AI Paper Atlas

Research map / 3D vision / Human pose estimation

Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation

Ailing Zeng, Xiao Sun, Lei Yang, Nanxuan Zhao, Minhao Liu, Qiang Xu

ICCV 2021 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 177 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 hierarchical fusion of short- and long-range hops instead of single-stage fusion (ablation)HCSF skeletal GNN · Human3.6M (2D GT)MPJPE (mm): outperforms Non-hierarchy by 2mm~3.7mm under different LImproved
add hop-aware (per-hop channel squeezing) processing to the hierarchy (ablation)HCSF skeletal GNN · Human3.6M (2D GT)MPJPE (mm): 34.2 -> 32.6 (L=3); consistent drop of 1.6mm~1.8mm without itImproved
reduce squeezing ratio d from 1 to 1/8 (ablation)HCSF · Human3.6M (2D GT)MPJPE (mm): 35.4 -> 31.4Improved
squeeze further to d=1/16 (ablation)HCSF · Human3.6M (2D GT)MPJPE (mm): 31.4 -> 32.6Hurt
initialise learnable graph from physical topology rather than dense or random (ablation)dynamic graph learning · Human3.6M (2D GT)MPJPE (mm): physical 32.1 vs dense 35.7 vs random 40.8Improved
learn graph only from dynamic offsets of input features (ablation)dynamic graph learning · Human3.6M (2D GT)MPJPE (mm): 30.8 -> 44.3Hurt
add dynamic offsets to weighted graph M_k (Eq. 8 with alpha) (ablation)HCSF static baseline · Human3.6M (2D GT)MPJPE (mm): 30.8 -> 30.5 (M+O), 30.4 (Eq. 8)Improved
add temporal-aware scheme to dynamic graph construction (ablation)HCSF with dynamic graph · Human3.6M (2D GT)MPJPE (mm): 30.8 -> 29.7Improved
add temporal-aware scheme to dynamic graph (detected 2D temporal input) (ablation)Ours · Human3.6M (temporal, detected)MPJPE (mm): 46.4 -> 45.7Improved
use 3x1 temporal kernel instead of longer or strided kernels (ablation)temporal-aware dynamic graph · Human3.6M (2D GT)MPJPE (mm): 30.8 -> 30.4 (3,1); 30.7 (7,1)Mixed
replace k-hop, MixHop or MS-Hop aggregation with HCSF (ablation)skeleton action recognition GNN · NTU RGB+D X-View (static graph)top-1 accuracy (%): 94.1 -> 94.8 (vs MS-Hop)Improved
use 3-frame temporal convolution in dynamic graph for action recognition (ablation)HCSF dynamic graph · NTU RGB+D X-Viewtop-1 accuracy (%): 94.7 -> 95.3Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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