AI Paper Atlas

Research map / 3D vision / Human pose estimation

Conservative Wasserstein Training for Pose Estimation

Xiaofeng Liu, Yang Zou, Tong Che, Peng Ding, Ping Jia, Jane You, B.V.K. Vijaya Kumar

ICCV 2019 · 3D vision › Human pose estimation · approach: Learned camera pose estimation · 35 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
use squared arc length instead of arc length as ground metric (ablation)Wasserstein loss, one-hot · CAVIAR head poseMAAD: 18.8 -> 17.1Improved
use concave chord-length ground metric instead of arc length (ablation)Wasserstein loss, one-hot · CAVIAR head poseMAAD: 18.8 -> 19.1Hurt
add adaptive ground metric learning (ablation)Wasserstein arc length · CAVIAR head poseMAAD: 18.8 -> 17.5Improved
add adaptive ground metric learning (ablation)Wasserstein squared arc length · CAVIAR head poseMAAD: 17.1 -> 17.3No clear effect
use exact instead of approximate Wasserstein computation (ablation)Wasserstein squared arc length · CAVIAR head poseMAAD: 17.8 -> 17.1Improved
add adaptive ground metric learning (ablation)Wasserstein arc length · TUD pedestrian (36 poses)Mean AE: 19.1 -> 20.5Hurt
add Binomial-uniform conservative target label (ablation)Wasserstein squared arc length · TUD pedestrian (36 poses)Mean AE: 18.5 -> 16.3Improved
use Poisson instead of Binomial conservative label (ablation)Wasserstein squared arc length · TUD pedestrian (36 poses)Mean AE: 16.3 -> 17.7Hurt
add conservative target label (ablation)Wasserstein arc length · EPFL vehicleMean AE: 6.46 -> 6.30Improved
add conservative target label (ablation)Wasserstein squared arc length · EPFL vehicleMean AE: 6.23 -> 6.04Improved
use cube instead of square of arc length as ground metric (ablation)Wasserstein loss, one-hot · EPFL vehicleMean AE: 6.23 -> 6.47Hurt
use Huber ground metric instead of squared arc length (ablation)Wasserstein loss, one-hot · EPFL vehicleMean AE: 6.23 -> 6.20No clear effect

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