AI Paper Atlas

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

Learning Unseen Emotions from Gestures via Semantically-Conditioned Zero-Shot Perception with Adversarial Autoencoders

Abhishek Banerjee, Uttaran Bhattacharya, Aniket Bera

AAAI 2022 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Transductive and semantic-dictionary zero-shot · 13 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 SC-AAE instead of CADA-VAEGZSL emotion recognition · MPI EBEDB seen and unseen emotion classesharmonic mean: 33.27% -> 58.43%Improved
Use FS-GER instead of STEPfully supervised emotion recognition · MPI EBEDB seen emotion classesaccuracy: 70.38% -> 77.61%Improved
Set δ to 1.5 while γ is 1 (ablation)SC-AAE · MPI EBEDB seen and unseen emotion classesharmonic meanImproved
Vary γ while keeping δ at 1.5 (ablation)SC-AAE · MPI EBEDB seen and unseen emotion classesharmonic meanNo clear effect
Use latent embedding size d=16 (ablation)SC-AAE · MPI EBEDB seen and unseen emotion classesharmonic meanImproved

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