AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Emotion-Aware Multi-View Contrastive Learning for Facial Emotion Recognition

Daeha Kim, Byung Cheol Song

ECCV 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Uncertainty-aware multi-view learning · 18 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 AVCE contrastive loss instead of InfoNCE (ablation)AVCE (AL) · Aff-wildCCC (valence): 0.637 -> 0.682Improved
use AVCE contrastive loss instead of Barlow-Twins (ablation)AVCE (AL) · Aff-wildCCC (valence): 0.653 -> 0.682Improved
add Ldis term (ablation)AVCE (AL) · Aff-wildCCC (valence): 0.642 -> 0.682Improved
add Ldis term (ablation)AVCE (AL) · Aff-wildCCC (arousal): 0.548 -> 0.594Improved
use angular similarity instead of dot-product similarity f1 (ablation)AVCE (AL) · Aff-wildCCC (valence): 0.640 -> 0.682Improved
use valence-penalizing similarity f2 instead of f (ablation)AVCE (AL) · Aff-wildCCC (valence/arousal): 0.682 -> 0.691 (V); 0.594 -> 0.581 (A)Mixed
add negative-pair mining post-processing (ablation)AVCE · Aff-wildCCC (arousal): about 0.02Improved
use AVCE instead of CAF (AL)AVCE (AL) · Aff-wildCCC (valence): 0.54 -> 0.682Improved
use AVCE (AL) instead of CAF (AL)AVCE (AL) · AFEW-VACCC (valence): 0.58 -> 0.629Improved
use AVCE (R18) instead of Sanchez et al.AVCE (R18) · Aff-wild2 (validation)mean CCC: 0.468 -> 0.499Improved
use AVCE explanations in user study vs CAF and baselineAVCE · user study (32 pairs, 12 subjects)top-1 accuracy: 67.96% vs 25.78% and 6.26%Improved

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