AI Paper Atlas

Research map / Video / Video segmentation and tracking

A Recurrent Encoder-Decoder Network for Sequential Face Alignment

Xi Peng, Rogerio S. Feris, Xiaoyu Wang, Dimitris N. Metaxas

ECCV 2016 · Video › Video segmentation and tracking · approach: Deepfake video detection · 153 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 spatial recurrence with shared weights instead of independent cascaded networks (ablation)Cascade of three networks · AFLW large pose (>30 deg)mean error (%): 8.07 -> 7.33Improved
share weights across steps via spatial recurrence (ablation)Cascade of three networks · AFLW large pose (>30 deg)memory (MB): 88.9 -> 29.6Improved
share weights across steps via spatial recurrence (ablation)Cascade of three networks · AFLW large pose (>30 deg)failure rate (%): 25.5 -> 17.3Improved
add temporal recurrent learning f_tRNN (ablation)Model without f_tRNN · 300-VW validation, commonmean error (%): 4.52 -> 4.21Improved
add temporal recurrent learning f_tRNN (ablation)Model without f_tRNN · 300-VW validation, commonfailure rate (%): 3.48 -> 1.71Improved
add temporal recurrent learning f_tRNN (ablation)Model without f_tRNN · 300-VW validation, challengingmean error (%): 6.27 -> 5.64Improved
add temporal recurrent learning f_tRNN (ablation)Model without f_tRNN · 300-VW validation, challengingfailure rate (%): 13.3 -> 5.40Improved
add temporal recurrent learning f_tRNN (ablation)Model without f_tRNN · 300-VW validation, fullmean error (%): 5.83 -> 5.25Improved
add supervised identity classification (f_CLS) in the bottleneck (ablation)Model without f_CLS · 300-VW test, left eye landmark after 10 epochsvalidation accuracy: 0.8 -> 0.84Improved
add supervised identity classification (f_CLS) in the bottleneck (ablation)Model without f_CLS · 300-VW test accuracytesting accuracy: approximately 9% improvementImproved
increase spatial recurrent steps to the fourth step (ablation)3-step model · AFLW validationmean errorNo clear effect
use more spatial recurrent steps on large-pose faces rather than near frontal (ablation)Spatial recurrent learning · AFLW validation 45-90 deg vs 0-15 degmean error improvement: 23.3% improvement on 45-90 deg set and 6.10% improvement on 0-15 deg pose setMixed

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