AI Paper Atlas

Research map / 3D vision / Human pose estimation

Deep Deformation Network for Object Landmark Localization

Xiang Yu, Feng Zhou, Manmohan Chandraker

ECCV 2016 · 3D vision › Human pose estimation · approach: Learned camera pose estimation · 113 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 PTN refinement on top of SBN (ablation)SBN · HelenPCK@0.05: 51.4 -> 85.2Improved
add PTN refinement on top of SBN (ablation)SBN · iBugPCK@0.05: 22.6 -> 56.6Improved
add SBN initialization before PTN (ablation)PTN · HelenPCK@0.05: 81.4 -> 85.2Improved
add SBN initialization before PTN (ablation)PTN · iBugPCK@0.05: 49.1 -> 56.6Improved
add SBN initialization before PTN (ablation)PTN · LFPWPCK@0.10: 91.3 -> 91.6Improved
use TPS non-rigid warp instead of affine transformation (ablation)a-DDN · HelenPCK@0.05: 67.8 -> 85.2Improved
use TPS non-rigid warp instead of affine transformation (ablation)a-DDN · iBugPCK@0.05: 38.7 -> 56.6Improved
use TPS non-rigid warp instead of affine transformation (ablation)a-DDN · LSPmean PCK@0.2: 68.3 -> 84.3Improved
replace cGPRT with DDNcGPRT · 300-Wnormalized error: 5.71 -> 5.65Improved
replace Chen & Yuille CNN+graphical model with DDNChen & Yuille · LSPmean PCK@0.2: 73.4 -> 84.3Improved
replace Zhang et al. FCN segmentation approach with DDN regressionZhang et al. · CUB200-2011Back PCK@0.10: 85.6 -> 94.0Improved
replace Zhang et al. FCN segmentation approach with DDN regressionZhang et al. · CUB200-2011Bee PCK@0.10: 94.9 -> 82.5Hurt

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