AI Paper Atlas

Research map / 3D vision / Human pose estimation

On Boosting Single-Frame 3D Human Pose Estimation via Monocular Videos

Zhi Li, Xuan Wang, Fei Wang, Peilin Jiang

ICCV 2019 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 52 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
fine-tune on predictions refined by low-rank trajectory optimisation instead of raw predictions (ablation)fine-tuning with plain loss · H36M validation (subject-wise protocol S1)MPJPE: 94.5 -> 91.0Improved
add weighted fidelity loss to raw-prediction fine-tuning (ablation)original supervision · H36M validation (subject-wise protocol S1)MPJPE: 94.5 -> 93.0Improved
add weighted fidelity loss to optimised-prediction fine-tuning (ablation)optimised supervision · H36M validation (subject-wise protocol S1)MPJPE: 91.0 -> 90.5Improved
add bone-length consistency loss to raw-prediction fine-tuning (ablation)original supervision + weighted fidelity · H36M validation (subject-wise protocol S1)MPJPE: 93.0 -> 92.6Improved
add bone-length consistency loss to optimised fine-tuning (ablation)optimised supervision + weighted fidelity · H36M validation (subject-wise protocol S1)MPJPE: 90.5 -> 88.8Improved
full two-stage fine-tuning with unlabelled videobaseline trained on S1 · H36M validation (subject-wise protocol S1)MPJPE: 97.7 -> 88.8Improved
trajectory optimisation of predictions on unlabelled H36M video (ablation)H36M S5-8 predictions · H36M S5-8 trajectory optimisation (baseline trained on S1)MPJPE: 91.20 -> 81.67Improved
trajectory optimisation of predictions on unlabelled 3DHP video (ablation)3DHP S2-8 predictions · 3DHP S2-8 optimisation (S1)MPJPE: 132.25 -> 125.97Improved
semi-supervised training of the 2D-input baseline without ground truth 2D annotationsPavllo semi-supervised · H36M validation (subject-wise protocol S1)MPJPE: 98.6 -> 119.3Hurt
fine-tune on unlabelled videos of new hard actionsaction-wise protocol hard · H36M validation, 4 hard unlabelled actions (action-wise protocol hard)MPJPE: 138.09 -> 119.76Improved
fine-tune on unlabelled videos of new actionsaction-wise protocol half · H36M validation, unlabelled half of actionsMPJPE: 98.92 -> 88.75Improved
fine-tune on unlabelled phoning video when labelled data is only discussion (class mismatch)discussion-trained model · H36M PhoningMPJPE: 144.5 -> 134.2Improved

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