A Two-stream Hybrid CNN-Transformer Network for Skeleton-based Human Interaction Recognition

no code implementations • 31 Dec 2023 • Ruoqi Yin, Jianqin Yin

Specifically, Transformer-based stream integrates 3D convolutions with multi-head self-attention to learn inter-token correlations; We propose a new multi-branch CNN framework for CNN-based streams that automatically learns joint spatio-temporal features from skeleton sequences.

Human Interaction Recognition Specificity

Global Relation Modeling and Refinement for Bottom-Up Human Pose Estimation

no code implementations • 27 Mar 2023 • Ruoqi Yin, Jianqin Yin

In this paper, we concern on the bottom-up paradigm in multi-person pose estimation (MPPE).

Multi-Person Pose Estimation Relation

An Improved Baseline Framework for Pose Estimation Challenge at ECCV 2022 Visual Perception for Navigation in Human Environments Workshop

no code implementations • 13 Mar 2023 • Jiajun Fu, Yonghao Dang, Ruoqi Yin, Shaojie Zhang, Feng Zhou, Wending Zhao, Jianqin Yin

This technical report describes our first-place solution to the pose estimation challenge at ECCV 2022 Visual Perception for Navigation in Human Environments Workshop.

Human Detection Pose Estimation