AI Paper Atlas

Research map / Image generation / Editing and style transfer

Masked Linear Regression for Learning Local Receptive Fields for Facial Expression Synthesis

Nazar Khan, Arbish Akram, Arif Mahmood, Sania Ashraf, Kashif Murtaza

IJCV 2019 · Image generation › Editing and style transfer · approach: Identity-preserving face manipulation · 9 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 masked local receptive fields instead of dense l2 regressionridge regression · CK+ expression synthesis 12 mappings (grayscale)mean MSE x100: 1.904 -> 1.460Improved
replace l1 sparsity with masked regressionmasked regression · CK+ expression synthesis 12 mappings (grayscale)mean MSE x100: 1.548 -> 1.460Improved
replace l0 sparsity with masked regressionmasked regression · CK+ expression synthesis 12 mappings (grayscale)mean MSE x100: 1.665 -> 1.460Improved
use 5x5 receptive field instead of 3x3 (ablation)masked regression · CK+ expression synthesis 12 mappings (grayscale)mean MSE x100: 1.487 -> 1.460Improved
use 9x9 receptive field instead of 5x5 (ablation)masked regression · CK+ expression synthesis 12 mappings (grayscale)mean MSE x100: 1.460 -> 1.548Hurt
use 7x7 receptive field instead of 5x5 (ablation)masked regression · CK+ expression synthesis 12 mappings (grayscale)mean MSE x100: 1.460 -> 1.501Hurt
apply masked regression per channel to RGBmasked regression · Expression synthesis RGB 56x56 12 mappingsmean MSE x100: 0.907 -> 0.862Improved
use masked regression instead of l1 for training speedmasked regression · RGB expression mappingstraining time (s): 16.782 -> 0.010Improved
use masked regression instead of GANs for model sizemasked regression · 128x128 imagesmodel size (x10^4 parameters): 4100 -> 16.2Improved
use masked regression instead of Pix2Pix for speedmasked regression · 128x128 imagesexecution time (msec): 320 -> 2.70Improved
use masked regression instead of Pix2Pix on out-of-dataset imagesmasked regression · out-of-dataset imagesaccuracy drop (pct points): 35.72 -> 12.39Improved
learned bias added to weight transformation (ablation)masked regression · qualitative synthesisvisual qualityImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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