atlas

Research map / Detection and segmentation / CNN features

Dynamic Attention-Controlled Cascaded Shape Regression Exploiting Training Data Augmentation and Fuzzy-Set Sample Weighting

CVPR 2017 · Detection and segmentation › CNN features · approach: Pedestrian and crowd detection · 114 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 DAC-CSR instead of CCLfacial landmark detection · AFLW-fullaverage error: 2.72% -> 2.27%Helped
Use DAC-CSR instead of CCLfacial landmark detection · AFLW-frontalaverage error: 2.17% -> 1.81{ }%Helped
Use DAC-CSR instead of RARfacial landmark detection · COFWerror: 6.03% -> 6.03%No clear effect
Use DAC-CSR instead of RARfacial landmark detection · COFWfailure rate: 4.14% -> 4.73%Hurt
Use DAC-CSR instead of RARfacial landmark detection · COFWspeed: 4 (GPU) -> 10Helped
Add the DAC-CSR architecture to classical CSR (ablation)facial landmark detection · COFWaverage errorHelped
Add 2D-synthesised profile-face augmentation (ablation)classical CSR · COFWaverage errorHelped
Combine DAC-CSR with 2D-synthesised profile-face augmentation (ablation)facial landmark detection · COFWaverage errorHelped

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