AI Paper Atlas

Research map / 3D vision / Human pose estimation

Deformable Pose Traversal Convolution for 3D Action and Gesture Recognition

Junwu Weng, Mengyuan Liu, Xudong Jiang, Junsong Yuan

ECCV 2018 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 72 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
add deformable offsets to pose traversal convolution (ablation)Pose Traversal Conv · DHG Fineaccuracy (%): 77.1 -> 81.9Improved
add deformable offsets to pose traversal convolution (ablation)Pose Traversal Conv · DHG Both-14accuracy (%): 81.1 -> 85.8Improved
add deformable offsets to pose traversal convolution (ablation)Pose Traversal Conv · NTU-RGB+D cross-subjectaccuracy (%): 76.1 -> 76.8Improved
add deformable offsets to pose traversal convolution (ablation)Pose Traversal Conv · Berkeley MHADaccuracy (%): 98.6 -> 100.0Improved
use pose traversal representation instead of single-chain flattening (ablation)Pose Chain Conv · DHG Fineaccuracy (%): 76.2 -> 77.1Improved
use pose traversal representation instead of single-chain flattening (ablation)Pose Chain Conv · DHG Both-14accuracy (%): 80.4 -> 81.1Mixed
use pose traversal representation instead of single-chain flattening (ablation)Pose Chain Conv · Berkeley MHADaccuracy (%): 96.4 -> 98.6Improved
add deformable offsets under severe joint noise (50% noisy joints) (ablation)Pose Traversal Conv · Berkeley MHAD noiseaccuracy: 7.64%Improved
add deformable offsets under small noise (amplitude up to 5) (ablation)Pose Traversal Conv · Berkeley MHAD small noiseaccuracy (%): 96.36 -> 98.18Improved
use 3D instead of 2D pose inputD-Pose Traversal Conv · DHG Both-14accuracy (%): 85.1 -> 85.8No clear effect
use 3D instead of 2D pose inputPose Traversal Conv · DHG Fineaccuracy (%): 74.6 -> 77.1Improved
add deformable offsets for the Pinch gesture (ablation)Pose Traversal Conv · DHG-14 Pinchaccuracy: 49% -> 71.5%Improved

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