AI Paper Atlas

Research map / 3D vision / Human pose estimation

Heatmap Regression without Soft-Argmax for Facial Landmark Detection

Chiao-An Yang, Raymond A. Yeh

ICCV 2025 · 3D vision › Human pose estimation · approach: Learned camera pose estimation · 4 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
replace Soft-argmax l2 loss (STAR) with structured prediction loss, no label smoothing (ablation)heatmap regression · WFLW fullFR: 2.32 -> 2.23No clear effect
add image-aware label smoothing to structured loss (ablation)structured loss · WFLW fullFR: 2.23 -> 1.84Improved
add image-aware label smoothing to structured loss (ablation)structured loss · WFLW fullNME: 4.02 -> 3.99Improved
make label smoothing image-aware instead of image-unaware (ablation)structured loss · WFLW fullFR: 2.12 -> 1.84Improved
add image-aware label smoothing to STAR loss (ablation)STAR · WFLW fullFR: 2.32 -> 2.12Improved
use smooth-l1 margin instead of no margin (ablation)structured loss · WFLW fullFR: 2.16 -> 1.84Improved
use smooth-l1 margin instead of l2 (ablation)structured loss · WFLW fullFR: 2.00 -> 1.84Improved
use smooth-l1 margin instead of l1 (ablation)structured loss · WFLW fullFR: 2.04 -> 1.84Improved
add image-aware label smoothing (ablation)structured loss · WFLW-L (large pose)NME: 6.68 -> 6.58Improved
add image-aware label smoothing (ablation)structured loss · WFLW-M (make-up)NME: 3.93 -> 3.89Improved
add image-aware label smoothing (ablation)structured loss · WFLW-B (blur)NME: 4.56 -> 4.57No clear effect
replace Soft-argmax with structured prediction loss plus label smoothingSTAR · WFLW fullNME: 4.02 -> 3.99Improved

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