AI Paper Atlas

Research map / Detection and segmentation / CNN features

Cascaded Continuous Regression for Real-Time Incremental Face Tracking

Enrique Sánchez-Lozano, Brais Martinez, Georgios Tzimiropoulos, Michel Valstar

ECCV 2016 · Detection and segmentation › CNN features · approach: Pedestrian and crowd detection · 58 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
use iCCR rank-update instead of incremental SDM updateincremental cascaded regression · model update costupdate time (ms): 705 -> 72Improved
replace sampled perturbations with continuous regression (CCR instead of SDM)cascaded regression · 300VW test (all categories)AUC: 0.49 -> 0.49No clear effect
add incremental learning (iCCR instead of CCR)CCR · 300VW test (all categories)accuracy curveImproved
add incremental learningCCR in fully automated system · 300VW category 3accuracy curveImproved
filter badly tracked frames with an SVM before incremental updates (ablation)iCCR · 300VW testaccuracyImproved
use continuous regression instead of sampled SDM at small errorsCCR · 300VW testaccuracy curveMixed

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