AI Paper Atlas

Research map / Video / Action recognition

Modeling the Relative Visual Tempo for Self-supervised Skeleton-based Action Recognition

Yisheng Zhu, Hu Han, Zhengtao Yu, Guangcan Liu

ICCV 2023 · Video › Action recognition · approach: Skeleton-based action recognition · 40 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 tempo prediction with relative visual tempo learning (ablation)RVTCLR · NTU-60 Xsub linear jointtop-1 accuracy: 52.7 -> 63.1Improved
add appearance-consistency task to RVTL (ablation)RVTCLR · NTU-60 Xsub linear jointtop-1 accuracy: 63.1 -> 73.3Improved
add nearest neighbor mining stage (ablation)AC+RVTL · NTU-60 Xsub linear jointtop-1 accuracy: 73.3 -> 74.4Improved
add Distribution-Consistency branch on motion stream (ablation)RVTCLR · NTU-60 Xsub linear motiontop-1 accuracy: 57.5 -> 70.8Improved
add DC branch on joint stream (ablation)RVTCLR · NTU-60 Xview linear jointtop-1 accuracy: 79.4 -> 79.1No clear effect
use Gaussian noise, blur and channel mask as strong augmentations instead of normal (ablation)SDA in DC branch · NTU-60 Xsub linear motiontop-1 accuracy: 55.2 -> 67.9Improved
add spatial flip or temporal flip or rotate as strong augmentation (ablation)SDA · NTU-60 Xview linear motiontop-1 accuracy: 58.2 -> 55.9 (temporal flip)Hurt
add IIPB and NLB (FSEM) (ablation)DC branch · NTU-60 Xsub linear motiontop-1 accuracy: 67.9 -> 70.8Improved
use DD loss with weak-view distribution instead of one-hot targets (ablation)DC branch · NTU-60 Xsub linear motiontop-1 accuracy: 64.6 -> 70.8Improved
RVTCLR+ vs 3s-AimCLR under linear eval on NTU-120 Xsub3s-RVTCLR+ · NTU-120 Xsub lineartop-1 accuracy: 68.2 -> 68.0No clear effect

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