Xu Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xu Wang has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Yujie Li
School of Artificial Intelligence, Guilin University of Electronic Technology, Guilin, China
3 shared publications - Haoyu Wang
School of Artificial Intelligence, Guilin University of Electronic Technology, Jinji Road, Guilin 541004, China
2 shared publications - Longzhao Huang
School of Artificial Intelligence, Guilin University of Electronic Technology, Jinji Road, Guilin 541004, China
2 shared publications - Ahmad Chaddad
Guilin University of Electronic Technology
1 shared publication - Ahmed Bouridane
Department of Computer Engineering, University of Sharjah, UAE
1 shared publication - Qizong Lu
School of Computer and Electronic Information, Guangxi University, Nanning 530004, China
1 shared publication
Latest Publications
- 11 June 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 331
SCPid: Point cloud semantic scene completion via spatial-chunked perception and image prior distillation
- 11 June 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 331
SCPid: Point cloud semantic scene completion via spatial-chunked perception and image prior distillation
- Open Access
A Video Summarization Model Based on Deep Reinforcement Learning with Long-Term Dependency
Deep summarization models have succeeded in the video summarization field based on the development of gated recursive unit (GRU) and long and short-term memory (LSTM) technology. However, for some long videos, GRU and LSTM cannot effectively capture long-term dependencies. This paper proposes a deep summarization network with auxiliary summarization losses to address this problem. We introduce an unsupervised auxiliary summarization loss module with LSTM and a swish activation function to capture the long-term dependencies for video summarization, which can be easily integrated with various networks. The proposed model is an unsupervised framework for deep reinforcement learning that does not depend on any labels or user interactions. Additionally, we implement a reward function () that jointly considers the consistency, diversity, and representativeness of generated summaries. Furthermore, the proposed model is lightweight and can be successfully deployed on mobile devices and enhance the experience of mobile users and reduce pressure on server operations. We conducted experiments on two benchmark datasets and the results demonstrate that our proposed unsupervised approach can obtain better summaries than existing video summarization methods. Furthermore, the proposed algorithm can generate higher F scores with a nearly 6.3% increase on the SumMe dataset and a 2.2% increase on the TVSum dataset compared to the DR-DSN model.Open AccessA Video Summarization Model Based on Deep Reinforcement Learning with Long-Term Dependency
Deep summarization models have succeeded in the video summarization field based on the development of gated recursive unit (GRU) and long and short-term memory (LSTM) technology. However, for some long videos, GRU and LSTM cannot effectively capture long-term dependencies. This paper proposes a deep summarization network with auxiliary summarization losses to address this problem. We introduce an unsupervised auxiliary summarization loss module with LSTM and a swish activation function to capture the long-term dependencies for video summarization, which can be easily integrated with various networks. The proposed model is an unsupervised framework for deep reinforcement learning that does not depend on any labels or user interactions. Additionally, we implement a reward function () that jointly considers the consistency, diversity, and representativeness of generated summaries. Furthermore, the proposed model is lightweight and can be successfully deployed on mobile devices and enhance the experience of mobile users and reduce pressure on server operations. We conducted experiments on two benchmark datasets and the results demonstrate that our proposed unsupervised approach can obtain better summaries than existing video summarization methods. Furthermore, the proposed algorithm can generate higher F scores with a nearly 6.3% increase on the SumMe dataset and a 2.2% increase on the TVSum dataset compared to the DR-DSN model. - Open Access
Gaze Estimation Approach Using Deep Differential Residual Network
Gaze estimation, which is a method to determine where a person is looking at given the person’s full face, is a valuable clue for understanding human intention. Similarly to other domains of computer vision, deep learning (DL) methods have gained recognition in the gaze estimation domain. However, there are still gaze calibration problems in the gaze estimation domain, thus preventing existing methods from further improving the performances. An effective solution is to directly predict the difference information of two human eyes, such as the differential network (Diff-Nn). However, this solution results in a loss of accuracy when using only one inference image. We propose a differential residual model (DRNet) combined with a new loss function to make use of the difference information of two eye images. We treat the difference information as auxiliary information. We assess the proposed model (DRNet) mainly using two public datasets (1) MpiiGaze and (2) Eyediap. Considering only the eye features, DRNet outperforms the state-of-the-art gaze estimation methods with angular-error of 4.57 and 6.14 using MpiiGaze and Eyediap datasets, respectively. Furthermore, the experimental results also demonstrate that DRNet is extremely robust to noise images.
Open AccessGaze Estimation Approach Using Deep Differential Residual Network
Gaze estimation, which is a method to determine where a person is looking at given the person’s full face, is a valuable clue for understanding human intention. Similarly to other domains of computer vision, deep learning (DL) methods have gained recognition in the gaze estimation domain. However, there are still gaze calibration problems in the gaze estimation domain, thus preventing existing methods from further improving the performances. An effective solution is to directly predict the difference information of two human eyes, such as the differential network (Diff-Nn). However, this solution results in a loss of accuracy when using only one inference image. We propose a differential residual model (DRNet) combined with a new loss function to make use of the difference information of two eye images. We treat the difference information as auxiliary information. We assess the proposed model (DRNet) mainly using two public datasets (1) MpiiGaze and (2) Eyediap. Considering only the eye features, DRNet outperforms the state-of-the-art gaze estimation methods with angular-error of 4.57 and 6.14 using MpiiGaze and Eyediap datasets, respectively. Furthermore, the experimental results also demonstrate that DRNet is extremely robust to noise images.
- Open Access
- 23 June 2022
- Published by EDP Sciences in ITM Web of Conferences
- Vol. 47, 02015
Research on supply chain planning based on genetic algorithm and long short-term memory
With the integration of intelligent algorithm into the supply chain process, the fficiency of supply chain planning has been further improved through automatic prediction and decision-making. Although intelligent algorithms are developing, their challenges including real-time nature of supply chain planning and the complexity of scenarios hinder their true potential. In this study, we proposed an improved genetic algorithm (GA)-long short-term memory (LSTM) neural network prediction algorithm to solve various optimization planning problems for the supply chain from suppliers to production enterprises. Specifically, to determine stable suppliers, we first constructed the technique for order preference by similarity to ideal solution (TOPSIS) model to quantitatively evaluate each supplier, and the rationality of the index weight of the TOPSIS algorithm can be enhanced by the entropy method. Finally, the GA and LSTM were used to solve the decision-making and planning problem in raw material supply chain. Our results indicate that the algorithm we proposed can not only efficiently solve the decision planning problem in the raw material supply chain, but it also reasonably analyzes the suppliers quantitatively.
- 23 June 2022
- Published by EDP Sciences in ITM Web of Conferences
- Vol. 47, 02015
Open AccessResearch on supply chain planning based on genetic algorithm and long short-term memory
With the integration of intelligent algorithm into the supply chain process, the fficiency of supply chain planning has been further improved through automatic prediction and decision-making. Although intelligent algorithms are developing, their challenges including real-time nature of supply chain planning and the complexity of scenarios hinder their true potential. In this study, we proposed an improved genetic algorithm (GA)-long short-term memory (LSTM) neural network prediction algorithm to solve various optimization planning problems for the supply chain from suppliers to production enterprises. Specifically, to determine stable suppliers, we first constructed the technique for order preference by similarity to ideal solution (TOPSIS) model to quantitatively evaluate each supplier, and the rationality of the index weight of the TOPSIS algorithm can be enhanced by the entropy method. Finally, the GA and LSTM were used to solve the decision-making and planning problem in raw material supply chain. Our results indicate that the algorithm we proposed can not only efficiently solve the decision planning problem in the raw material supply chain, but it also reasonably analyzes the suppliers quantitatively.