AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Hierarchical Consistent Contrastive Learning for Skeleton-Based Action Recognition with Growing Augmentations

Jiahang Zhang, Lilang Lin, Jiaying Liu

AAAI 2023 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Inductive bias and minimal representations · 68 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 HiCLR's growing augmentation and asymmetric hierarchical consistency with strong augmentationsST-GCN · NTU60, linear evaluationaccuracy: 78.9 -> 80.4; 83.8 -> 85.5Improved
Use HiCLR's growing augmentation and asymmetric hierarchical consistency with strong augmentationsDSTA-Net · NTU120, linear evaluationaccuracy: 66.0 -> 67.3; 68.7 -> 69.9Improved
Add Random Mask in HiCLR's strong-augmentation branch (ablation)Joint stream · NTU60 xsub, linear evaluationaccuracy: 68.3 -> 77.6Improved
Add Random Mask in HiCLR's strong-augmentation branch (ablation)Joint stream · NTU60 xview, linear evaluationaccuracy: 76.4 -> 82.0Improved
Add Drop/Add Edges as the strong augmentation (ablation)Bone stream · NTU60 xsub, linear evaluationaccuracy: 69.4 -> 76.9Improved
Use Random Mask before weaker augmentations rather than after them (ablation)HiCLR, joint stream · NTU60 xsub, linear evaluationaccuracy: 77.6 -> 74.7Hurt
Combine BA and NA into one branch and use two branches (ablation)HiCLR, joint stream · NTU60 xsub, linear evaluationaccuracy: 77.6 -> 74.0Hurt
Combine NA and Mask into one branch and use two branches (ablation)HiCLR, joint stream · NTU60 xsub, linear evaluationaccuracy: 77.6 -> 76.7Hurt
Use KL divergence rather than cosine similarity for hierarchical consistency (ablation)HiCLR, joint stream · NTU60 xsub, linear evaluationaccuracy: 75.8% -> 77.6%Improved
Use KL divergence rather than L1 for hierarchical consistency (ablation)HiCLR, joint stream · NTU60 xsub, linear evaluationaccuracy: 73.6% -> 77.6%Improved
Apply Random Mask directly, without the hierarchical design (ablation)Baseline, joint stream · NTU60 xsub, linear evaluationaccuracy: 68.3% -> 56.7%Hurt
Use the hierarchical design with Random Mask instead of applying it directly (ablation)Baseline, joint stream · NTU60 xsub, linear evaluationaccuracy: 56.7% -> 77.6%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