Qing Ding
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Qing Ding has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Xinming Zhang
University of Science and Technology of China, Hefei, China
6 shared publications - Wenyu Zhang
University of Science and Technology of China, Hefei, China
4 shared publications - Dan Keun Sung
School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Korea
2 shared publications - Xin Deng
Spatial Intelligence Group
2 shared publications Baojun Jia
1 shared publication- Baojun Jia
University of Science and Technology of China, Hefei, China
1 shared publication
Latest Publications
- Open Access
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 2168-2179
Pixel Adapter: A Graph-Based Post-Processing Approach for Scene Text Image Super-Resolution
Current Scene text image super-resolution approaches primarily focus on extracting robust features, acquiring text information, and complex training strategies to generate super-resolution images. However, the upsampling module, which is crucial in the process of converting low-resolution images to high-resolution ones, has received little attention in existing works. To address this issue, we propose the Pixel Adapter Module (PAM) based on graph attention to address pixel distortion caused by upsampling. The PAM effectively captures local structural information by allowing each pixel to interact with its neighbors and update features. Unlike previous graph attention mechanisms, our approach achieves 2-3 orders of magnitude improvement in efficiency and memory utilization by eliminating the dependency on sparse adjacency matrices and introducing a sliding window approach for efficient parallel computation. Additionally, we introduce the MLP-based Sequential Residual Block (MSRB) for robust feature extraction from text images, and a Local Contour Awareness loss (ℒlca) to enhance the model's perception of details. Comprehensive experiments on TextZoom demonstrate that our proposed method generates high-quality super-resolution images, surpassing existing methods in recognition accuracy. For single-stage and multi-stage strategies, we achieved improvements of 0.7% and 2.6%, respectively, increasing the performance from 52.6% and 53.7% to 53.3% and 56.3%. The code is available at https://github.com/wenyu1009/RTSRN.
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 2168-2179
Open AccessPixel Adapter: A Graph-Based Post-Processing Approach for Scene Text Image Super-Resolution
Current Scene text image super-resolution approaches primarily focus on extracting robust features, acquiring text information, and complex training strategies to generate super-resolution images. However, the upsampling module, which is crucial in the process of converting low-resolution images to high-resolution ones, has received little attention in existing works. To address this issue, we propose the Pixel Adapter Module (PAM) based on graph attention to address pixel distortion caused by upsampling. The PAM effectively captures local structural information by allowing each pixel to interact with its neighbors and update features. Unlike previous graph attention mechanisms, our approach achieves 2-3 orders of magnitude improvement in efficiency and memory utilization by eliminating the dependency on sparse adjacency matrices and introducing a sliding window approach for efficient parallel computation. Additionally, we introduce the MLP-based Sequential Residual Block (MSRB) for robust feature extraction from text images, and a Local Contour Awareness loss (ℒlca) to enhance the model's perception of details. Comprehensive experiments on TextZoom demonstrate that our proposed method generates high-quality super-resolution images, surpassing existing methods in recognition accuracy. For single-stage and multi-stage strategies, we achieved improvements of 0.7% and 2.6%, respectively, increasing the performance from 52.6% and 53.7% to 53.3% and 56.3%. The code is available at https://github.com/wenyu1009/RTSRN.
- Open Access
Pixel Adapter: A Graph-Based Post-Processing Approach for Scene Text Image Super-Resolution
Current Scene text image super-resolution approaches primarily focus on extracting robust features, acquiring text information, and complex training strategies to generate super-resolution images. However, the upsampling module, which is crucial in the process of converting low-resolution images to high-resolution ones, has received little attention in existing works. To address this issue, we propose the Pixel Adapter Module (PAM) based on graph attention to address pixel distortion caused by upsampling. The PAM effectively captures local structural information by allowing each pixel to interact with its neighbors and update features. Unlike previous graph attention mechanisms, our approach achieves 2-3 orders of magnitude improvement in efficiency and memory utilization by eliminating the dependency on sparse adjacency matrices and introducing a sliding window approach for efficient parallel computation. Additionally, we introduce the MLP-based Sequential Residual Block (MSRB) for robust feature extraction from text images, and a Local Contour Awareness loss ($\mathcal{L}_{lca}$) to enhance the model's perception of details. Comprehensive experiments on TextZoom demonstrate that our proposed method generates high-quality super-resolution images, surpassing existing methods in recognition accuracy. For single-stage and multi-stage strategies, we achieved improvements of 0.7\% and 2.6\%, respectively, increasing the performance from 52.6\% and 53.7\% to 53.3\% and 56.3\%. The code is available at https://github.com/wenyu1009/RTSRN.
Open AccessPixel Adapter: A Graph-Based Post-Processing Approach for Scene Text Image Super-Resolution
Current Scene text image super-resolution approaches primarily focus on extracting robust features, acquiring text information, and complex training strategies to generate super-resolution images. However, the upsampling module, which is crucial in the process of converting low-resolution images to high-resolution ones, has received little attention in existing works. To address this issue, we propose the Pixel Adapter Module (PAM) based on graph attention to address pixel distortion caused by upsampling. The PAM effectively captures local structural information by allowing each pixel to interact with its neighbors and update features. Unlike previous graph attention mechanisms, our approach achieves 2-3 orders of magnitude improvement in efficiency and memory utilization by eliminating the dependency on sparse adjacency matrices and introducing a sliding window approach for efficient parallel computation. Additionally, we introduce the MLP-based Sequential Residual Block (MSRB) for robust feature extraction from text images, and a Local Contour Awareness loss ($\mathcal{L}_{lca}$) to enhance the model's perception of details. Comprehensive experiments on TextZoom demonstrate that our proposed method generates high-quality super-resolution images, surpassing existing methods in recognition accuracy. For single-stage and multi-stage strategies, we achieved improvements of 0.7\% and 2.6\%, respectively, increasing the performance from 52.6\% and 53.7\% to 53.3\% and 56.3\%. The code is available at https://github.com/wenyu1009/RTSRN.
- Open Access
Pixel-wise Graph Attention Networks for Person Re-identification
Graph convolutional networks (GCN) is widely used to handle irregular data since it updates node features by using the structure information of graph. With the help of iterated GCN, high-order information can be obtained to further enhance the representation of nodes. However, how to apply GCN to structured data (such as pictures) has not been deeply studied. In this paper, we explore the application of graph attention networks (GAT) in image feature extraction. First of all, we propose a novel graph generation algorithm to convert images into graphs through matrix transformation. It is one magnitude faster than the algorithm based on K Nearest Neighbors (KNN). Then, GAT is used on the generated graph to update the node features. Thus, a more robust representation is obtained. These two steps are combined into a module called pixel-wise graph attention module (PGA). Since the graph obtained by our graph generation algorithm can still be transformed into a picture after processing, PGA can be well combined with CNN. Based on these two modules, we consulted the ResNet and design a pixel-wise graph attention network (PGANet). The PGANet is applied to the task of person re-identification in the datasets Market1501, DukeMTMC-reID and Occluded-DukeMTMC (outperforms state-of-the-art by 0.8\%, 1.1\% and 11\% respectively, in mAP scores). Experiment results show that it achieves the state-of-the-art performance. \href{https://github.com/wenyu1009/PGANet}{The code is available here}.
Open AccessPixel-wise Graph Attention Networks for Person Re-identification
Graph convolutional networks (GCN) is widely used to handle irregular data since it updates node features by using the structure information of graph. With the help of iterated GCN, high-order information can be obtained to further enhance the representation of nodes. However, how to apply GCN to structured data (such as pictures) has not been deeply studied. In this paper, we explore the application of graph attention networks (GAT) in image feature extraction. First of all, we propose a novel graph generation algorithm to convert images into graphs through matrix transformation. It is one magnitude faster than the algorithm based on K Nearest Neighbors (KNN). Then, GAT is used on the generated graph to update the node features. Thus, a more robust representation is obtained. These two steps are combined into a module called pixel-wise graph attention module (PGA). Since the graph obtained by our graph generation algorithm can still be transformed into a picture after processing, PGA can be well combined with CNN. Based on these two modules, we consulted the ResNet and design a pixel-wise graph attention network (PGANet). The PGANet is applied to the task of person re-identification in the datasets Market1501, DukeMTMC-reID and Occluded-DukeMTMC (outperforms state-of-the-art by 0.8\%, 1.1\% and 11\% respectively, in mAP scores). Experiment results show that it achieves the state-of-the-art performance. \href{https://github.com/wenyu1009/PGANet}{The code is available here}.
- Open Access
PointVector: A Vector Representation In Point Cloud Analysis
In point cloud analysis, point-based methods have rapidly developed in recent years. These methods have recently focused on concise MLP structures, such as PointNeXt, which have demonstrated competitiveness with Convolutional and Transformer structures. However, standard MLPs are limited in their ability to extract local features effectively. To address this limitation, we propose a Vector-oriented Point Set Abstraction that can aggregate neighboring features through higher-dimensional vectors. To facilitate network optimization, we construct a transformation from scalar to vector using independent angles based on 3D vector rotations. Finally, we develop a PointVector model that follows the structure of PointNeXt. Our experimental results demonstrate that PointVector achieves state-of-the-art performance $\textbf{72.3\% mIOU}$ on the S3DIS Area 5 and $\textbf{78.4\% mIOU}$ on the S3DIS (6-fold cross-validation) with only $\textbf{58\%}$ model parameters of PointNeXt. We hope our work will help the exploration of concise and effective feature representations. The code will be released soon.Open AccessPointVector: A Vector Representation In Point Cloud Analysis
In point cloud analysis, point-based methods have rapidly developed in recent years. These methods have recently focused on concise MLP structures, such as PointNeXt, which have demonstrated competitiveness with Convolutional and Transformer structures. However, standard MLPs are limited in their ability to extract local features effectively. To address this limitation, we propose a Vector-oriented Point Set Abstraction that can aggregate neighboring features through higher-dimensional vectors. To facilitate network optimization, we construct a transformation from scalar to vector using independent angles based on 3D vector rotations. Finally, we develop a PointVector model that follows the structure of PointNeXt. Our experimental results demonstrate that PointVector achieves state-of-the-art performance $\textbf{72.3\% mIOU}$ on the S3DIS Area 5 and $\textbf{78.4\% mIOU}$ on the S3DIS (6-fold cross-validation) with only $\textbf{58\%}$ model parameters of PointNeXt. We hope our work will help the exploration of concise and effective feature representations. The code will be released soon. - 13 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 22 (10) , 6027-6040
Modeling and Characterization of the Detection and Suppression of Bogus Messages in Vehicular Ad Hoc Networks
It is very important to detect and prevent bogus messages (here called rumors) in vehicular ad hoc networks (VANETs) because such misbehaviors could cause road safety problems and even casualties. In this paper, we first propose an evolutionary public goods game (EPGG) model to detect bogus messages and stimulate nodes to implement data verification. When a node detects a rumor, it immediately broadcasts an anti-rumor. We here present a susceptible, immune, and neutral (SIN) rumor diffusion model to characterize the spread of rumors and anti-rumors. Moreover, we propose a dynamic, hierarchical public goods game (DHPGG) model to analyze the symbiosis and confrontation of rumors and anti-rumors. Simulation results show these models could detect and suppress rumors effectively in VANETs.
- 13 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 22 (10) , 6027-6040
Modeling and Characterization of the Detection and Suppression of Bogus Messages in Vehicular Ad Hoc Networks
It is very important to detect and prevent bogus messages (here called rumors) in vehicular ad hoc networks (VANETs) because such misbehaviors could cause road safety problems and even casualties. In this paper, we first propose an evolutionary public goods game (EPGG) model to detect bogus messages and stimulate nodes to implement data verification. When a node detects a rumor, it immediately broadcasts an anti-rumor. We here present a susceptible, immune, and neutral (SIN) rumor diffusion model to characterize the spread of rumors and anti-rumors. Moreover, we propose a dynamic, hierarchical public goods game (DHPGG) model to analyze the symbiosis and confrontation of rumors and anti-rumors. Simulation results show these models could detect and suppress rumors effectively in VANETs.
- 7 August 2021
- Published by Springer Nature
- p. 349-360
EGIM: Evolution Graph Based Interest Modeling for Click-Through Rate Prediction
- 7 August 2021
- Published by Springer Nature
- p. 349-360
EGIM: Evolution Graph Based Interest Modeling for Click-Through Rate Prediction
- 30 October 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 20 (11) , 3995-4005
A Public Goods Game Theory-Based Approach to Cooperation in VANETs Under a High Vehicle Density Condition
There are high demands for cooperation among vehicle nodes to disseminate data in vehicular ad hoc networks (VANETs). Game theory approaches have been applied to analyzing and regulating the behavior of nodes in complex networks. However, game theory-based cooperation in VANETs still poses a research challenge due to continuous changes in the network topology. In this paper, we focus on the issue of the common behavior of cooperation in group vehicular interactions. We first present a dynamic member public goods game (PGG) model for real VANETs in which games are carried out within each group. Then, a dynamic grouping PGG (DGPGG) model is proposed to model VANETs with high-node density. In addition, a greedy neighbor selection strategy is proposed to replace the typical random strategy. Finally, the individual reputation of a vehicle is integrated into the DGPGG model. The simulation results show that the DGPGG model can greatly increase the proportion of cooperative nodes in high-density VANETs no matter whether the network is static or dynamic. When the network topology changes quickly, the greedy neighbor selection strategy can promote cooperation between nodes more effectively than the random strategy.
- 30 October 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 20 (11) , 3995-4005
A Public Goods Game Theory-Based Approach to Cooperation in VANETs Under a High Vehicle Density Condition
There are high demands for cooperation among vehicle nodes to disseminate data in vehicular ad hoc networks (VANETs). Game theory approaches have been applied to analyzing and regulating the behavior of nodes in complex networks. However, game theory-based cooperation in VANETs still poses a research challenge due to continuous changes in the network topology. In this paper, we focus on the issue of the common behavior of cooperation in group vehicular interactions. We first present a dynamic member public goods game (PGG) model for real VANETs in which games are carried out within each group. Then, a dynamic grouping PGG (DGPGG) model is proposed to model VANETs with high-node density. In addition, a greedy neighbor selection strategy is proposed to replace the typical random strategy. Finally, the individual reputation of a vehicle is integrated into the DGPGG model. The simulation results show that the DGPGG model can greatly increase the proportion of cooperative nodes in high-density VANETs no matter whether the network is static or dynamic. When the network topology changes quickly, the greedy neighbor selection strategy can promote cooperation between nodes more effectively than the random strategy.
- Open Access
- 6 February 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 5, 2262-2271
RECT: A Cloud-Based Learning Tool for Graduate Software Engineering Practice Courses With Remote Tutor Support
Nowadays, remote collaborative learning tools for computer science education mostly emphasize providing learning resources and realizing virtual collaborative learning environment for students. Many people in this field tend to have their mind fixed on the process improvement of such a collaboration as a whole, while few notice that individuals may have different roles and impacts on this type of teamwork. There usually is a “supervisor” on the team, who offers support to all members in the collaborative learning environment. However, such support may not always be as accessible as students demand it to be. Therefore, this paper describes a cloud-based tool to support software engineering practice courses in collaboration with remote tutors. This system utilizes a cloud storage platform to provide sharing of multimedia study materials and a better management of project developing cycles. A remote collaborative component called the Virtual Debug Laboratory is designed to improve and share students' debugging experience in the same team. The most innovative feature of this system is that it amplifies the role of tutoring in remote collaborative learning environments so that tutors can, in real time, assist students in debugging during actual project developing and demonstrate step by step to the students the process of debugging. The results of the analyzed data regarding the use of this system indicate that the system can potentially enhance students' abilities in project developing and debugging in software engineering practice courses. It is our hope that these preliminary data can provide a future reference for the software education community.
- 6 February 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 5, 2262-2271
Open AccessRECT: A Cloud-Based Learning Tool for Graduate Software Engineering Practice Courses With Remote Tutor Support
Nowadays, remote collaborative learning tools for computer science education mostly emphasize providing learning resources and realizing virtual collaborative learning environment for students. Many people in this field tend to have their mind fixed on the process improvement of such a collaboration as a whole, while few notice that individuals may have different roles and impacts on this type of teamwork. There usually is a “supervisor” on the team, who offers support to all members in the collaborative learning environment. However, such support may not always be as accessible as students demand it to be. Therefore, this paper describes a cloud-based tool to support software engineering practice courses in collaboration with remote tutors. This system utilizes a cloud storage platform to provide sharing of multimedia study materials and a better management of project developing cycles. A remote collaborative component called the Virtual Debug Laboratory is designed to improve and share students' debugging experience in the same team. The most innovative feature of this system is that it amplifies the role of tutoring in remote collaborative learning environments so that tutors can, in real time, assist students in debugging during actual project developing and demonstrate step by step to the students the process of debugging. The results of the analyzed data regarding the use of this system indicate that the system can potentially enhance students' abilities in project developing and debugging in software engineering practice courses. It is our hope that these preliminary data can provide a future reference for the software education community.
- 5 November 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 5 (1) , 76-79
Coverage Efficiency-Based Broadcast Protocol for Asynchronous Wireless Sensor Networks
Due to the independent sleep/wake scheduling of nodes in asynchronous wireless sensor networks (WSNs), a sender should send the same packet several times to make sure all the neighbor nodes can receive the packet in a broadcast process. Moreover, the order of the neighbor nodes receiving the packet has effect on the performance of broadcast. In this letter, we focus on the dynamics in the process of broadcast in WSNs and jointly consider the coverage knowledge, link quality, and sleep/wake scheduling information of neighbor nodes. We first choose a receiver with large newly added coverage area to accelerate the broadcast process. Then, we select the sender and its receiver or the coverage order for the nodes not being accommodated in the overlap coverage area to efficiently improve the broadcast performance. Simulation results have shown that our proposed protocol can reduce energy consumption and number of transmissions.
- 5 November 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 5 (1) , 76-79
Coverage Efficiency-Based Broadcast Protocol for Asynchronous Wireless Sensor Networks
Due to the independent sleep/wake scheduling of nodes in asynchronous wireless sensor networks (WSNs), a sender should send the same packet several times to make sure all the neighbor nodes can receive the packet in a broadcast process. Moreover, the order of the neighbor nodes receiving the packet has effect on the performance of broadcast. In this letter, we focus on the dynamics in the process of broadcast in WSNs and jointly consider the coverage knowledge, link quality, and sleep/wake scheduling information of neighbor nodes. We first choose a receiver with large newly added coverage area to accelerate the broadcast process. Then, we select the sender and its receiver or the coverage order for the nodes not being accommodated in the overlap coverage area to efficiently improve the broadcast performance. Simulation results have shown that our proposed protocol can reduce energy consumption and number of transmissions.