AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Semi-Supervised Teacher-Reference-Student Architecture for Action Quality Assessment

Wulian Yun, Mengshi Qi, Fei Peng, Huadong Ma

ECCV 2024 · Label-efficient and robust learning › Semi-supervised learning · approach: Confidence-based pseudo-label selection · 12 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 reference network to teacher-student baseline (ablation)teacher-student baseline · MTL-AQA (10% labels)Spearman correlation: 0.751 -> 0.811Improved
add reference network to teacher-student baseline (ablation)teacher-student baseline · MTL-AQA (40% labels)Spearman correlation: 0.865 -> 0.891Improved
add confidence memory to teacher network (ablation)teacher-student baseline · MTL-AQA (10% labels)Spearman correlation: 0.751 -> 0.794Improved
add confidence memory to teacher network (ablation)teacher-student baseline · MTL-AQA (40% labels)Spearman correlation: 0.865 -> 0.870No clear effect
update memory by confidence instead of direct current-output update (ablation)Base + RN · MTL-AQA (10% labels)Spearman correlation: 0.811 -> 0.813Improved
add confidence memory to reference network (ablation)Base + RN + TM · MTL-AQA (10% labels)Spearman correlation: 0.813 -> 0.825Improved
add confidence memory to reference network (ablation)Base + RN + TM · MTL-AQA (40% labels)Spearman correlation: 0.893 -> 0.901Improved
increase labeled data proportion from 10% to 40% (ablation)Ours · MTL-AQASpearman correlation: 0.825 -> 0.901Improved
use semi-supervised teacher-reference-student instead of S4AQAOurs · Rhythmic Gymnastics (40% labels, average)Spearman correlation: 0.342 -> 0.529Improved
use semi-supervised teacher-reference-student instead of S4AQAOurs · JIGSAWS Knot Tying (50% labels)Spearman correlation: 0.813 -> 0.753Hurt

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