AI Paper Atlas

Research map / Video / Action recognition

Feature Hallucination for Self-supervised Action Recognition

Lei Wang, Piotr Koniusz

IJCV 2025 · Video › Action recognition · approach: Disentangled action recognition · 7 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 Power Normalization (AsinhE, SigmE or AxMin) to the HAF and BoW/FV streams (ablation)hallucination pipeline · HMDB-51 (split 1)accuracy: 82.29 -> 83.20Improved
add multiple sketches per BoW plus Power Normalization (ablation)HAF*+BoW halluc. (256px) · MPII Cooking ActivitiesmAP: 77.8 -> 80.4Improved
add multiple sketches per BoW plus Power Normalization (ablation)HAF+BoW halluc. (512px) · MPII Cooking ActivitiesmAP: 78.5 -> 81.7Improved
double the frame resolution to 512px before human detectionHAF+BoW hal.+MSK/PN · MPII Cooking ActivitiesmAP: 80.4 -> 81.7Improved
double the frame resolution to 512px before human detectionHAF+BoW halluc. · MPII Cooking ActivitiesmAP: 77.8 -> 78.5Improved

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