AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Zero-Shot Emotion Recognition via Affective Structural Embedding

Chi Zhan, Dongyu She, Sicheng Zhao, Ming-Ming Cheng, Jufeng Yang

ICCV 2019 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 60 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
add the affective adversarial constraint Ladv (ablation)affective structural embedding · FI 6:2accuracy (%): 66.41 -> 67.53Improved
add Ladv to the basic embedding only (with L*as) (ablation)Base · FI 6:2accuracy (%): 65.12 -> 65.46Improved
add structural alignment loss Las (ablation)Base · FI 6:2accuracy (%): 65.12 -> 66.41Improved
add reconstruction loss Lre to Las (ablation)Base + Las · FI 6:2accuracy (%): 65.12 -> 67.28Improved
add class-center alignment (second part of Las) (ablation)Base + L*as · FI 6:2accuracy (%): 65.46 -> 66.41Improved
train all components together (ablation)affective structural embedding · FI 6:2accuracy (%): 67.53 -> 68.87Improved
concatenate ANP and deep features (M) for baseline methods (ablation)comparison ZSL methods · FI/ArtPhoto/Abstract/IAPSa/Emotion6accuracy (%)No clear effect
use ANP features instead of deep featuresbaseline ZSL methods · Emotion6accuracy (%)Mixed
use proposed method over CDLZSL emotion recognition · FI generalized ZSL 6:2accuracy (%): 35.72 -> 39.54Improved
use proposed method over CDL in cross-dataset recognitionZSL emotion recognition · FI->Emo6accuracy (%): 55.15 -> 61.94Improved
change test classes to excitement and sadnessOurs · FI 6:2accuracy (%): 68.87 -> 74.03Improved
change test classes to all negative emotionsOurs · FI 4:4accuracy (%): 54.73 -> 42.92Hurt

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