AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

SkeletonContext: Skeleton-side Context Prompt Learning for Zero-Shot Skeleton-based Action Recognition

Ning Wang, Tieyue Wu, Naeha Sharif, Farid Boussaid, Guangming Zhu, Lin Mei, Mohammed Bennamoun, Liang Zhang

CVPR 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Attribute-based zero-shot learning · 1 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 Differential Joint Encoder (ablation)Shift-GCN baseline · NTU-60 (55/5) ZSLaccuracy: 79.4 -> 81.4Improved
add Semantic Context Grounding (ablation)baseline + DJE · NTU-60 (55/5) ZSLaccuracy: 81.4 -> 83.9Improved
add Progressive Partial Masking (ablation)baseline + DJE + SCG · NTU-60 (55/5) ZSLaccuracy: 83.9 -> 87.4Improved
add Key Part Decoupling (ablation)baseline + DJE + SCG + PPM · NTU-60 (55/5) ZSLaccuracy: 87.4 -> 89.6Improved
add Key Part Decoupling (ablation)baseline + DJE + SCG + PPM · NTU-120 (96/24) GZSLaccuracy: 55.9 -> 56.1Improved
add context reconstruction loss L_ccr (ablation)SkeletonContext · NTU-60 (55/5) ZSLaccuracy: 86.4 -> 89.6Improved
add key part decoupling loss L_kpd (ablation)SkeletonContext · NTU-60 (55/5) ZSLaccuracy: 88.2 -> 89.6Improved
add both L_ccr and L_kpd (ablation)SkeletonContext · NTU-60 (55/5) GZSLharmonic mean: 75.1 -> 77.1Improved
use all three slots instead of environment only (ablation)structured context prompt · NTU-60 (55/5) ZSLaccuracy: 84.4 -> 89.6Improved
use used-object and target slots in addition to environment (ablation)structured context prompt · NTU-60 (55/5) ZSLaccuracy: 87.0 -> 89.6Improved
use SkeletonContext instead of FS-VAE on hard similar classesNTU-120 (96/24) · Hard level GZSLaccuracy: 50.7 -> 55.8Improved
use SkeletonContext instead of FS-VAE on easy similar classesNTU-120 (96/24) · Easy level ZSLaccuracy: 61.5 -> 63.3Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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