works on
attention mechanisms 1CNN-ViT hybrid 1human pose estimation 1low-resolution image processing 1multi-scale feature extraction 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

cs.CV2026

Cascaded Multi-Scale Attention for Enhanced Multi-Scale Feature Extraction and Interaction with Low-Resolution Images

Xiangyong Lu, Masanori Suganuma, Takayuki Okatani

The paper introduces Cascaded Multi-Scale Attention (CMSA), an attention module for CNN‑ViT hybrid networks that extracts and fuses multi‑scale features without downsampling, impro…