AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Cross-Domain Multi-Person Human Activity Recognition via Near-Field Wi-Fi Sensing

Xin Li, Jingzhi Hu, Yinghui He, Hongbo Wang, Jin Gan, Jun Luo

TPAMI 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Cross-domain few-shot with transformers · 1 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 inter-class margin enlarging in PT and FT (ablation)WiAnchor · NFS-Fi, RT/HS absentaccuracy without FT samples (%): 54.4 -> 86.3Improved
add inter-class margin enlarging in PT and FT (ablation)WiAnchor · NFS-Fi, categories with FT samplesaccuracy (%): 85.2 -> 91.4Improved
add anchor matching (ablation)WiAnchor · NFS-Fi, RT/HS absentaccuracy without FT samples (%): 52.3 -> 86.3Improved
add anchor matching (ablation)WiAnchor · NFS-Fi, categories with FT samplesaccuracy (%): 86.7 -> 91.4Improved
add composite inference strategy (ablation)WiAnchor · NFS-Fi, RT/HS absentaccuracy without FT samples (%): 79.2 -> 86.3Improved
add composite inference strategy (ablation)WiAnchor · NFS-Fi, categories with FT samplesaccuracy (%): 90.7 -> 91.4Improved
WiAnchor instead of standard fine-tuning for absent categoriesbase GRU model · NFS-Fi, RT and HS absentaccuracy (%): 29.5 -> 86.3 (about 56.8% improvement)Improved
WiAnchor instead of class-sensitive learningclass-sensitive baseline · NFS-Fioverall accuracy (%): 77.7 -> 90.4Improved
WiAnchor instead of data augmentationdata augmentation baseline · NFS-Fioverall accuracy (%): 81.6 -> 90.4Improved
WiAnchor instead of module optimizationmodule optimization baseline · NFS-Fioverall accuracy (%): 79.4 -> 90.4Improved
increase number of source subjects in pre-training beyond sixWiAnchor · NFS-FiaccuracyNo clear effect
increase FT samples per category beyond 10WiAnchor · NFS-FiaccuracyNo clear effect

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