AI Paper Atlas

Research map / 3D vision / Human pose estimation

Inference Stage Optimization for Cross-scenario 3D Human Pose Estimation

Jianfeng Zhang, Xuecheng Nie, Jiashi Feng

NeurIPS 2020 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 26 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
adapt the pose model on each target sample using online ISO-CycleFSL-trained 3D pose model · MPI-INF-3DHP unscaledPCK: 78.9 -> 83.6Improved
adapt the pose model on each target sample using online ISO-CycleFSL-trained 3D pose model · MPI-INF-3DHP unscaledMPJPE: 103.8 -> 92.2Improved
add geometric cycle consistency to adversarial SSL (ablation)ISO-Adversary on MPI-INF-3DHP · MPI-INF-3DHP unscaled, online settingPCK: 83.0 -> 83.6Improved
add geometric cycle consistency to adversarial SSL (ablation)ISO-Adversary on MPI-INF-3DHP · MPI-INF-3DHP unscaled, joint settingPCK: 80.9 -> 81.3Improved
add geometric cycle consistency to adversarial SSL (ablation)ISO-Adversary on MPI-INF-3DHP · MPI-INF-3DHP unscaled, vanilla settingPCK: 82.1 -> 82.5Improved
stream adaptation parameters across target instances instead of resetting per sample (ablation)ISO-Cycle · MPI-INF-3DHP unscaledPCK: 82.5 -> 83.6Improved
increase vanilla ISO iterations from 1 to 10 (ablation)Vanilla ISO-Cycle · MPI-INF-3DHPPCK: 81.5% -> 82.5%Improved
increase online ISO iterations above 1 (ablation)Online ISO-Cycle · MPI-INF-3DHPPCKHurt
use a large learning rate such as 2e-3 for online adaptation (ablation)Online ISO-Cycle · MPI-INF-3DHPPCK: 70.9% PCKHurt
perform SSL once per 10 samples instead of on every sample (ablation)Online ISO · MPI-INF-3DHP unscaledPCK: 83.6 -> 83.0Hurt
perform SSL once per 10 samples instead of on every sample (ablation)Online ISO · MPI-INF-3DHP unscaledTime[s]: 0.027 -> 0.004Improved
add Gaussian noise with standard deviation 10 to 2D inputs (ablation)ISO · MPI-INF-3DHPPCK: 83.6 -> 79.6Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy