Research map / Vision-language and multimodal / CLIP and zero-shot
Saber: Anchoring Semantics to Scale-Aware Kinetic Salience for Zero-Shot Skeleton Action Recognition
Yongquan Zhu, Biru Ning, Jingyu 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 local temporal folding branch (ablation) | Saber · NTU RGB+D 55/5 | ZSL accuracy: 79.5 -> 87.5 | Improved |
| add strided temporal folding branch (ablation) | Saber · NTU RGB+D 55/5 | ZSL accuracy: 82.8 -> 87.5 | Improved |
| add instance-adaptive high-pass filter (I-A) (ablation) | Saber · NTU RGB+D 55/5 | ZSL accuracy: 79.2 -> 87.5 | Improved |
| use probabilistic anchoring instead of rigid static anchoring (ablation) | Saber · NTU RGB+D 55/5 | ZSL accuracy: 80.2 -> 87.5 | Improved |
| add content-aware kinetic gating (ablation) | Saber · NTU RGB+D 120 110/10 | ZSL accuracy: 70.7 -> 76.8 | Improved |
| use reverse KL divergence instead of L2 distance (ablation) | Saber · NTU RGB+D 55/5 | ZSL accuracy: 81.4 -> 87.5 | Improved |
| add l1 kinetic sparsity regularization (ablation) | Saber · NTU RGB+D 55/5 | ZSL accuracy: 82.4 -> 87.5 | Improved |
| use SAB-Encoder instead of ST-GCN (ablation) | Saber · NTU RGB+D 55/5 | ZSL accuracy: 76.9 -> 87.5 | Improved |
| add Multi-Head Instance-Adaptive module (ablation) | Saber · NTU RGB+D two-person interaction | ZSL accuracy: 69.7 -> 77.9 | Improved |
| compare with SOTA on NTU RGB+D 55/5 GZSL harmonic mean | Saber · NTU RGB+D 55/5 | GZSL H: 75.7 -> 76.1 | Improved |
| compare with SOTA on NTU RGB+D 48/12 ZSL | Saber · NTU RGB+D 48/12 | ZSL accuracy: Neuron 62.7 vs Saber 61.5 | Mixed |
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 4 of 4 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
- Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognition (CVPR 2025 · similarity 0.90)
- Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition (CVPR 2024 · similarity 0.89)
- Semantic-guided Cross-Modal Prompt Learning for Skeleton-based Zero-shot Action Recognition (CVPR 2025 · similarity 0.89)
- Boosting Skeleton-based Zero-Shot Action Recognition with Training-Free Test-Time Adaptation (NeurIPS 2025 · similarity 0.88)
- Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition (CVPR 2025 · similarity 0.88)
- Navigating Open Set Scenarios for Skeleton-Based Action Recognition (AAAI 2024 · similarity 0.87)
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.
