AI Paper Atlas

Research map / 3D vision / Human pose estimation

Chirality Nets for Human Pose Regression

Raymond Yeh, Yuan-Ting Hu, Alexander Schwing

NeurIPS 2019 · 3D vision › Human pose estimation · approach: Heatmap and coordinate pose encoding · 14 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
Replace the temporal convolutional network layers with chirality-equivariant layersHuman3.6M 2D-to-3D pose estimation · Human3.6M, Protocol 1 (MPJPE)MPJPE: 0.1 mmImproved
Replace the baseline with the chirality-equivariant single-frame modelHuman3.6M 2D-to-3D pose estimation · Human3.6M, single-frame comparisonMPJPE: 0.4 mmImproved
Use chirality-equivariant layers instead of the baseline without test-time augmentationHuman3.6M 2D-to-3D pose estimation · Human3.6M, Protocol 1MPJPE: 1 mmImproved
Use chirality-equivariant temporal convolutionHumanEva-I 2D-to-3D pose estimation · HumanEva-I, Protocol 1MPJPE: 0.8mmImproved
Use chirality-equivariant temporal convolutionHumanEva-I 2D-to-3D pose estimation · HumanEva-I, Protocol 2P-MPJPE: 0.2 mmImproved
Use chirality-equivariant layersHuman3.6M 2D-to-3D pose estimation · Human3.6M, Protocol 2P-MPJPE: 0.3mmHurt
Use chirality-equivariant layersHuman3.6M limited-data pose estimation · Human3.6M, training data from S1 at 0.1%MPJPEHurt
Use chirality-equivariant layers with batch-size 32Human3.6M limited-data pose estimation · Human3.6M, S1 0.1%MPJPE: 100.4mm; 102.3mmImproved
Replace the non-chiral sequence model with the chirality-equivariant modelPenn Action pose forecasting · Penn ActionPCK@0.05Improved
Add train and test-time augmentation to the non-chiral forecasting baselinePenn Action pose forecasting · Penn ActionPCK@0.05Improved
Add a chiral-invariance layer and chirality-equivariant layers before itOurs-Conv skeleton action recognition · Kinetics-400Top-1 accuracyImproved
Add a chiral-invariance layer and chirality-equivariant layers before itOurs-Conv skeleton action recognition · Kinetics-400Top-5 accuracyImproved

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