AI Paper Atlas

Research map / 3D vision / Human pose estimation

DeeperCut: A Deeper, Stronger, and Faster Multi-person Pose Estimation Model

Eldar Insafutdinov, Leonid Pishchulin, Bjoern Andres, Mykhaylo Andriluka, Bernt Schiele

ECCV 2016 · 3D vision › Human pose estimation · approach: Multi-person pose estimation · 1,217 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 intermediate supervision (ablation)ResNet-152 part detector · LSP (PC)PCK: 89.1 -> 90.1Improved
add intermediate supervision (ablation)ResNet-152 part detector · MPII Single PersonPCKh: 87.8 -> 88.5Improved
use ResNet-152 instead of ResNet-50 (16 px stride) (ablation)part detector · LSP (PC)PCK: 87.2 -> 89.1Improved
increase stride from 8 px to 16 px with 2x up-sampling (ablation)ResNet-50 · LSP (PC)PCK: 87.8 -> 87.2Hurt
replace DeepCut pairwise with image-conditioned pairwise (ablation)DeepCut · MPII Multi-Person ValAP: 33.3 -> 47.7Improved
replace DeepCut unary with proposed ResNet part detectors (ablation)DeeperCut · MPII Multi-Person ValAP: 47.7 -> 52.3Improved
apply location refinement before NMS (ablation)DeeperCut · MPII Multi-Person ValAP: 52.3 -> 52.6Improved
make pairwise bi-directional instead of uni-directional (ablation)image-conditioned pairwise · MPII Multi-Person ValAP: 51.1 -> 52.6Improved
add angle features to pairwise (ablation)image-conditioned pairwise · MPII Multi-Person ValAP: 51.3 -> 52.6Improved
use more aggressive NMS (24 px radius) (ablation)1-stage optimization · MPII Multi-Person ValAP: 52.6 -> 54.5Improved
increase detections from 100 to 150 (ablation)1-stage optimization · MPII Multi-Person ValAP: 54.5 -> 55.1Improved
use 2-stage incremental optimization instead of 1-stage with 150 detections (ablation)DeeperCut · MPII Multi-Person ValAP: 55.1 -> 56.5Improved

Later papers that compared with this method

5 later accepted papers report DeeperCut as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.

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