Xuejing Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xuejing Li has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Tao Jing
School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China
2 shared publications - Zhewei Zhang
Department of Electronic Engineering, Tsinghua University, Beijing, China
2 shared publications - Bowen Ding
Artificial Intelligence Research Institute of China Unicom, Beijing 100048, China
1 shared publication Chunhua Tian
K2data Ltd. Research Department of artificial intelligence, Beijing, China
1 shared publicationHaohui Fu
Beijing Jiaotong University
1 shared publication- Meilin Gao
Institution of Electronic Information Engineering, Beijing Jiaotong University, Shang Yuan Road No. 3, Haidian District, Beijing 100044, China
1 shared publication
Latest Publications
- Open Access
- 30 June 2019
- Published by MDPI AG in Applied Sciences
- Vol. 9 (13) , 2670
A Model-Based Approach of Foreground Region of Interest Detection for Video Codecs
Detecting the Region of Interest (ROI) for video clips is a significant and useful technique both in video codecs and surveillance/monitor systems. In this paper, a new model-based detection method is designed which suits video compression codecs by proposing two models: an “inter” and “intra” model. The “inter” model exploits the motion information represented as blocks by global motion compensation approaches while the “intra” model extracts the objects details through objects filtering and image segmentation procedures. Finally, the detection results are formed through a new clustering with fine-tune approach from the “intra” model assisted with the “inter” model. Experimental results show that the proposed method fits well for real-time video codecs and it achieves a good performance both on detection precision and on computing time. In addition, the proposed method is versatile for a wide range of surveillance videos with different characteristics.
- 30 June 2019
- Published by MDPI AG in Applied Sciences
- Vol. 9 (13) , 2670
Open AccessA Model-Based Approach of Foreground Region of Interest Detection for Video Codecs
Detecting the Region of Interest (ROI) for video clips is a significant and useful technique both in video codecs and surveillance/monitor systems. In this paper, a new model-based detection method is designed which suits video compression codecs by proposing two models: an “inter” and “intra” model. The “inter” model exploits the motion information represented as blocks by global motion compensation approaches while the “intra” model extracts the objects details through objects filtering and image segmentation procedures. Finally, the detection results are formed through a new clustering with fine-tune approach from the “intra” model assisted with the “inter” model. Experimental results show that the proposed method fits well for real-time video codecs and it achieves a good performance both on detection precision and on computing time. In addition, the proposed method is versatile for a wide range of surveillance videos with different characteristics.
- 23 January 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 30 (3) , 632-645
Objects Discovery Based on Co-Occurrence Word Model With Anchor-Box Polishing
State-of-art objects discovery approaches can be categorized into two categories: The deep learning methods based on convolutional neural network with region proposals, and the conventional machine learning methods based on topic models, low-rank matrix factorization, or image processing. Deep learning methods for objects discovery are based on sacrificing computational complexity to achieve precision, and the training time can be long without GPU platforms, whereas the conventional methods are usually lack of detection accuracy. To effectively address the problems of the training complexity and the detection speed, we present a new objects discovery approach by proposing a two-stage (training and verification) method. In the training stage, a topic model with words co-occurrence prior is proposed on the basis of Latent Dirichlet Allocation (LDA) model, in which the co-occurrence information among the features is sufficiently ultilized. In the verification stage, we propose an Anchor-box polishing algorithm that fine-tunes the detection results corresponding to the pre-trained topic model from some conventional algorithms with fast detection time. Experiments on various datasets demonstrate that the proposed approach can improve the detection performance in terms of efficiency and computing costs. It is also robust to objects different in colors, lightings, scales, etc. Interestingly, the proposed method can be combined with many fast but inaccurate detection algorithms, in which it enhances the model’s flexibility.
- 23 January 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 30 (3) , 632-645
Objects Discovery Based on Co-Occurrence Word Model With Anchor-Box Polishing
State-of-art objects discovery approaches can be categorized into two categories: The deep learning methods based on convolutional neural network with region proposals, and the conventional machine learning methods based on topic models, low-rank matrix factorization, or image processing. Deep learning methods for objects discovery are based on sacrificing computational complexity to achieve precision, and the training time can be long without GPU platforms, whereas the conventional methods are usually lack of detection accuracy. To effectively address the problems of the training complexity and the detection speed, we present a new objects discovery approach by proposing a two-stage (training and verification) method. In the training stage, a topic model with words co-occurrence prior is proposed on the basis of Latent Dirichlet Allocation (LDA) model, in which the co-occurrence information among the features is sufficiently ultilized. In the verification stage, we propose an Anchor-box polishing algorithm that fine-tunes the detection results corresponding to the pre-trained topic model from some conventional algorithms with fast detection time. Experiments on various datasets demonstrate that the proposed approach can improve the detection performance in terms of efficiency and computing costs. It is also robust to objects different in colors, lightings, scales, etc. Interestingly, the proposed method can be combined with many fast but inaccurate detection algorithms, in which it enhances the model’s flexibility.
- 23 January 2018
- Published by Springer Nature
- p. 164-172
Intelligent Perceptive QoS Based Centralized Admission Control for Route Computing
- 23 January 2018
- Published by Springer Nature
- p. 164-172
Intelligent Perceptive QoS Based Centralized Admission Control for Route Computing