Wenting Cui
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
Wenting Cui has a total of 37 co-authors. Here are the top co-authors by number of shared publications:
- Shaoyi Du
Xi’an Jiaotong University
6 shared publications - Runzhao Yao
College of Artificial Intelligence, Institute of Robotics and Automatic Information System, Nankai University, Tianjin, China
3 shared publications - Aixue Ye
Huawei Noahs Ark Lab, Huawei Technologies Company Ltd., Beijing, China
2 shared publications - Canhui Tang
National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xian Jiaotong University, Shaanxi, Xi’an China
2 shared publications - Feng Wen
Huawei Noahs Ark Lab, Huawei Technologies Company Ltd., Beijing, China
2 shared publications - Zhiqiang Tian
School of Software Engineering, Xian Jiaotong University, Xian, China
2 shared publications
Latest Publications
- 21 November 2024
- Published by Springer Nature
- p. 287-303
PARE-Net: Position-Aware Rotation-Equivariant Networks for Robust Point Cloud Registration
- 21 November 2024
- Published by Springer Nature
- p. 287-303
PARE-Net: Position-Aware Rotation-Equivariant Networks for Robust Point Cloud Registration
- 30 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 27 (15209210) , 900-913
RDD: Learning Reinforced 3D Detectors and Descriptors Based on Policy Gradient
Keypoint detection and descriptor matching are two vital steps in the 3D feature extraction framework, but they are difficult to learn in an end-to-end fashion due to their inherent discreteness. To tackle the non-differentiable operations, we formulate feature extraction as a decision-making problem: the network is treated as a policy pool that can make probabilistic estimations for keypoint selection and feature matching, supervised by maximizing a reward expectation of actions. In this way, we propose a novel end-to-end training paradigm of 3D feature extraction based on the stochastic policy gradient method, named Reinforced Detectors and Descriptors (RDD). Firstly, we propose a local-to-global probabilistic keypoint selection module that formulates the sampling probabilities of keypoints in a local-and-global mechanism to yield sparse and accurate keypoints. Secondly, we regard feature matching as an optimal transport problem and an efficient Sinkhorn method is leveraged to solve the optimal matching probabilities. In particular, we carefully design a reward function and derive gradients of probabilistic actions, thus overcoming the discreteness and providing reinforced supervision signals. Since our reward function is calculated from sampled keypoints rather than from randomly sampled points as in existing methods, the gap between training and inference is bridged. Experimental results demonstrate that our approach exceeds the quality of state-of-the-art methods and shows strong generalization ability. Remarkably, our approach can achieve significantly higher Registration Recall than other advanced methods when aligning scenes with a small number of keypoints, due to our highly accurate and repeatable detector.
- 30 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 27 (15209210) , 900-913
RDD: Learning Reinforced 3D Detectors and Descriptors Based on Policy Gradient
Keypoint detection and descriptor matching are two vital steps in the 3D feature extraction framework, but they are difficult to learn in an end-to-end fashion due to their inherent discreteness. To tackle the non-differentiable operations, we formulate feature extraction as a decision-making problem: the network is treated as a policy pool that can make probabilistic estimations for keypoint selection and feature matching, supervised by maximizing a reward expectation of actions. In this way, we propose a novel end-to-end training paradigm of 3D feature extraction based on the stochastic policy gradient method, named Reinforced Detectors and Descriptors (RDD). Firstly, we propose a local-to-global probabilistic keypoint selection module that formulates the sampling probabilities of keypoints in a local-and-global mechanism to yield sparse and accurate keypoints. Secondly, we regard feature matching as an optimal transport problem and an efficient Sinkhorn method is leveraged to solve the optimal matching probabilities. In particular, we carefully design a reward function and derive gradients of probabilistic actions, thus overcoming the discreteness and providing reinforced supervision signals. Since our reward function is calculated from sampled keypoints rather than from randomly sampled points as in existing methods, the gap between training and inference is bridged. Experimental results demonstrate that our approach exceeds the quality of state-of-the-art methods and shows strong generalization ability. Remarkably, our approach can achieve significantly higher Registration Recall than other advanced methods when aligning scenes with a small number of keypoints, due to our highly accurate and repeatable detector.
- 11 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (12) , 14760-14776
Hunter: Exploring High-Order Consistency for Point Cloud Registration With Severe Outliers
After decades of investigation, point cloud registration is still a challenging task in practice, especially when the correspondences are contaminated by a large number of outliers. It may result in a rapidly decreasing probability of generating a hypothesis close to the true transformation, leading to the failure of point cloud registration. To tackle this problem, we propose a transformation estimation method, named Hunter, for robust point cloud registration with severe outliers. The core of Hunter is to design a global-to-local exploration scheme to robustly find the correct correspondences. The global exploration aims to exploit guided sampling to generate promising initial alignments. To this end, a hypergraph-based consistency reasoning module is introduced to learn the high-order consistency among correct correspondences, which is able to yield a more distinct inlier cluster that facilitates the generation of all-inlier hypotheses. Moreover, we propose a preference-based local exploration module that exploits the preference information of top-$k$ promising hypotheses to find a better transformation. This module can efficiently obtain multiple reliable transformation hypotheses by using a multi-initialization searching strategy. Finally, we present a distance-angle based hypothesis selection criterion to choose the most reliable transformation, which can avoid selecting symmetrically aligned false transformations. Experimental results on simulated, indoor, and outdoor datasets, demonstrate that Hunter can achieve significant superiority over the state-of-the-art methods, including both learning-based and traditional methods (as shown in Fig. 1). Moreover, experimental results also indicate that Hunter can achieve more stable performance compared with all other methods with severe outliers.- 11 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (12) , 14760-14776
Hunter: Exploring High-Order Consistency for Point Cloud Registration With Severe Outliers
After decades of investigation, point cloud registration is still a challenging task in practice, especially when the correspondences are contaminated by a large number of outliers. It may result in a rapidly decreasing probability of generating a hypothesis close to the true transformation, leading to the failure of point cloud registration. To tackle this problem, we propose a transformation estimation method, named Hunter, for robust point cloud registration with severe outliers. The core of Hunter is to design a global-to-local exploration scheme to robustly find the correct correspondences. The global exploration aims to exploit guided sampling to generate promising initial alignments. To this end, a hypergraph-based consistency reasoning module is introduced to learn the high-order consistency among correct correspondences, which is able to yield a more distinct inlier cluster that facilitates the generation of all-inlier hypotheses. Moreover, we propose a preference-based local exploration module that exploits the preference information of top-$k$ promising hypotheses to find a better transformation. This module can efficiently obtain multiple reliable transformation hypotheses by using a multi-initialization searching strategy. Finally, we present a distance-angle based hypothesis selection criterion to choose the most reliable transformation, which can avoid selecting symmetrically aligned false transformations. Experimental results on simulated, indoor, and outdoor datasets, demonstrate that Hunter can achieve significant superiority over the state-of-the-art methods, including both learning-based and traditional methods (as shown in Fig. 1). Moreover, experimental results also indicate that Hunter can achieve more stable performance compared with all other methods with severe outliers.- Open Access
- 16 October 2021
- Published by Association for Computing Machinery (ACM)
- p. 92-100
Co-Drink: Exploring Social Support Water Bottles to Increase the Hydration Status of Individuals with Intimate Relationship
Due to busy work routines in the modern society, it is common that people neglect to drink water. Social influences, such as interactions between friends and lovers, appears to be crucial to foster healthy behaviors. In this study, we investigate leveraging social support mechanisms in the design of persuasive technology to increase the frequency of daily fluid intakes. We firstly carried out an auto-ethnography as well as a probe-based co-design study to explore dedicated social mechanisms for promoting healthy hydration habits. This led to the conceptualization of Co-Drink that focuses on technology-enabled social interactions between individuals with intimate relationships to stimulate their water intake behaviors. Co-Drink was implemented as a pair of smart water bottles with ambient light. It also associated with an app to facilitate a coaching mode and a co-learning mode for persuading health behavior change. The prototypes of Co-Drink were evaluated in a Wizard-of-Oz study with three dyads of college students. Results showed its benefits for hydration health promotion and applicability for daily life use, due to the embedded social mechanisms and the ambient displays integrated with the water bottle. Based on these qualitative findings, we discuss implications for the future development of persuasive technologies for improving water intake behaviors.
- 16 October 2021
- Published by Association for Computing Machinery (ACM)
- p. 92-100
Open AccessCo-Drink: Exploring Social Support Water Bottles to Increase the Hydration Status of Individuals with Intimate Relationship
Due to busy work routines in the modern society, it is common that people neglect to drink water. Social influences, such as interactions between friends and lovers, appears to be crucial to foster healthy behaviors. In this study, we investigate leveraging social support mechanisms in the design of persuasive technology to increase the frequency of daily fluid intakes. We firstly carried out an auto-ethnography as well as a probe-based co-design study to explore dedicated social mechanisms for promoting healthy hydration habits. This led to the conceptualization of Co-Drink that focuses on technology-enabled social interactions between individuals with intimate relationships to stimulate their water intake behaviors. Co-Drink was implemented as a pair of smart water bottles with ambient light. It also associated with an app to facilitate a coaching mode and a co-learning mode for persuading health behavior change. The prototypes of Co-Drink were evaluated in a Wizard-of-Oz study with three dyads of college students. Results showed its benefits for hydration health promotion and applicability for daily life use, due to the embedded social mechanisms and the ambient displays integrated with the water bottle. Based on these qualitative findings, we discuss implications for the future development of persuasive technologies for improving water intake behaviors.
- 1 October 2020
- Published by Elsevier in Pattern Recognition Letters
- Vol. 138, 298-304
Robust and precise isotropic scaling registration algorithm using bi-directional distance and correntropy
- 1 October 2020
- Published by Elsevier in Pattern Recognition Letters
- Vol. 138, 298-304
Robust and precise isotropic scaling registration algorithm using bi-directional distance and correntropy
- 8 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 50 (7) , 2891-2904
Predicting COVID-19 in China Using Hybrid AI Model
The coronavirus disease 2019 (COVID-19) breaking out in late December 2019 is gradually being controlled in China, but it is still spreading rapidly in many other countries and regions worldwide. It is urgent to conduct prediction research on the development and spread of the epidemic. In this article, a hybrid artificial-intelligence (AI) model is proposed for COVID-19 prediction. First, as traditional epidemic models treat all individuals with coronavirus as having the same infection rate, an improved susceptible-infected (ISI) model is proposed to estimate the variety of the infection rates for analyzing the transmission laws and development trend. Second, considering the effects of prevention and control measures and the increase of the public's prevention awareness, the natural language processing (NLP) module and the long short-term memory (LSTM) network are embedded into the ISI model to build the hybrid AI model for COVID-19 prediction. The experimental results on the epidemic data of several typical provinces and cities in China show that individuals with coronavirus have a higher infection rate within the third to eighth days after they were infected, which is more in line with the actual transmission laws of the epidemic. Moreover, compared with the traditional epidemic models, the proposed hybrid AI model can significantly reduce the errors of the prediction results and obtain the mean absolute percentage errors (MAPEs) with 0.52%, 0.38%, 0.05%, and 0.86% for the next six days in Wuhan, Beijing, Shanghai, and countrywide, respectively.
- 8 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 50 (7) , 2891-2904
Predicting COVID-19 in China Using Hybrid AI Model
The coronavirus disease 2019 (COVID-19) breaking out in late December 2019 is gradually being controlled in China, but it is still spreading rapidly in many other countries and regions worldwide. It is urgent to conduct prediction research on the development and spread of the epidemic. In this article, a hybrid artificial-intelligence (AI) model is proposed for COVID-19 prediction. First, as traditional epidemic models treat all individuals with coronavirus as having the same infection rate, an improved susceptible-infected (ISI) model is proposed to estimate the variety of the infection rates for analyzing the transmission laws and development trend. Second, considering the effects of prevention and control measures and the increase of the public's prevention awareness, the natural language processing (NLP) module and the long short-term memory (LSTM) network are embedded into the ISI model to build the hybrid AI model for COVID-19 prediction. The experimental results on the epidemic data of several typical provinces and cities in China show that individuals with coronavirus have a higher infection rate within the third to eighth days after they were infected, which is more in line with the actual transmission laws of the epidemic. Moreover, compared with the traditional epidemic models, the proposed hybrid AI model can significantly reduce the errors of the prediction results and obtain the mean absolute percentage errors (MAPEs) with 0.52%, 0.38%, 0.05%, and 0.86% for the next six days in Wuhan, Beijing, Shanghai, and countrywide, respectively.
- Open Access
- 24 January 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 22225-22234
Robust Rigid Registration Algorithm Based on Correntropy and Bi-Directional Distance
- 24 January 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 22225-22234
Open AccessRobust Rigid Registration Algorithm Based on Correntropy and Bi-Directional Distance