AI Paper Atlas

Research map / 3D vision / Human pose estimation

Viewpoint Estimation---Insights & Model

Gilad Divon, Ayellet Tal

ECCV 2018 · 3D vision › Human pose estimation · approach: Category-level object pose estimation

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
replace VGG with ResNet backbone in a unified Faster R-CNN network (ablation)VGG classification model · PASCAL3D+ (synthetic+real)mAVP24: 36.1 -> 39.5Improved
replace VGG with ResNet backbone (real data only) (ablation)VGG classification model · PASCAL3D+ (real data)mAVP24: 31.1 -> 37.6Improved
use geometric loss instead of classification loss (ablation)ResNet/Faster R-CNN · PASCAL3D+mAVP24: 39.5 -> 40.6Improved
integrate over viewpoints within a bin instead of selecting the max-activation bin (ablation)ResNet/Faster R-CNN with geometric loss · PASCAL3D+mAVP24: 40.6 -> 43.2Improved
replace geometric loss with the viewpoint loss (triplet + flip) (ablation)ResNet/Faster R-CNN with integral · PASCAL3D+mAVP24: 43.2 -> 44.4Improved
add unlabeled video data in semi-supervised triplet training (ablation)viewpoint-loss model · PASCAL3D+mAVP24: 44.4 -> 45.9Improved
add synthetic images to real training data (ablation)ResNet/Faster R-CNN classification · PASCAL3D+mAVP24: 37.6 -> 39.5Improved
use contrastive loss instead of geometric loss (ablation)geometric-loss model · PASCAL3D+ (real data, loss comparison)mAVP24: 43.2 -> 42.5Hurt
use flip loss instead of geometric loss (ablation)geometric-loss model · PASCAL3D+ (real data, loss comparison)mAVP24: 43.2 -> 43.6Improved
add triplet loss to geometric loss (ablation)geometric-loss model · PASCAL3D+ (real data, loss comparison)mAVP24: 43.2 -> 44.1Improved
add flip loss to triplet+geometric loss (viewpoint loss) (ablation)triplet+geometric model · PASCAL3D+ (real data, loss comparison)mAVP24: 44.1 -> 44.4Improved
full model versus prior state of the artVGG/Fast R-CNN prior work · PASCAL3D+mAVP24: 36.1 -> 45.9Improved

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