An Integral Pose Regression System for the ECCV2018 PoseTrack Challenge

Xiao Sun, Chuankang Li, Stephen Lin

2018-09-173D Human Pose Estimation regression Pose Estimation

Abstract

For the ECCV 2018 PoseTrack Challenge, we present a 3D human pose estimation system based mainly on the integral human pose regression method. We show a comprehensive ablation study to examine the key performance factors of the proposed system. Our system obtains 47mm MPJPE on the CHALL_H80K test dataset, placing second in the ECCV2018 3D human pose estimation challenge. Code will be released to facilitate future work.

Results

Task	Dataset	Metric	Value	Model
3D Human Pose Estimation	CHALL H80K	MPJPE	55.3	ResNet
Pose Estimation	CHALL H80K	MPJPE	55.3	ResNet
3D	CHALL H80K	MPJPE	55.3	ResNet
1 Image, 2*2 Stitchi	CHALL H80K	MPJPE	55.3	ResNet

Related Papers

Language Integration in Fine-Tuning Multimodal Large Language Models for Image-Based Regression2025-07-20 $π^3$: Scalable Permutation-Equivariant Visual Geometry Learning2025-07-17 Revisiting Reliability in the Reasoning-based Pose Estimation Benchmark2025-07-17 DINO-VO: A Feature-based Visual Odometry Leveraging a Visual Foundation Model2025-07-17 From Neck to Head: Bio-Impedance Sensing for Head Pose Estimation2025-07-17 AthleticsPose: Authentic Sports Motion Dataset on Athletic Field and Evaluation of Monocular 3D Pose Estimation Ability2025-07-17 Neural Network-Guided Symbolic Regression for Interpretable Descriptor Discovery in Perovskite Catalysts2025-07-16 Imbalanced Regression Pipeline Recommendation2025-07-16