AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Text-guided Feature Disentanglement for Cross-modal Gait Recognition

Zhiyang Lu, Ming Cheng

CVPR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Unimodal-to-multimodal representation transfer · 0 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 Gait Modality Text Dictionary guidance (ablation)TCFDNet · SUSTech1K 3D->2DRank-1: 56.2 -> 61.7Improved
add Feature Stability Enhancement (ablation)TCFDNet · SUSTech1K 3D->2DRank-1: 59.8 -> 61.7Improved
add Feature Stability Enhancement (ablation)TCFDNet · SUSTech1K 3D->2DRank-5: 80.6 -> 82.5Improved
add Text-guided Feature Disentanglement (with FSE absent) (ablation)TCFDNet · SUSTech1K 3D->2DRank-1: 58.9 -> 59.8Improved
add ResNet, MF and SW to ViT-only backbone (ablation)TCFDNet · SUSTech1K 3D->2DRank-1: 54.9 -> 61.7Improved
add Spatial Weighting module (ablation)TCFDNet · SUSTech1K 3D->2DRank-1: 56.7 -> 58.4Improved
add ViT and MF to ResNet+SW backbone (ablation)TCFDNet · SUSTech1K 3D->2DRank-1: 58.4 -> 61.7Improved
set top-k text prototypes to 16 (ablation)TCFDNet · SUSTech1KRank-1Improved

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