AI Paper Atlas

Research map / 3D vision / Human pose estimation

Deep Globally Constrained MRFs for Human Pose Estimation

Ioannis Marras, Petar Palasek, Ioannis Patras

ICCV 2017 · 3D vision › Human pose estimation · approach: Heatmap and coordinate pose encoding · 7 citations (OpenAlex)

This paper tried a common change: Add data augmentation

use the proposed data augmentation instead of that of Tompson et al. · MPII (PCK@0.15) · PCK full body: 48.98 -> 49.62 Improved

What 689 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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 the MRF spatial model between the coarse and refinement networks (ablation)coarse+coarse-to-fine model · MPII (PCK@0.15)PCK full body: 45.71 -> 47.49Improved
add the coarse-to-fine refinement network to the coarse model (ablation)coarse model · MPII (PCK@0.15)PCK full body: 38.71 -> 45.71Improved
add the coarse-to-fine refinement network to the coarse model (ablation)coarse model · FashionPose (PCK@0.15)PCK full body: 84.55 -> 86.95Improved
add the MRF model to the coarse+refinement pipeline (full model) (ablation)coarse+coarse-to-fine model · FashionPose (PCK@0.15)PCK full body: 86.95 -> 90.21Improved
iterate the MRF inference rather than a single loop (ablation)full model · MPII (PCK@0.15)PCK full body: 48.40 -> 49.62Improved
increase the number of pairwise filters from K=1 to K=4 (ablation)full model · MPII (PCK@0.15)PCK full body: 48.60 -> 49.62Improved
place the MRF before the refinement network instead of after it (ablation)full model · MPII (PCK@0.15)PCK full body: 47.49 -> 49.62Improved
use the proposed data augmentation instead of that of Tompson et al. (ablation)full model · MPII (PCK@0.15)PCK full body: 48.98 -> 49.62Improved
use the proposed larger coarse ConvNet instead of that of Tompson et al.coarse model · MPII (PCK@0.15)PCK full body: 36.25 -> 38.71Improved
use the proposed constrained MRF full model instead of the MRF of Tompson et al.full model · MPII (PCK@0.15)PCK full body: 44.08 -> 49.62Improved

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