeurocomputing, 2024
- A comprehensive survey on human pose estimation approachesMultimedia Systems, 2022
- Self-supervised Keypoint Correspondences for Multi-person Pose Estimation and Tracking in Videos2020
- Multi-person Pose Estimation for Pose Tracking with Enhanced Cascaded Pyramid Network2019
- Multi-Domain Pose Network for Multi-Person Pose Estimation and Tracking2019
- Simple Baselines for Human Pose Estimation and Tracking2018
- PoseTrack: Joint Multi-person Pose Estimation and Tracking2017
- Thin-Slicing Network: A Deep Structured Model for Pose Estimation in Videos2017
- Deep Residual Learning for Image Recognition2016
- Microsoft COCO: Common Objects in Context2014