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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add Differential Joint Encoder (ablation) | Shift-GCN baseline · NTU-60 (55/5) ZSL | accuracy: 79.4 -> 81.4 | Improved |
| add Semantic Context Grounding (ablation) | baseline + DJE · NTU-60 (55/5) ZSL | accuracy: 81.4 -> 83.9 | Improved |
| add Progressive Partial Masking (ablation) | baseline + DJE + SCG · NTU-60 (55/5) ZSL | accuracy: 83.9 -> 87.4 | Improved |
| add Key Part Decoupling (ablation) | baseline + DJE + SCG + PPM · NTU-60 (55/5) ZSL | accuracy: 87.4 -> 89.6 | Improved |
| add Key Part Decoupling (ablation) | baseline + DJE + SCG + PPM · NTU-120 (96/24) GZSL | accuracy: 55.9 -> 56.1 | Improved |
| add context reconstruction loss L_ccr (ablation) | SkeletonContext · NTU-60 (55/5) ZSL | accuracy: 86.4 -> 89.6 | Improved |
| add key part decoupling loss L_kpd (ablation) | SkeletonContext · NTU-60 (55/5) ZSL | accuracy: 88.2 -> 89.6 | Improved |
| add both L_ccr and L_kpd (ablation) | SkeletonContext · NTU-60 (55/5) GZSL | harmonic mean: 75.1 -> 77.1 | Improved |
| use all three slots instead of environment only (ablation) | structured context prompt · NTU-60 (55/5) ZSL | accuracy: 84.4 -> 89.6 | Improved |
| use used-object and target slots in addition to environment (ablation) | structured context prompt · NTU-60 (55/5) ZSL | accuracy: 87.0 -> 89.6 | Improved |
| use SkeletonContext instead of FS-VAE on hard similar classes | NTU-120 (96/24) · Hard level GZSL | accuracy: 50.7 -> 55.8 | Improved |
| use SkeletonContext instead of FS-VAE on easy similar classes | NTU-120 (96/24) · Easy level ZSL | accuracy: 61.5 -> 63.3 | Improved |
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.
- Neuron — Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognition (CVPR 2025) · better on 9 of 10 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
- Semantic-guided Cross-Modal Prompt Learning for Skeleton-based Zero-shot Action Recognition (CVPR 2025 · similarity 0.94)
- Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognition (CVPR 2025 · similarity 0.92)
- Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition (CVPR 2024 · similarity 0.92)
- Heterogeneous Skeleton-Based Action Representation Learning (CVPR 2025 · similarity 0.90)
- Boosting Skeleton-based Zero-Shot Action Recognition with Training-Free Test-Time Adaptation (NeurIPS 2025 · similarity 0.89)
- Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition (CVPR 2025 · similarity 0.89)
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.
