Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleSeptember 2024
Dual-consistency constraints network for noisy facial expression recognition
AbstractAlthough existing facial expression recognition (FER) methods have achieved great success, their performance degrades significantly under noisy labels caused by low-quality images, ambiguous expressions, and subjective and incorrect labeling. ...
Highlights- An effective DC-Net is presented to learn robust representations to suppress noisy samples.
- A novel Class Activation Mapping Attention Consistency is proposed to make model focus on partially important features.
- A novel Class ...
- research-articleJune 2024
Hard semantic mask strategy for automatic facial action unit recognition with teacher–student model
AbstractFacial Action Coding System (FACS) is a widely used technique in affective computing, which defines a series of facial action units (AUs) corresponding to localized regions of the face. Fine-grained feature information of critical regions is ...
- research-articleJuly 2024
Learning from feature and label spaces’ bias for uncertainty-adaptive facial emotion recognition
Pattern Recognition Letters (PTRL), Volume 182, Issue CPages 97–103https://doi.org/10.1016/j.patrec.2024.04.015AbstractDeveloping an accurate deep model for facial emotion recognition is a long-term challenge. It is because the uncertainty of emotions, stemming from the ambiguity of different emotional categories and the difference of subjective annotations, can ...
Highlights- We establish an uncertainty-adaptive framework via exploring the bias between two kinds of sample sets.
- We custom two modules namely cross-space attention consistency learning module and soft-label learning module.
- The experimental ...
- research-articleMay 2024
Learning informative and discriminative semantic features for robust facial expression recognition
Journal of Visual Communication and Image Representation (JVCIR), Volume 98, Issue Chttps://doi.org/10.1016/j.jvcir.2024.104062AbstractFacial expression recognition (FER) becomes challenging in real-world scenarios, which requires learning informative and discriminative features from challenging datasets to obtain robust facial expression recognition. In this paper, we propose ...
Highlights- An effective IDSFL network is presented to learn robust representations for FER in the wild.
- A novel multi-channel feature modulator incorporating Gabor features is proposed to learn informative features.
- A specific emotion-aware ...
- research-articleSeptember 2023
RT-Net: Region-Enhanced Attention Transformer Network for Polyp Segmentation
Neural Processing Letters (NPLE), Volume 55, Issue 9Pages 11975–11991https://doi.org/10.1007/s11063-023-11405-yAbstractColonic polyps are highly correlated with colorectal cancer. Prevention of colorectal cancer is the detection and removal of polyps in the early stages of the disease. But the detection process relies on the physician’s experience and is prone to ...
-
- research-articleJune 2023
Feature fusion of multi-granularity and multi-scale for facial expression recognition
The Visual Computer: International Journal of Computer Graphics (VISC), Volume 40, Issue 3Pages 2035–2047https://doi.org/10.1007/s00371-023-02900-3AbstractAlthough great progress has been made in facial expression recognition, it still faces challenges such as occlusion and pose changes in real-world scenario. To address this issue, we propose a simple yet effective multi-granularity and multi-scale ...
- research-articleMay 2023
ST-VQA: shrinkage transformer with accurate alignment for visual question answering
Applied Intelligence (KLU-APIN), Volume 53, Issue 18Pages 20967–20978https://doi.org/10.1007/s10489-023-04564-xAbstractWhile transformer-based models have been remarkably successful in the field of visual question answering (VQA), their approaches to achieve vision and language feature alignment are simple and coarse. In recent years, this shortcoming has been ...
- research-articleDecember 2022
Three-dimensional quantum wavelet transforms
Frontiers of Computer Science: Selected Publications from Chinese Universities (FCS), Volume 17, Issue 5https://doi.org/10.1007/s11704-022-1639-yAbstractWavelet transform is being widely used in the field of information processing. One-dimension and two-dimension quantum wavelet transforms have been investigated as important tool algorithms. However, three-dimensional quantum wavelet transforms ...
- research-articleNovember 2022
Collaborative learning network for head pose estimation
Highlights- Propose a collaborative learning framework for head pose estimation.
- Learn ...
Head pose estimation is an important task in many real-world applications, such as human–computer interaction, driver monitoring, face localization and gaze estimation. In this paper, we present a novel collaborative learning framework ...
- research-articleNovember 2022
HRNet:A hierarchical recurrent convolution neural network for retinal vessel segmentation
Multimedia Tools and Applications (MTAA), Volume 81, Issue 28Pages 39829–39851https://doi.org/10.1007/s11042-022-12696-4AbstractThe extraction of retinal vessel is of great importance in the diagnosis of fundus disease. Many approaches have been proposed for vessel segmentation. However, these models have some drawbacks. First, the encoder-decoder structures, U-Net i.e., ...
- research-articleSeptember 2022
MFC-Net: Multi-scale fusion coding network for Image Deblurring
Applied Intelligence (KLU-APIN), Volume 52, Issue 11Pages 13232–13249https://doi.org/10.1007/s10489-021-02993-0AbstractThe existing image blind deblurring methods mostly adopt the “coarse-to-fine” scheme, which always require a mass of parameters and can not mine the blur information effectively. To tackle the above problems, we design a lightweight multi-scale ...
- ArticleJuly 2022
Cooperative Positioning Enhancement for HDVs and CAVs Coexisting Environment Using Deep Neural Networks
AbstractAccurate vehicle positioning is a key technology affecting traffic safety and travel efficiency. High precision positioning technology combined with the internet of vehicles (IoV) can improve the positioning accuracy of human-driving vehicles (...
- research-articleJuly 2022
HT-Net: hierarchical context-attention transformer network for medical ct image segmentation
Applied Intelligence (KLU-APIN), Volume 52, Issue 9Pages 10692–10705https://doi.org/10.1007/s10489-021-03010-0AbstractConvolutional neural networks (CNNs) have been a prevailing technique in the field of medical CT image processing. Although encoder-decoder CNNs exploit locality for efficiency, they cannot adequately model remote pixel relationships. Recent works ...
- research-articleJune 2022
A multi-scale gated network for retinal hemorrhage detection
Applied Intelligence (KLU-APIN), Volume 53, Issue 5Pages 5259–5273https://doi.org/10.1007/s10489-022-03476-6AbstractRetinal hemorrhage detection is of great significance for clinical diagnosis and disease control. However, most of the traditional methods need to obtain candidate lesions firstly, and then determine the true lesions. To address this problem, we ...
- research-articleJune 2022
ECA-CBAM: Classification of Diabetic Retinopathy: Classification of diabetic retinopathy by cross-combined attention mechanism
ICIAI '22: Proceedings of the 2022 6th International Conference on Innovation in Artificial IntelligencePages 78–82https://doi.org/10.1145/3529466.3529468Although there is no distinctive header, this is the abstract. Diabetic retinopathy is an ophthalmological disease that causes bleeding in the fundus and loss of vision due to damage to blood vessels in the retina. It is one of the main causes of vision ...
- research-articleJanuary 2022
Safety and energy-saving driving behaviour evaluation with driving feature constraint TOPSIS method
International Journal of Computing Science and Mathematics (IJCSM), Volume 16, Issue 1Pages 59–70https://doi.org/10.1504/ijcsm.2022.126769There are many factors including driving behaviours, roads, weather to affect the safety and energy-saving of the vehicle and these driving behaviours have different features which impact the safety and energy-saving. To improve the performance of safety ...
- research-articleJanuary 2022
MC-Net: multi-scale context-attention network for medical CT image segmentation
Applied Intelligence (KLU-APIN), Volume 52, Issue 2Pages 1508–1519https://doi.org/10.1007/s10489-021-02506-zAbstractThe encoder-decoder CNN architecture has greatly improved CT medical image segmentation, but it encounters a bottleneck due to the loss of details in the encoding process, which limits the accuracy improvement. To address this problem, we propose ...
- research-articleDecember 2020
Style transfer for QR code
Multimedia Tools and Applications (MTAA), Volume 79, Issue 45-46Pages 33839–33852https://doi.org/10.1007/s11042-019-08555-4AbstractDue to fast scanning response and strong damage resistance, Quick Response (QR) code has been used widely in product tracking, item identification, time tracking, document management, and general marketing. The standard QR code consisting of black ...
- research-articleJune 2020
Md-Net: Multi-scale Dilated Convolution Network for CT Images Segmentation
Neural Processing Letters (NPLE), Volume 51, Issue 3Pages 2915–2927https://doi.org/10.1007/s11063-020-10230-xAbstractAccurate CT image segmentation is of great importance to the clinical diagnosis. Due to the high similarity of gray values in CT image, the segmented areas are easily affected by their surroundings, which leads to the loss of semantic information. ...
- research-articleMay 2020