AI Paper Atlas

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

ICCV 2025 · Vision-language and multimodal › CLIP and zero-shot · approach: Attribute-based zero-shot learning · 10 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 semantic-based descriptions (SD) (ablation)baseline · NTU-60 55/5 ZSLaccuracy (%): 83.3 -> 85.4Improved
add frequency-enhanced module (FM) (ablation)baseline · NTU-60 55/5 ZSLaccuracy (%): 83.3 -> 85.8Improved
add calibrated loss (CL) (ablation)baseline · NTU-60 55/5 ZSLaccuracy (%): 83.3 -> 84.4Improved
add calibrated loss (CL) (ablation)baseline · NTU-60 48/12 ZSLaccuracy (%): 49.8 -> 54.1Improved
add calibrated loss (CL) (ablation)baseline · NTU-120 96/24 ZSLaccuracy (%): 60.7 -> 60.0Hurt
combine SD, FM and CL (ablation)baseline · NTU-60 55/5 ZSLaccuracy (%): 83.3 -> 86.9Improved
combine SD, FM and CL (ablation)baseline · NTU-60 48/12 ZSLaccuracy (%): 49.8 -> 57.2Improved
add explicit frequency adjustment instead of learnable weights (ablation)FS-VAE · NTU-60 55/5 ZSLaccuracy (%): 84.2 -> 86.9Improved
add explicit frequency adjustment instead of learnable weights (ablation)FS-VAE · NTU-60 48/12 ZSLaccuracy (%): 52.6 -> 57.2Improved
add global description to action label (ablation)text inputs · NTU-60 55/5 ZSLaccuracy (%): 81.9 -> 82.0Improved
add local description alone instead of action label (ablation)text inputs · NTU-60 55/5 ZSLaccuracy (%): 81.9 -> 79.3Hurt
add action label to local and global descriptions (ablation)text inputs · NTU-60 55/5 ZSLaccuracy (%): 83.7 -> 86.9Improved

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