AI Paper Atlas

Research map / 3D vision / Human pose estimation

Click Here: Human-Localized Keypoints as Guidance for Viewpoint Estimation

Ryan Szeto, Jason J. Corso

ICCV 2017 · 3D vision › Human pose estimation · approach: Learned camera pose estimation · 15 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 keypoint map and class conditioned learned attention (full CH-CNN) over fine-tuned image-only R4CNNR4CNN fine-tuned · PASCAL 3D+ val (mean)Acc pi/6 (%): 85.7 -> 90.7Improved
same, MedErrR4CNN fine-tuned · PASCAL 3D+ val (mean)MedErr (degrees): 6.74 -> 6.35Improved
add keypoint class to the keypoint map for the attention weights (ablation)CH-CNN (keypoint map only) · PASCAL 3D+ val (mean)Acc pi/6 (%): 85.6 -> 90.7Improved
add keypoint map to the keypoint class for the attention weights (ablation)CH-CNN (keypoint class only) · PASCAL 3D+ val (mean)Acc pi/6 (%): 86.8 -> 90.7Improved
learn attention from keypoint data instead of fixed Gaussian weight map (ablation)Keypoint features · PASCAL 3D+ val (mean)Acc pi/6 (%): 84.4 -> 90.7Improved
learn attention from keypoint data instead of fixed uniform weight map (ablation)Keypoint features · PASCAL 3D+ val (mean)Acc pi/6 (%): 85.4 -> 90.7Improved
provide the true keypoint map and class instead of blank ones at test time (ablation)CH-CNN · PASCAL 3D+ val (mean)Acc pi/6 (%): 74.1 -> 90.7Improved
provide the true keypoint class in addition to true map at test time (ablation)CH-CNN · PASCAL 3D+ val (mean)Acc pi/6 (%): 83.1 -> 90.7Improved
fine-tune R4CNN on the new synthetic keypoint-dataset rendersR4CNN · PASCAL 3D+ val (mean)Acc pi/6 (%): 84.1 -> 85.7Improved
use Chebyshev distance transform keypoint map instead of Gaussian map (ablation)CH-CNN · PASCAL 3D+ val (mean)Acc pi/6 (%): 84.4 -> 90.7Improved
use Chebyshev instead of Euclidean distance transform keypoint map (ablation)CH-CNN · PASCAL 3D+ val (mean)MedErr (degrees): 6.31 -> 6.35No clear effect
use Chebyshev instead of Manhattan distance transform keypoint map (ablation)CH-CNN · PASCAL 3D+ val (mean)Acc pi/6 (%): 89.8 -> 90.7No 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