AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Cross Euclidean-to-Riemannian Metric Learning with Application to Face Recognition from Video

Zhiwu Huang, Ruiping Wang, Shiguang Shan, Luc Van Gool, Xilin Chen

TPAMI 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses

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
use RBF kernel instead of linear kernel (ablation)CERML-ES · COX V2S V1-S (deep)accuracy (%): 84.67 -> 86.21Improved
use RBF kernel instead of linear kernel (ablation)CERML-EG · COX V2S V1-S (deep)accuracy (%): 85.36 -> 85.71No clear effect
use RBF kernel instead of linear kernel (ablation)CERML-EA · COX V2S V1-S (deep)accuracy (%): 86.17 -> 86.40No clear effect
use RBF kernel instead of linear kernel (ablation)CERML-ES · COX V2V V3-V2 (deep)accuracy (%): 98.77 -> 97.46Hurt
use RBF kernel instead of linear kernel (ablation)CERML-EG · COX V2V V2-V1 (deep)accuracy (%): 97.84 -> 98.77Improved
use CERML-ES instead of Euclidean metric learning LMNNCERML-ES · COX V2S V1-S (gray)accuracy (%): 34.44 -> 51.41Improved
use CERML-ES instead of kernel cross-metric KGMA-ESCERML-ES · COX V2S V1-S (gray)accuracy (%): 41.89 -> 51.41Improved
use CERML-EG instead of CDLCERML-EG · COX V2V V2-V1 (deep)accuracy (%): 95.53 -> 97.77Improved
use CERML-ES instead of VGGDeepFace on PaSC control V2VCERML-ES · PaSC V2V control (deep)accuracy (%): 78.82 -> 79.92Improved
use CERML-EG instead of PMLCERML-EG · YTC (deep)accuracy (%): 86.98 -> 87.62Improved
compare CERML-ES with FaceNetCERML-ES · YTF (deep)accuracy (%): 95.1 vs 93.44Hurt
use CERML-EG instead of LFDA on PaSC V2S controlCERML-EG · PaSC V2S control (deep)accuracy (%): 72.44 -> 63.34Hurt

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