Tao Dai

Dr. Tao Dai

School of Software Engineering, Xi’an Jiaotong University

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
28 October 2019 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Closed access
TDTao Dai
Tao Dai
LZLi Zhu
Li Zhu
YWYaxiong Wang
Yaxiong Wang
KCKathleen M. Carley
Kathleen M. Carley
The rapid growth of scientific publications brings the problem of finding appropriate citations for authors. Context-aware citation recommendation is an essential technology to overcome this obstacle when given a fragment of manuscript. In this article, we propose a novel neural network model for context-aware citation recommendation by combining stacked denoising autoencoders (SDAE) and Bi-LSTM. To obtain effective embedding for cited paper, we extend SDAE into attentive SDAE (ASDAE) by utilizing the attentive information from citation context, which essentially enhance the learning ability of original SDAE. For citation context, we devise an attentive Bi-LSTM to obtain effective embedding. Specifically, the attentive Bi-LSTM is able to extract suitable citation context and recommend citations simultaneously when given a long text, which is a issue that few papers addressed before. We also integrate personalized author information to improve the performance of recommendation. Our model is essentially a seemly integration of different types of neural network with latent variables. We derive the generative process of our model, and develop a learning algorithm based on maximum a posteriori (MAP) estimation. Experimental results on the RefSeer, ANN and DBLP datasets show that our model outperforms baseline methods.

2 June 2017 in Journal of Ambient Intelligence and Humanized Computing
Verified
Journal Article
Closed access
PDF file
TDTao Dai
Tao Dai
LZLi Zhu
Li Zhu
XCXiaoyan Cai
Xiaoyan Cai
SPShirui Pan
Shirui Pan
SYSheng Yuan
Sheng Yuan

29 May 2019 in Journal of Ambient Intelligence and Humanized Computing
Verified
Journal Article
Closed access
PDF file
QXQiannan Xu
Qiannan Xu
LZLi Zhu
Li Zhu
TDTao Dai
Tao Dai
LGLei Guo
Lei Guo
SCSisi Cao
Sisi Cao

17 September 2022 in Expert Systems with Applications
Verified
Journal Article
Closed access
TDTao Dai
Tao Dai
JZJie Zhao
Jie Zhao
DLDehong Li
Dehong Li
STShun Tian
Shun Tian
XZXiangmo Zhao
Xiangmo Zhao
SPShirui Pan
Shirui Pan

13 November 2020 in Applied Intelligence
Verified
Journal Article
Closed access
PDF file
JWJie Wang
Jie Wang
LZLi Zhu
Li Zhu
TDTao Dai
Tao Dai
QXQiannan Xu
Qiannan Xu
TGTianyu Gao
Tianyu Gao

16 April 2019 in Remote Sensing
Verified
Journal Article
Open access
PDF file
JZJuli Zhang
Juli Zhang
JZJunyi Zhang
Junyi Zhang
TDTao Dai
Tao Dai
ZHZhanzhuang He
Zhanzhuang He
Manually annotating remote sensing images is laborious work, especially on large-scale datasets. To improve the efficiency of this work, we propose an automatic annotation method for remote sensing images. The proposed method formulates the multi-label annotation task as a recommended problem, based on non-negative matrix tri-factorization (NMTF). The labels of remote sensing images can be recommended directly by recovering the image–label matrix. To learn more efficient latent feature matrices, two graph regularization terms are added to NMTF that explore the affiliated relationships on the image graph and label graph simultaneously. In order to reduce the gap between semantic concepts and visual content, both low-level visual features and high-level semantic features are exploited to construct the image graph. Meanwhile, label co-occurrence information is used to build the label graph, which discovers the semantic meaning to enhance the label prediction for unlabeled images. By employing the information from images and labels, the proposed method can efficiently deal with the sparsity and cold-start problem brought by limited image–label pairs. Experimental results on the UCMerced and Corel5k datasets show that our model outperforms most baseline algorithms for multi-label annotation of remote sensing images and performs efficiently on large-scale unlabeled datasets.