AI Paper Atlas

Research map / Video / Video segmentation and tracking

Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors

Xuanyi Dong, Shoou-I Yu, Xinshuo Weng, Shih-En Wei, Yi Yang, Yaser Sheikh

CVPR 2018 · Video › Video segmentation and tracking · approach: Learned optical flow estimation · 220 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 SBR using unlabeled videoCPM · 300-W fullNME: 4.36 -> 4.10Improved
Add SBR using unlabeled videoCPM · AFLWNME: 2.33 -> 2.14Improved
Add SBR using unlabeled videoCPM · 300-VW category CAUC@0.08: 57.25 -> 58.22Improved
Add PAM adaptation on the videoCPM + SBR · 300-VW category CAUC@0.08: 58.22 -> 59.39Improved
Adapt the detector to the testing video with PAMCPM · YouTube CelebritiesNME: 5.26 -> 4.74Improved
Adapt the detector to the testing video with PAMReg · YouTube CelebritiesNME: 10.21 -> 9.31Improved
Use 5-frame rather than 3-frame LK tracking (ablation)CPM + PAM · YouTube CelebritiesNME: 4.74 -> 5.01Hurt
Use conv-1 features rather than RGB images for LK tracking (ablation)CPM + PAM · YouTube CelebritiesNME: 4.74 -> 5.13Hurt
Use self-training without registration-loss feedback (ablation)CPM · YouTube CelebritiesNME: 4.74 -> 5.45Hurt

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