Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
Partial Ring Scan: Revisiting Scan Order in Vision State Space Models
Yi-Kuan Hsieh, Kuan-Chuan Peng, Xin li +3
State Space Models (SSMs) have emerged as efficient alternatives to attention for vision tasks, offering lineartime sequence processing with competitive accuracy. Vision SSMs, howe…
cs.CV2025
Block-based Symmetric Pruning and Fusion for Efficient Vision Transformers
Yi-Kuan Hsieh, Jun-Wei Hsieh, Xin Li +2
Vision Transformer (ViT) has achieved impressive results across various vision tasks, yet its high computational cost limits practical applications. Recent methods have aimed to re…
cs.CV2023
Scale-Aware Crowd Count Network with Annotation Error Correction
Yi-Kuan Hsieh, Jun-Wei Hsieh, Yu-Chee Tseng +2
Traditional crowd counting networks suffer from information loss when feature maps are downsized through pooling layers, leading to inaccuracies in counting crowds at a distance. E…