Research map / Vision-language and multimodal / CLIP and zero-shot
Frequency-Semantic Enhanced Variational Autoencoder for Zero-Shot Skeleton-based Action Recognition
Wenhan Wu, Zhishuai Guo, Chen Chen, Hongfei Xue, Aidong Lu
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 semantic-based descriptions (SD) (ablation) | baseline · NTU-60 55/5 ZSL | accuracy (%): 83.3 -> 85.4 | Improved |
| add frequency-enhanced module (FM) (ablation) | baseline · NTU-60 55/5 ZSL | accuracy (%): 83.3 -> 85.8 | Improved |
| add calibrated loss (CL) (ablation) | baseline · NTU-60 55/5 ZSL | accuracy (%): 83.3 -> 84.4 | Improved |
| add calibrated loss (CL) (ablation) | baseline · NTU-60 48/12 ZSL | accuracy (%): 49.8 -> 54.1 | Improved |
| add calibrated loss (CL) (ablation) | baseline · NTU-120 96/24 ZSL | accuracy (%): 60.7 -> 60.0 | Hurt |
| combine SD, FM and CL (ablation) | baseline · NTU-60 55/5 ZSL | accuracy (%): 83.3 -> 86.9 | Improved |
| combine SD, FM and CL (ablation) | baseline · NTU-60 48/12 ZSL | accuracy (%): 49.8 -> 57.2 | Improved |
| add explicit frequency adjustment instead of learnable weights (ablation) | FS-VAE · NTU-60 55/5 ZSL | accuracy (%): 84.2 -> 86.9 | Improved |
| add explicit frequency adjustment instead of learnable weights (ablation) | FS-VAE · NTU-60 48/12 ZSL | accuracy (%): 52.6 -> 57.2 | Improved |
| add global description to action label (ablation) | text inputs · NTU-60 55/5 ZSL | accuracy (%): 81.9 -> 82.0 | Improved |
| add local description alone instead of action label (ablation) | text inputs · NTU-60 55/5 ZSL | accuracy (%): 81.9 -> 79.3 | Hurt |
| add action label to local and global descriptions (ablation) | text inputs · NTU-60 55/5 ZSL | accuracy (%): 83.7 -> 86.9 | Improved |
Closest papers by meaning
- Semantic-guided Cross-Modal Prompt Learning for Skeleton-based Zero-shot Action Recognition (CVPR 2025 · similarity 0.91)
- Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition (CVPR 2024 · similarity 0.90)
- Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton 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)
- Heterogeneous Skeleton-Based Action Representation Learning (CVPR 2025 · similarity 0.88)
- Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition (CVPR 2025 · similarity 0.88)
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.
