3 papers
cs.CV2022
Self-attention on Multi-Shifted Windows for Scene Segmentation
Litao Yu, Zhibin Li, Jian Zhang +1
Scene segmentation in images is a fundamental yet challenging problem in visual content understanding, which is to learn a model to assign every image pixel to a categorical label.…
cs.CV2022
Horizontal and Vertical Attention in Transformers
Litao Yu, Jian Zhang
Transformers are built upon multi-head scaled dot-product attention and positional encoding, which aim to learn the feature representations and token dependencies. In this work, we…
cs.CV2022
Spatial-temporal Analysis for Automated Concrete Workability Estimation
Litao Yu, Jian Zhang, Mohammed Bennamoun +3
Concrete workability measure is mostly determined based on subjective assessment of a certified assessor with visual inspections. The potential human error in measuring the workabi…