Yao Xiao

Yao Xiao

Auto-generated profile, based on publicly available information

Yao Xiao

Singapore University of Technology and Design

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 June 2015
Verified
Conference Paper
Closed access
YXYao Xiao
Yao Xiao
CLCewu Lu
Cewu Lu
ETEfstratios Tsougenis
Efstratios Tsougenis
YLYongyi Lu
Yongyi Lu
CTChi-Keung Tang
Chi-Keung Tang
Distance metric plays a key role in grouping superpixels to produce object proposals for object detection. We observe that existing distance metrics work primarily for low complexity cases. In this paper, we develop a novel distance metric for grouping two superpixels in high-complexity scenarios. Combining them, a complexity-adaptive distance measure is produced that achieves improved grouping in different levels of complexity. Our extensive experimentation shows that our method can achieve good results in the PASCAL VOC 2012 dataset surpassing the latest state-of-the-art methods.

1 June 2014
Verified
Conference Paper
Closed access
YXYao Xiao
Yao Xiao
ETEfstratios Tsougenis
Efstratios Tsougenis
CTChi-Keung Tang
Chi-Keung Tang
We present the first automatic method to remove shadows from single RGB-D images. Using normal cues directly derived from depth, we can remove hard and soft shadows while preserving surface texture and shading. Our key assumption is: pixels with similar normals, spatial locations and chromaticity should have similar colors. A modified nonlocal matching is used to compute a shadow confidence map that localizes well hard shadow boundary, thus handling hard and soft shadows within the same framework. We compare our results produced using state-of-the-art shadow removal on single RGB images, and intrinsic image decomposition on standard RGB-D datasets.

1 January 2023
Verified
Conference Paper
Open access
PDF file
YXYao Xiao
Yao Xiao
LXLu Xu
Lu Xu
JLJiaxi Li
Jiaxi Li
WLWei Lu
Wei Lu
Xiaoli LiXiaoli Li
Xiaoli Li
Yao Xiao, Lu Xu, Jiaxi Li, Wei Lu, Xiaoli Li. Findings of the Association for Computational Linguistics: EMNLP 2023. 2023.

1 October 2021 in IOP Conference Series: Earth and Environmental Science
Verified
Conference Paper
Open access
PDF file
CXChenlin Xiang
Chenlin Xiang
YZYingbin Zhang
Yingbin Zhang
YXYao Xiao
Yao Xiao
CLChao Lv
Chao Lv
Based on coupled analysis and energy approach, this study investigates the relationship between the direction of rupture propagation and the predominant direction of pulse-like ground motions and landslides during Chi-Chi earthquake and Hualien earthquake. 46 pulse-like ground motions are selected to study. The results show that pulse ground motions containing high-energy pulse tend to be perpendicular to the direction of fault rupture propagation in thrust events. In contrast, it occurred along the direction of fault rupture propagation in strike-slip events. The predominant direction of landslides is stronger directionality of rupture propagation in thrust events. It can provide research foundation for the risk zoning of regional earthquake landslides.

16 October 2023 in arXiv
Verified
Preprint
Open access
PDF file
YXYao Xiao
Yao Xiao
LXLu Xu
Lu Xu
JLJiaxi Li
Jiaxi Li
WLWei Lu
Wei Lu
Xiaoli LiXiaoli Li
Xiaoli Li
While prompt tuning approaches have achieved competitive performance with high efficiency, we observe that they invariably employ the same initialization process, wherein the soft prompt is either randomly initialized or derived from an existing embedding vocabulary. In contrast to these conventional methods, this study aims to investigate an alternative way to derive soft prompt. Our empirical studies show that the soft prompt typically exhibits a low intrinsic rank characteristic. With such observations, we propose decomposed prompt tuning, a novel approach that utilizes low-rank matrices to initialize the soft prompt. Through the low-rank reparameterization, our method significantly reduces the number of trainable parameters while maintaining effectiveness. Experimental results on the SuperGLUE benchmark in both high-resource and low-resource scenarios demonstrate the effectiveness of the proposed method.

1 January 2020
Verified
Conference Paper
Closed access
WXW. Xiao
W. Xiao
GLG. Lei
G. Lei
PLP. Li
P. Li
YXY. Xiao
Y. Xiao
YTYanghui Tan
Yanghui Tan