Tao Dai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Tao Dai has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Li Zhu
School of Software Engineering, Xi’an Jiaotong University, Xi’an 710049, China
4 shared publications - Qiannan Xu
Xi’an Jiaotong University, Xi’an, China
2 shared publications Daniel Jian Sun
1 shared publicationDehong Li
School of Economics and Management, Chang'an University, Xi'an, Shaanxi 710064, China
1 shared publication- Gang Hua
Dolby Laboratories, Bellevue, WA, USA
1 shared publication - Huiyu Wang1 shared publication
Latest Publications
- 4 December 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 303
Fine-grained reinforcement learning for natural language-based vehicle video clip retrieval
- 4 December 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 303
Fine-grained reinforcement learning for natural language-based vehicle video clip retrieval
- 5 May 2024
- Published by Springer Nature in Machine Vision and Applications
- Vol. 35 (4) , 1-11
Residual feature learning with hierarchical calibration for gaze estimation
- 5 May 2024
- Published by Springer Nature in Machine Vision and Applications
- Vol. 35 (4) , 1-11
Residual feature learning with hierarchical calibration for gaze estimation
- 17 September 2022
- Published by Elsevier in Expert Systems with Applications
- Vol. 213, 118841
Heterogeneous deep graph convolutional network with citation relational BERT for COVID-19 inline citation recommendation
- 17 September 2022
- Published by Elsevier in Expert Systems with Applications
- Vol. 213, 118841
Heterogeneous deep graph convolutional network with citation relational BERT for COVID-19 inline citation recommendation
- 13 November 2020
- Published by Springer Nature in Applied Intelligence
- Vol. 51 (6) , 3435-3449
Low-rank and sparse matrix factorization with prior relations for recommender systems
- 13 November 2020
- Published by Springer Nature in Applied Intelligence
- Vol. 51 (6) , 3435-3449
Low-rank and sparse matrix factorization with prior relations for recommender systems
- 28 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 28 (23299290) , 553-568
Attentive Stacked Denoising Autoencoder With Bi-LSTM for Personalized Context-Aware Citation Recommendation
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.
- 28 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 28 (23299290) , 553-568
Attentive Stacked Denoising Autoencoder With Bi-LSTM for Personalized Context-Aware Citation Recommendation
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.
- 29 May 2019
- Published by Springer Nature in Journal of Ambient Intelligence and Humanized Computing
- Vol. 11 (7) , 2683-2699
Non-negative matrix factorization for implicit aspect identification
- 29 May 2019
- Published by Springer Nature in Journal of Ambient Intelligence and Humanized Computing
- Vol. 11 (7) , 2683-2699
Non-negative matrix factorization for implicit aspect identification
- Open Access
- 16 April 2019
- Published by MDPI AG in Remote Sensing
- Vol. 11 (8) , 922
Exploring Weighted Dual Graph Regularized Non-Negative Matrix Tri-Factorization Based Collaborative Filtering Framework for Multi-Label Annotation of Remote Sensing Images
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.
- 16 April 2019
- Published by MDPI AG in Remote Sensing
- Vol. 11 (8) , 922
Open AccessExploring Weighted Dual Graph Regularized Non-Negative Matrix Tri-Factorization Based Collaborative Filtering Framework for Multi-Label Annotation of Remote Sensing Images
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.
- 2 June 2017
- Published by Springer Nature in Journal of Ambient Intelligence and Humanized Computing
- Vol. 9 (4) , 957-975
Explore semantic topics and author communities for citation recommendation in bipartite bibliographic network
- 2 June 2017
- Published by Springer Nature in Journal of Ambient Intelligence and Humanized Computing
- Vol. 9 (4) , 957-975
Explore semantic topics and author communities for citation recommendation in bipartite bibliographic network