AI Paper Atlas

Research map / Detection and segmentation / CNN features

DenseReg: Fully Convolutional Dense Shape Regression In-The-Wild

CVPR 2017 · Detection and segmentation › CNN features · approach: Local features and context in CNNs · 201 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 DenseReg to initialize MDM rather than use DenseReg aloneDenseReg on 300W · 300W testing datasetAUC: 0.3605 -> 0.5219Helped
Use DenseReg to initialize MDM rather than use DenseReg aloneDenseReg on 300W · 300W testing datasetFailure Rate (%): 10.83 -> 3.67Helped
Use DenseReg to initialize MDM rather than use DenseReg aloneDenseReg on 300VW · 300VW testing datasetAUC: 0.4320 -> 0.5937Helped
Use DenseReg to initialize MDM rather than use DenseReg aloneDenseReg on 300VW · 300VW testing datasetFailure Rate (%): 8.1 -> 4.57Helped
Use DenseReg to initialize MDM rather than use DenseReg aloneDenseReg on human ear landmark localization · Human ear test setAUC: 0.4150 -> 0.4842Helped
Add quantized classification and region-specific residual regression instead of plain coordinate regression (ablation)DenseReg · Dense shape regressionCoordinate estimation performanceHelped
Add the depth prediction branch (ablation)DenseReg · Face depth estimationPerformance of other branchesNo clear effect

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