368 Papers
929 Citations
Liang Xiao is an academic researcher from Nanjing University of Science and Technology. The author has contributed to research in topics: Computer science & Hyperspectral imaging. The author has an hindex of 24, co-authored 277 publications. Previous affiliations of Liang Xiao include Royal College of Surgeons in Ireland & Hubei University of Technology.
Chat about Author
Papers
Fast unstructured road detection and tracking from monocular video
Liang Xiao,Bin Dai,Tingbo Hu,Tao Wu +3 more
- 23 May 2015
TL;DR: A fast particle filer based unstructured road detection and tracking algorithm that can detect and track the road robustly in various unstructuring environments within real time is presented.
Fractional order variational pan-sharpening
Pengfei Liu,Liang Xiao,Songze Tang,Le Sun +3 more
- 10 Jul 2016
TL;DR: Experimental results show that the proposed method outperforms various well-known pan-sharpening methods in terms of higher spatial and spectral qualities.
A Novel Interaction Convolutional Network Based on Dependency Trees for Aspect-Level Sentiment Analysis
Lei Mao,Jianxia Chen,Shi Dong,Liang Xiao,Haoying Si,Shu Li,Xinyun Wu +6 more
TL;DR: This paper proposes ASAI-DT, a novel aspect-level sentiment analysis model using interactive convolutional networks and dependency trees, which outperforms existing models by accurately capturing relationships between aspect and viewpoint words in sentences.
Normal curvature-induced variational model for image restoration
Pengfei Liu,Liang Xiao,Tao Li +2 more
TL;DR: A novel normal curvature-induced variational model which involves a higher-order regulariser based on thenormal curvature prior information of image surface is proposed for image restoration and can achieve better and more balanced results in terms of peak-signal-to-noise ratio, convergence rate and restoration quality.
Efficient Deep Learning of Nonlocal Features for Hyperspectral Image Classification
TL;DR: Zhang et al. as mentioned in this paper proposed a deep fully convolutional network (FCN) with an efficient nonlocal module, named ENL-FCN, for hyperspectral image (HSI) classification.