AI Paper Atlas

Research map / 3D vision / Human pose estimation

Cross-Domain Adaptation for Animal Pose Estimation

Jinkun Cao, Hongyang Tang, Hao-Shu Fang, Xiaoyong Shen, Cewu Lu, Yu-Wing Tai

ICCV 2019 · 3D vision › Human pose estimation · approach: Heatmap and coordinate pose encoding · 219 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 human pose data to animal training (2k labels) (ablation)AlphaPose · Animal pose testmAP: 30.3 -> 51.5Improved
add human pose data to animal training (4k labels) (ablation)AlphaPose · Animal pose testmAP: 44.3 -> 62.3Improved
add domain adaptation network (2k labels) (ablation)WS-CDA · Animal pose testmAP: 51.5 -> 53.0Improved
add domain adaptation network (4k labels) (ablation)WS-CDA · Animal pose testmAP: 62.3 -> 63.1Improved
add unlabeled animal data without weighting factor (2k labels) (ablation)WS-CDA · Animal pose testmAP: 53.0 -> 45.7Hurt
add unlabeled animal data without weighting factor (4k labels) (ablation)WS-CDA · Animal pose testmAP: 63.1 -> 57.2Hurt
add reweighting factor RB (w2=10) with unlabeled animal data (2k labels) (ablation)WS-CDA · Animal pose testmAP: 45.7 -> 56.7Improved
add reweighting factor RB (w2=10) with unlabeled animal data (4k labels) (ablation)WS-CDA · Animal pose testmAP: 57.2 -> 65.7Improved
increase labeled animal instances from 2k to 4kWS-CDA · Animal pose testmAP: 56.7 -> 65.7Improved
use w2=10 instead of 1 (ablation)WS-CDA · Unseen animal class: catmAP: 34.5 -> 39.2Improved
add PPLO on top of WS-CDA (ablation)WS-CDA · Unseen animal class: catmAP: 39.2 -> 42.3Improved
add PPLO on top of WS-CDA (ablation)WS-CDA · Unseen animal class: cowmAP: 54.6 -> 57.3Improved

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