AI Paper Atlas

Research map / Video / Action recognition

Knowledge-Spreader: Learning Semi-Supervised Facial Action Dynamics by Consistifying Knowledge Granularity

Xiaotian Li, Xiang Zhang, Taoyue Wang, Lijun Yin

ICCV 2023 · Video › Action recognition · approach: Temporal action segmentation · 22 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
replace Transformer relation encoders with vanilla MLP (ablation)Knowledge-Spreader · BP4D (50% labels)F1: 64.5 -> 62.8Hurt
replace Transformer relation encoders with vanilla MLP (ablation)Knowledge-Spreader · DISFA (50% labels)F1: 61.6 -> 60.2Hurt
add knowledge distillation losses Ls and Lt (knowledge spreading) (ablation)Knowledge-Spreader · BP4D and DISFA (50% labels)F1: -2.0% on BP4D, -1.5% on DISFA when removedImproved
add spatial knowledge distillation (SKD) (ablation)Knowledge-Spreader · BP4D and DISFA (50% labels)F1: -1.3% on BP4D, -1.1% on DISFA when removedImproved
add temporal knowledge distillation (TKD) (ablation)Knowledge-Spreader · BP4D and DISFA (50% labels)F1: -0.9% on BP4D, -1.2% on DISFA when removedImproved
add Perturbation-aware Pseudo-labeling module (ablation)Knowledge-Spreader · BP4D and DISFA (50% labels)F1: -0.8% on BP4D, -1.0% on DISFA when removedImproved
replace self-supervised shuffle classifier with hard confidence threshold (ablation)Knowledge-Spreader · BP4D and DISFA (50% labels)F1: -0.3% on BP4D, -0.4% on DISFAHurt
filter pseudo labels with PPL instead of naive pseudo-labeling (ablation)Knowledge-Spreader · BP4D (10% labels)pseudo-label accuracy (%): 73.36% -> 76.35%Improved
use KS with only 2% labels on BP4D versus supervised methods with 100% labelsKnowledge-Spreader · BP4DF1: KS 10% labels 64.4 vs FAUDT 100% 64.2Improved
use KS instead of Pseudo-label, FixMatch or TCL under extremely few labelssemi-supervised AU detection · BP4D (1% labels)F1: 55.6 -> 59.9 vs TCLImproved

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