AI Paper Atlas

Research map / 3D vision / Human pose estimation

Multi-Task Head Pose Estimation in-the-Wild

Roberto Valle, José M. Buenaposada, Luis Baumela

TPAMI 2020 · 3D vision › Human pose estimation · approach: Heatmap and coordinate pose encoding · 97 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
attach pose losses at the encoder bottleneck instead of the decoder end (ablation)MNN · Overall validation lossloss: 18.6 -> 7.9Improved
add landmark pre-training before multi-task training (ablation)MNN · Overall validation lossloss: 8.7 -> 7.9Improved
use symmetric multi-task learning instead of single-task pose (ablation)MNN · Head pose avg (5 sets)mean MAE (deg): 2.54 -> 2.35Improved
add landmark pre-training to multi-task learning (ablation)MNN · Head pose avg (5 sets)mean MAE (deg): 2.35 -> 2.24Improved
fine-tune only on pose instead of all three tasks after pre-training (ablation)MNN · Head pose avg (5 sets)mean MAE (deg): 2.24 -> 2.24No clear effect
add multi-task learning to visibility estimation (ablation)MNN · COFW visibilityrecall at 80% precision (%): 21.75 -> 72.12Improved
add occlusion-aware regressor (OR) (ablation)MNN · COFWNME: 5.65 -> 5.04Improved
add occlusion-aware regressor (OR) (ablation)MNN · AFLWNME: 2.03 -> 1.97Improved
add occlusion-aware regressor (OR) (ablation)MNN · AFLW2000-3DNME: 2.77 -> 2.58Improved
use corrected pose annotations (AFLW2000-3D-POSIT) for evaluationMNN · AFLW2000-3Dmean MAE (deg): 3.83 -> 1.71Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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