Ting Wang
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
Research Subjects
Ting Wang has a total of 78 co-authors. Here are the top co-authors by number of shared publications:
- Aiguo Song
Southeast University
3 shared publications - Zhenxing Sun
College of Electrical Engineering and Control Science, Nanjing Tech University, Nanjing 211816, China
3 shared publications Chiyuan Ma
Department of Neurosurgery Jinling Hospital Affiliated Hospital of Medical School Nanjing University Nanjing Jiangsu China
2 shared publications- Guanghang Zhou
School Nanjing University of Technology China
2 shared publications - Guoping Yang
Nanjing Customs District P. R. China 360 Longpanzhong Road Qinhuai District China
2 shared publications - Jian Gao
Northwestern Polytechnical University
2 shared publications
Latest Publications
- 28 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (1) , 557-569
Facial Expression Recognition With Enhanced Relation-Aware Attention and Cross-Feature Fusion Transformer
Face expression recognition(FER) is an important research branch in the field of the computer vision neighborhood. Three prevalent problems in FER tasks that severely impact recognition rates are inter-class similarity, intra-class differences, and facial occlusion issues. Although there have been studies that address some of these issues, none of them can adequately address all three issues in a unified framework. In this paper, we propose a novel dual-branch structure of enhanced relation-aware attention and cross-feature fusion transformer network to comprehensively solve all three issues. Specifically, we design the Enhanced Relation-Aware Attention module to maximize the exploration of more local expression features. At the same time, the Transformer Perceptual Encoder module is adopted to establishing the contextual relationship between individual patches under global information. This greatly alleviates the inter-class similarity and the facial occlusion and facial pose transformation problems. On the basis of a dual branch structure, we extract facial image features using facial landmark features to guide them and design Cross-Feature Fusion Transformer module to deeply cross-fuse two different semantic features. Experiments are performed and results show that our method can greatly alleviated intra-class differences with comparison of several traditional methods on four commonly used datasets.
- 28 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (1) , 557-569
Facial Expression Recognition With Enhanced Relation-Aware Attention and Cross-Feature Fusion Transformer
Face expression recognition(FER) is an important research branch in the field of the computer vision neighborhood. Three prevalent problems in FER tasks that severely impact recognition rates are inter-class similarity, intra-class differences, and facial occlusion issues. Although there have been studies that address some of these issues, none of them can adequately address all three issues in a unified framework. In this paper, we propose a novel dual-branch structure of enhanced relation-aware attention and cross-feature fusion transformer network to comprehensively solve all three issues. Specifically, we design the Enhanced Relation-Aware Attention module to maximize the exploration of more local expression features. At the same time, the Transformer Perceptual Encoder module is adopted to establishing the contextual relationship between individual patches under global information. This greatly alleviates the inter-class similarity and the facial occlusion and facial pose transformation problems. On the basis of a dual branch structure, we extract facial image features using facial landmark features to guide them and design Cross-Feature Fusion Transformer module to deeply cross-fuse two different semantic features. Experiments are performed and results show that our method can greatly alleviated intra-class differences with comparison of several traditional methods on four commonly used datasets.
- Open Access
- 8 January 2025
- Published by Madison Academic Press in Advances in Engineering Technology Research
- Vol. 13 (1) , 10
Gait recognition method based on dual-branch feature fusion of Swin transformer-CNN
In the daily supervision of customs and air ports, it is necessary to identify the pathological gait of key passengers and suspected smuggling passengers. In this paper, a two-branch gait recognition framework combining global and local feature extraction is introduced. The framework includes a global extraction branch, which uses Swin transformer for feature extraction. A local extraction branch that uses 3DCNN and the CBAM module to enhance local information extraction. The experimental results show that our approach significantly improves the performance of walk recognition and achieves higher accuracy on two data sets that are widely used in most cases.
- 8 January 2025
- Published by Madison Academic Press in Advances in Engineering Technology Research
- Vol. 13 (1) , 10
Open AccessGait recognition method based on dual-branch feature fusion of Swin transformer-CNN
In the daily supervision of customs and air ports, it is necessary to identify the pathological gait of key passengers and suspected smuggling passengers. In this paper, a two-branch gait recognition framework combining global and local feature extraction is introduced. The framework includes a global extraction branch, which uses Swin transformer for feature extraction. A local extraction branch that uses 3DCNN and the CBAM module to enhance local information extraction. The experimental results show that our approach significantly improves the performance of walk recognition and achieves higher accuracy on two data sets that are widely used in most cases.
- Open Access
- 1 January 2025
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 19 (1)
Augmented Multiple Perturbation Dual Mean Teacher Model for Semi‐Supervised Intracranial Haemorrhage Segmentation
Generally, there are two problems restrict the intracranial haemorrhage (ICH) segmentation task: scarcity of labelled data, and poor accuracy of ICH segmentation. To address these two issues, we propose a semi‐supervised ICH segmentation model and a dedicated ICH segmentation backbone network. Our approach aims at leveraging semi‐supervised modelling so as to alleviate the challenge of limited labelled data availability, while the dedicated ICH segmentation backbone network further enhances the segmentation precision. An augmented multiple perturbation dual mean teacher model is designed. Based on it, the prediction accuracy may be improved by a more stringent confidence‐weighted cross‐entropy (CW‐CE) loss, and the feature perturbation may be increased using adversarial feature perturbation for the purpose of improving the generalization ability and efficiency of consistent learning. In the ICH segmentation backbone network, we promote the segmentation accuracy by extracting both local and global features of ICH and fusing them in depth. We also fuse the features with rich details from the upper encoder during the up‐sampling process to reduce the loss of feature information. Experiments on our private dataset ICHDS, and the public dataset IN22SD demonstrate that our model outperforms current state‐of‐the‐art ICH segmentation models, achieving a maximum improvement of over 10% in Dice and exhibiting the best overall performance.
- 1 January 2025
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 19 (1)
Open AccessAugmented Multiple Perturbation Dual Mean Teacher Model for Semi‐Supervised Intracranial Haemorrhage Segmentation
Generally, there are two problems restrict the intracranial haemorrhage (ICH) segmentation task: scarcity of labelled data, and poor accuracy of ICH segmentation. To address these two issues, we propose a semi‐supervised ICH segmentation model and a dedicated ICH segmentation backbone network. Our approach aims at leveraging semi‐supervised modelling so as to alleviate the challenge of limited labelled data availability, while the dedicated ICH segmentation backbone network further enhances the segmentation precision. An augmented multiple perturbation dual mean teacher model is designed. Based on it, the prediction accuracy may be improved by a more stringent confidence‐weighted cross‐entropy (CW‐CE) loss, and the feature perturbation may be increased using adversarial feature perturbation for the purpose of improving the generalization ability and efficiency of consistent learning. In the ICH segmentation backbone network, we promote the segmentation accuracy by extracting both local and global features of ICH and fusing them in depth. We also fuse the features with rich details from the upper encoder during the up‐sampling process to reduce the loss of feature information. Experiments on our private dataset ICHDS, and the public dataset IN22SD demonstrate that our model outperforms current state‐of‐the‐art ICH segmentation models, achieving a maximum improvement of over 10% in Dice and exhibiting the best overall performance.
- 3 December 2024
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 19 (1) , 1-9
Gait recognition with global–local feature fusion based on swin transformer-3DCNN
- 3 December 2024
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 19 (1) , 1-9
Gait recognition with global–local feature fusion based on swin transformer-3DCNN
- 20 November 2024
- Published by Springer Nature
- p. 3-11
Computer Vision Based Quality Control for Molding Injection Machines
- 20 November 2024
- Published by Springer Nature
- p. 3-11
Computer Vision Based Quality Control for Molding Injection Machines
- Open Access
- 13 February 2024
- Published by Springer Nature in Research Square
Facial Expression Recognition with Enhanced Relation-Aware Attention and Cross-Feature Fusion transformer
Face expression recognition(FER) is an important research branch in the field of the computer vision neighborhood. Three prevalent problems in FER tasks that severely impact recognition rates are inter-class similarity, intra-class differences, and facial occlusion issues. Although there have been studies that address some of these issues, none of them can adequately address all three issues in a unified framework. In this paper, we propose a novel dual-branch structure of enhanced relation-aware attention and cross-feature fusion transformer network to comprehensively solve all three issues. Specifically, we design the Enhanced Relation-Aware Attention module to maximize the exploration of more local expression features. At the same time, the Transformer Perceptual Encoder module is adopted to establishing the contextual relationship between individual patches under global information. This greatly alleviates the inter-class similarity problem and the facial occlusion and facial pose transformation problems. On the basis of a dual branch structure, we extract facial image features using facial landmarks features to guide them and design Cross-Feature Fusion Transformer module to deeply cross-fuse two different semantic features. Experiments are performed and results show that our method can greatly alleviated intra-class difference problem with comparison of several traditional methods on three commonly used datasets.
- 13 February 2024
- Published by Springer Nature in Research Square
Open AccessFacial Expression Recognition with Enhanced Relation-Aware Attention and Cross-Feature Fusion transformer
Face expression recognition(FER) is an important research branch in the field of the computer vision neighborhood. Three prevalent problems in FER tasks that severely impact recognition rates are inter-class similarity, intra-class differences, and facial occlusion issues. Although there have been studies that address some of these issues, none of them can adequately address all three issues in a unified framework. In this paper, we propose a novel dual-branch structure of enhanced relation-aware attention and cross-feature fusion transformer network to comprehensively solve all three issues. Specifically, we design the Enhanced Relation-Aware Attention module to maximize the exploration of more local expression features. At the same time, the Transformer Perceptual Encoder module is adopted to establishing the contextual relationship between individual patches under global information. This greatly alleviates the inter-class similarity problem and the facial occlusion and facial pose transformation problems. On the basis of a dual branch structure, we extract facial image features using facial landmarks features to guide them and design Cross-Feature Fusion Transformer module to deeply cross-fuse two different semantic features. Experiments are performed and results show that our method can greatly alleviated intra-class difference problem with comparison of several traditional methods on three commonly used datasets.
- 26 September 2023
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 68 (19) , 195019
DE-UFormer: U-shaped dual encoder architectures for brain tumor segmentation
Objective . In brain tumor segmentation tasks, the convolutional neural network (CNN) or transformer is usually acted as the encoder since the encoder is necessary to be used. On one hand, the convolution operation of CNN has advantages of extracting local information although its performance of obtaining global expressions is bad. On the other hand, the attention mechanism of the transformer is good at establishing remote dependencies while it is lacking in the ability to extract high-precision local information. Either high precision local information or global contextual information is crucial in brain tumor segmentation tasks. The aim of this paper is to propose a brain tumor segmentation model that can simultaneously extract and fuse high-precision local and global contextual information. Approach . We propose a network model DE-Uformer with dual encoders to obtain local features and global representations using both CNN encoder and Transformer encoder. On the basis of this, we further propose the nested encoder-aware feature fusion (NEaFF) module for effective deep fusion of the information under each dimension. It may establishe remote dependencies of features under a single encoder via the spatial attention Transformer. Meanwhile ,it also investigates how features extracted from two encoders are related with the cross-encoder attention transformer. Main results . The proposed algorithm segmentation have been performed on BraTS2020 dataset and private meningioma dataset. Results show that it is significantly better than current state-of-the-art brain tumor segmentation methods. Significance . The method proposed in this paper greatly improves the accuracy of brain tumor segmentation. This advancement helps healthcare professionals perform a more comprehensive analysis and assessment of brain tumors, thereby improving diagnostic accuracy and reliability. This fully automated brain model segmentation model with high accuracy is of great significance for critical decisions made by physicians in selecting treatment strategies and preoperative planning.
- 26 September 2023
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 68 (19) , 195019
DE-UFormer: U-shaped dual encoder architectures for brain tumor segmentation
Objective . In brain tumor segmentation tasks, the convolutional neural network (CNN) or transformer is usually acted as the encoder since the encoder is necessary to be used. On one hand, the convolution operation of CNN has advantages of extracting local information although its performance of obtaining global expressions is bad. On the other hand, the attention mechanism of the transformer is good at establishing remote dependencies while it is lacking in the ability to extract high-precision local information. Either high precision local information or global contextual information is crucial in brain tumor segmentation tasks. The aim of this paper is to propose a brain tumor segmentation model that can simultaneously extract and fuse high-precision local and global contextual information. Approach . We propose a network model DE-Uformer with dual encoders to obtain local features and global representations using both CNN encoder and Transformer encoder. On the basis of this, we further propose the nested encoder-aware feature fusion (NEaFF) module for effective deep fusion of the information under each dimension. It may establishe remote dependencies of features under a single encoder via the spatial attention Transformer. Meanwhile ,it also investigates how features extracted from two encoders are related with the cross-encoder attention transformer. Main results . The proposed algorithm segmentation have been performed on BraTS2020 dataset and private meningioma dataset. Results show that it is significantly better than current state-of-the-art brain tumor segmentation methods. Significance . The method proposed in this paper greatly improves the accuracy of brain tumor segmentation. This advancement helps healthcare professionals perform a more comprehensive analysis and assessment of brain tumors, thereby improving diagnostic accuracy and reliability. This fully automated brain model segmentation model with high accuracy is of great significance for critical decisions made by physicians in selecting treatment strategies and preoperative planning.
- 7 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Haptics
- Vol. 17 (3) , 302-309
Design and Evaluation of a Wearable Fingertip Device for Three-Dimensional Skin-Slip Display
Skin-slip provides crucial cues about the interaction state and surface properties. Currently, most skin-slip devices focus on two-dimensional tactile slip display and have limitations when displaying surface properties like bumps and contours. In this paper, a wearable fingertip device with a simple, effective, and low-cost design for three-dimensional skin-slip display is proposed. Continuous multi-directional skin-slip and normal indentation are combined to convey the sensation of three-dimensional geometric properties in virtual reality during active finger exploration. The device has a tactile belt, a five-bar mechanism, and four motors. Cooperating with the angle-mapping strategy, two micro DC motors are used to transmit continuous multi-directional skin-slip. Two servo motors are used to drive the five-bar mechanism to provide normal indentation. The characteristics of the device were obtained through the bench tests. Three experiments were designed and sequentially conducted to evaluate the performance of the device in three-dimensional surface exploration. The experimental results suggested that this device could effectively transmit continuous multi-directional skin-slip sensations, convey different bumps, and display surface contours.
- 7 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Haptics
- Vol. 17 (3) , 302-309
Design and Evaluation of a Wearable Fingertip Device for Three-Dimensional Skin-Slip Display
Skin-slip provides crucial cues about the interaction state and surface properties. Currently, most skin-slip devices focus on two-dimensional tactile slip display and have limitations when displaying surface properties like bumps and contours. In this paper, a wearable fingertip device with a simple, effective, and low-cost design for three-dimensional skin-slip display is proposed. Continuous multi-directional skin-slip and normal indentation are combined to convey the sensation of three-dimensional geometric properties in virtual reality during active finger exploration. The device has a tactile belt, a five-bar mechanism, and four motors. Cooperating with the angle-mapping strategy, two micro DC motors are used to transmit continuous multi-directional skin-slip. Two servo motors are used to drive the five-bar mechanism to provide normal indentation. The characteristics of the device were obtained through the bench tests. Three experiments were designed and sequentially conducted to evaluate the performance of the device in three-dimensional surface exploration. The experimental results suggested that this device could effectively transmit continuous multi-directional skin-slip sensations, convey different bumps, and display surface contours.
- 31 August 2023
- Published by Springer Nature
- p. 145-152
A Deep Learning Ensemble for Ultrasonic Weld Quality Control
- 31 August 2023
- Published by Springer Nature
- p. 145-152
A Deep Learning Ensemble for Ultrasonic Weld Quality Control
- 20 June 2023
- Published by Springer Nature in Journal of Intelligent & Robotic Systems
- Vol. 108 (3) , 1-16
A Novel Grasping Teleoperation Control for Dual-Handed System
- 20 June 2023
- Published by Springer Nature in Journal of Intelligent & Robotic Systems
- Vol. 108 (3) , 1-16
A Novel Grasping Teleoperation Control for Dual-Handed System