AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Discovering Deformable Keypoint Pyramids

Jianing Qian, Anastasios Panagopoulos, Dinesh Jayaraman

ECCV 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Object-centric learning theory and video · 3 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 the combined reconstruction loss (ablation)Keypoint Pyramids · H3.6M keypoint regression (flattened, 30 keypoints)RMSE: 45.23 -> 43.30Improved
add the transport loss (ablation)Keypoint Pyramids · H3.6M keypoint regression (flattened, 30 keypoints)RMSE: 45.85 -> 43.30Improved
add the spring loss (ablation)Keypoint Pyramids · H3.6M keypoint regression (flattened, 30 keypoints)RMSE: 45.28 -> 43.30Improved
use reconstruction loss overall plus level-wise transport loss instead of transport loss everywhere (ablation)Keypoint Pyramids · H3.6M keypoint regression (flattened, 30 keypoints)RMSE: 49.53 -> 43.30Improved
use reconstruction loss overall plus level-wise transport loss instead of reconstruction everywhere (ablation)Keypoint Pyramids · H3.6M keypoint regression (flattened, 30 keypoints)RMSE: 46.93 -> 43.30Improved
condition level-l keypoint encoder on level l-1 keypoints (ablation)Keypoint Pyramids · H3.6M keypoint regression (flattened, 30 keypoints)RMSE: 43.75 -> 43.30No clear effect
use only level 1 keypoints instead of level 2 (ablation)Keypoint Pyramids · H3.6M keypoint regressionRMSE: 43.97 -> 52.81Hurt
flatten both levels (30 keypoints) instead of level 2 onlyKeypoint Pyramids · H3.6M keypoint regression (flattened, 30 keypoints)RMSE: 43.97 -> 43.30Improved
hierarchical Keypoint Pyramids vs flat Transporter with 30 keypointsTransporter · H3.6M keypoint regression (flattened, 30 keypoints)RMSE: 47.45 -> 43.30Improved
hierarchical Keypoint Pyramids vs flat KeyNet with 30 keypointsKeyNet · H3.6M keypoint regression (flattened, 30 keypoints)RMSE: 46.71 -> 43.30Improved
hierarchical Keypoint Pyramids (L1+L2) keypoints vs flat Transporter (30) as input to action classifierTransporter · H3.6M action classificationaccuracy: 0.177 -> 0.218Improved
hierarchical Keypoint Pyramids (L1+L2) keypoints vs flat KeyNet (30) as input to action classifierKeyNet · H3.6M action classificationaccuracy: 0.179 -> 0.218Improved

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