Research map / 3D vision / Human pose estimation
ChildPose: Foundation for Children Pose Modeling
Jiakai Chen, Yifan Shen, Boyi Li, Chuanmiao Dong, Xu Cao
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Introduces ChildPose, a modular video foundation model that adapts pretrained pose encoders into a streaming model for child-centric pose estimation.
Problem
Human pose estimation is dominated by adult-centric models, leaving children underrepresented due to data scarcity, distinct body morphology, and unique motion dynamics.
Approach
Transforms pretrained pose encoders into a streaming pediatric video model via memory-augmented processing (the abstract is truncated, so further details are unknown).
Closest papers by meaning
- Unsupervised Human Pose Estimation Through Transforming Shape Templates (CVPR 2021 · similarity 0.87)
- InclusiveVidPose: Bridging the Pose Estimation Gap for Individuals with Limb Deficiencies in Video-Based Motion (ICLR 2026 · similarity 0.86)
- FlexPose: Pose Distribution Adaptation with Limited Guidance (AAAI 2025 · similarity 0.85)
- TexturePose: Supervising Human Mesh Estimation With Texture Consistency (ICCV 2019 · similarity 0.85)
- Putting People in Their Place: Monocular Regression of 3D People in Depth (CVPR 2022 · similarity 0.85)
- HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation (NeurIPS 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
