Jifeng Guo
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
Jifeng Guo has a total of 41 co-authors. Here are the top co-authors by number of shared publications:
- Zhiqi Pang
Faculty of Computing, Harbin Institute of Technology, Harbin, China
7 shared publications - Wenbo Sun
College of Information and Computer Engineering, Northeast Forestry University, Harbin, China
4 shared publications Yu Chen
College of Information and Computer Engineering, Northeast Forestry University, Harbin, China
4 shared publications- Jingtan Guo
Control Technology Institute, Wuxi Institute of Technology, Wuxi, China
2 shared publications - Mingzhi Wang
School of Software Dalian University of Technology Dalian China
2 shared publications - Rui Chang
College of Information and Computer Engineering, Northeast Forestry University, Harbin, China
2 shared publications
Latest Publications
- Open Access
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 2636-2645
ClearNight: Synergistic Dual-Prior Aggregation for Nighttime Image Dehazing
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 2636-2645
Open AccessClearNight: Synergistic Dual-Prior Aggregation for Nighttime Image Dehazing
- 20 May 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 200
DSCL-ReID: Person re-identification with dynamic prompts and contrastive learning
- 20 May 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 200
DSCL-ReID: Person re-identification with dynamic prompts and contrastive learning
- Retracted
- 24 January 2024
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (33) , 80279
RETRACTED ARTICLE: HR-CycleGAN: Face highlight reduction based on improved cycle-consistent adversarial networks
- 24 January 2024
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (33) , 80279
RetractedRETRACTED ARTICLE: HR-CycleGAN: Face highlight reduction based on improved cycle-consistent adversarial networks
- Open Access
- 12 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Systems and Rehabilitation Engineering
- Vol. 31 (15344320) , 3664-3674
Multimodal Autism Spectrum Disorder Diagnosis Method Based on DeepGCN
Multimodal data play an important role in the diagnosis of brain diseases. This study constructs a whole-brain functional connectivity network based on functional MRI data, uses non-imaging data with demographic information to complement the classification task for diagnosing subjects, and proposes a multimodal and across-site WL-DeepGCN-based method for classification to diagnose autism spectrum disorder (ASD). This method is used to resolve the existing problem that deep learning ASD identification cannot efficiently utilize multimodal data. In the WL-DeepGCN, a weight-learning network is used to represent the similarity of non-imaging data in the latent space, introducing a new approach for constructing population graph edge weights, and we find that it is beneficial and robust to define pairwise associations in the latent space rather than the input space. We propose a graph convolutional neural network residual connectivity approach to reduce the information loss due to convolution operations by introducing residual units to avoid gradient disappearance and gradient explosion. Furthermore, an EdgeDrop strategy makes the node connections sparser by randomly dropping edges in the raw graph, and its introduction can alleviate the overfitting and oversmoothing problems in the DeepGCN training process. We compare the WL-DeepGCN model with competitive models based on the same topics and nested 10-fold cross-validation show that our method achieves 77.27% accuracy and 0.83 AUC for ASD identification, bringing substantial performance gains.
- 12 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Systems and Rehabilitation Engineering
- Vol. 31 (15344320) , 3664-3674
Open AccessMultimodal Autism Spectrum Disorder Diagnosis Method Based on DeepGCN
Multimodal data play an important role in the diagnosis of brain diseases. This study constructs a whole-brain functional connectivity network based on functional MRI data, uses non-imaging data with demographic information to complement the classification task for diagnosing subjects, and proposes a multimodal and across-site WL-DeepGCN-based method for classification to diagnose autism spectrum disorder (ASD). This method is used to resolve the existing problem that deep learning ASD identification cannot efficiently utilize multimodal data. In the WL-DeepGCN, a weight-learning network is used to represent the similarity of non-imaging data in the latent space, introducing a new approach for constructing population graph edge weights, and we find that it is beneficial and robust to define pairwise associations in the latent space rather than the input space. We propose a graph convolutional neural network residual connectivity approach to reduce the information loss due to convolution operations by introducing residual units to avoid gradient disappearance and gradient explosion. Furthermore, an EdgeDrop strategy makes the node connections sparser by randomly dropping edges in the raw graph, and its introduction can alleviate the overfitting and oversmoothing problems in the DeepGCN training process. We compare the WL-DeepGCN model with competitive models based on the same topics and nested 10-fold cross-validation show that our method achieves 77.27% accuracy and 0.83 AUC for ASD identification, bringing substantial performance gains.
- 11 April 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 82 (26) , 41307-41321
DCTNet: hybrid deep neural network-based EEG signal for detecting depression
- 11 April 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 82 (26) , 41307-41321
DCTNet: hybrid deep neural network-based EEG signal for detecting depression
- Open Access
- 24 December 2022
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 17 (5) , 1427-1437
Independency‐enhancing adversarial active learning
The core idea of active learning is to obtain higher model performance with less annotation cost. This paper proposes an independency‐enhancing adversarial active learning method. Independency‐enhancing adversarial active learning is different from the previous methods and pays more attention to sample independence. Specifically, it is believed that the informativeness of a group of samples is related to sample independence rather than the simple sum of the informativeness of each sample in the group. Therefore, an independent sample selection module based on hierarchical clustering is designed to ensure sample independence. An adversarial approach is used to learn the feature representation of a sample and use the predicted loss value to label the state of the sample. Finally, samples are selected according to the uncertainty of the samples, the diversity of the samples and the independence of the samples. The experimental results on four datasets (CIFAR‐100, Caltech‐101, Cityscapes and BDD100K) demonstrate the effectiveness and superiority of independency‐enhancing adversarial active learning.
- 24 December 2022
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 17 (5) , 1427-1437
Open AccessIndependency‐enhancing adversarial active learning
The core idea of active learning is to obtain higher model performance with less annotation cost. This paper proposes an independency‐enhancing adversarial active learning method. Independency‐enhancing adversarial active learning is different from the previous methods and pays more attention to sample independence. Specifically, it is believed that the informativeness of a group of samples is related to sample independence rather than the simple sum of the informativeness of each sample in the group. Therefore, an independent sample selection module based on hierarchical clustering is designed to ensure sample independence. An adversarial approach is used to learn the feature representation of a sample and use the predicted loss value to label the state of the sample. Finally, samples are selected according to the uncertainty of the samples, the diversity of the samples and the independence of the samples. The experimental results on four datasets (CIFAR‐100, Caltech‐101, Cityscapes and BDD100K) demonstrate the effectiveness and superiority of independency‐enhancing adversarial active learning.
- Open Access
- 22 October 2022
- Published by Wiley in Computational Intelligence and Neuroscience
- Vol. 2022, 1-15
Multiscale Traffic Sign Detection Method in Complex Environment Based on YOLOv4
Traffic sign detection is a challenging problem in the field of unmanned driving, particularly important in complex environments. We propose a method, based on the improved You only look once (YOLO) v4, to detect and recognize multiscale traffic signs in complex environments. This method employs an image preprocessing module that can classify and denoize images of complex environments and then input the images into the improved YOLOv4. We also design an improved feature pyramid structure to replace the original feature pyramid of YOLOv4. This structure uses an adaptive feature fusion module and a multiscale feature transfer mechanism to reduce putative information loss in the feature map generation process and improve the information transfer between deep and shallow features, enhancing the representation ability of feature pyramids. Finally, we use EIOU LOSS and Cluster-NMS to further improve the model performance. The experimental results on the fusion of Tsinghua-Tencent 100 K and our collected dataset show that the proposed method achieves an mAP of 81.78%. Compared to existing methods, our method demonstrates its superiority with regard to traffic sign detection.
- 22 October 2022
- Published by Wiley in Computational Intelligence and Neuroscience
- Vol. 2022, 1-15
Open AccessMultiscale Traffic Sign Detection Method in Complex Environment Based on YOLOv4
Traffic sign detection is a challenging problem in the field of unmanned driving, particularly important in complex environments. We propose a method, based on the improved You only look once (YOLO) v4, to detect and recognize multiscale traffic signs in complex environments. This method employs an image preprocessing module that can classify and denoize images of complex environments and then input the images into the improved YOLOv4. We also design an improved feature pyramid structure to replace the original feature pyramid of YOLOv4. This structure uses an adaptive feature fusion module and a multiscale feature transfer mechanism to reduce putative information loss in the feature map generation process and improve the information transfer between deep and shallow features, enhancing the representation ability of feature pyramids. Finally, we use EIOU LOSS and Cluster-NMS to further improve the model performance. The experimental results on the fusion of Tsinghua-Tencent 100 K and our collected dataset show that the proposed method achieves an mAP of 81.78%. Compared to existing methods, our method demonstrates its superiority with regard to traffic sign detection.
- Open Access
- 15 August 2022
- Published by Frontiers Media SA in Frontiers in Genetics
- Vol. 13, 963349
A method for identifying moonlighting proteins based on linear discriminant analysis and bagging-SVM
Moonlighting proteins have at least two independent functions and are widely found in animals, plants and microorganisms. Moonlighting proteins play important roles in signal transduction, cell growth and movement, tumor inhibition, DNA synthesis and repair, and metabolism of biological macromolecules. Moonlighting proteins are difficult to find through biological experiments, so many researchers identify moonlighting proteins through bioinformatics methods, but their accuracies are relatively low. Therefore, we propose a new method. In this study, we select SVMProt-188D as the feature input, and apply a model combining linear discriminant analysis and basic classifiers in machine learning to study moonlighting proteins, and perform bagging ensemble on the best-performing support vector machine. They are identified accurately and efficiently. The model achieves an accuracy of 93.26% and an F-sorce of 0.946 on the MPFit dataset, which is better than the existing MEL-MP model. Meanwhile, it also achieves good results on the other two moonlighting protein datasets.
- 15 August 2022
- Published by Frontiers Media SA in Frontiers in Genetics
- Vol. 13, 963349
Open AccessA method for identifying moonlighting proteins based on linear discriminant analysis and bagging-SVM
Moonlighting proteins have at least two independent functions and are widely found in animals, plants and microorganisms. Moonlighting proteins play important roles in signal transduction, cell growth and movement, tumor inhibition, DNA synthesis and repair, and metabolism of biological macromolecules. Moonlighting proteins are difficult to find through biological experiments, so many researchers identify moonlighting proteins through bioinformatics methods, but their accuracies are relatively low. Therefore, we propose a new method. In this study, we select SVMProt-188D as the feature input, and apply a model combining linear discriminant analysis and basic classifiers in machine learning to study moonlighting proteins, and perform bagging ensemble on the best-performing support vector machine. They are identified accurately and efficiently. The model achieves an accuracy of 93.26% and an F-sorce of 0.946 on the MPFit dataset, which is better than the existing MEL-MP model. Meanwhile, it also achieves good results on the other two moonlighting protein datasets.
- 11 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 28 (10709908) , 2142-2146
Biclustering Collaborative Learning for Cross-Domain Person Re-Identification
In the cross-domain person re-identification (ReID) method based on clustering, the performance of the model depends heavily on the quality of the information it obtains from clustering. To improve the reliability of the clustering information obtained by the model, we propose a biclustering collaborative learning (BCL) framework derived from an identity disentanglement adaptation network (IDA-Net). IDA-Net encodes the identity and style of the input image and transfers the style on the premise of maintaining identity consistency. By comparing the clustering results obtained on the same dataset before and after the transfer process, BCL can select hard samples with higher confidence for model optimization. In each iteration, we design a conditional batch hard triplet loss to optimize the two networks. Extensive experiments on large-scale datasets (Maket1501, DukeMTMC-reID and MSMT17) demonstrate the superior performance of BCL over the state-of-the-art methods.
- 11 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 28 (10709908) , 2142-2146
Biclustering Collaborative Learning for Cross-Domain Person Re-Identification
In the cross-domain person re-identification (ReID) method based on clustering, the performance of the model depends heavily on the quality of the information it obtains from clustering. To improve the reliability of the clustering information obtained by the model, we propose a biclustering collaborative learning (BCL) framework derived from an identity disentanglement adaptation network (IDA-Net). IDA-Net encodes the identity and style of the input image and transfers the style on the premise of maintaining identity consistency. By comparing the clustering results obtained on the same dataset before and after the transfer process, BCL can select hard samples with higher confidence for model optimization. In each iteration, we design a conditional batch hard triplet loss to optimize the two networks. Extensive experiments on large-scale datasets (Maket1501, DukeMTMC-reID and MSMT17) demonstrate the superior performance of BCL over the state-of-the-art methods.
- 9 August 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 32 (5) , 3164-3177
Median Stable Clustering and Global Distance Classification for Cross-Domain Person Re-Identification
The person re-identification (ReID) method in a single-domain achieves appealing performance, but its reliance on label information greatly limits its extensibility. Therefore, the unsupervised cross-domain ReID method has received extensive attention. Its purpose is to optimize the model by using the labelled source domain and the unlabelled target domain and finally make the model well generalized in the target domain. We propose an unsupervised cross-domain ReID method based on median stable clustering (MSC) and global distance classification (GDC). Specifically, the measurement method used by MSC comprehensively considers the similarity between clusters, the number of samples in a cluster, and the combined similarity within a cluster. Different from the method based on triple loss, GDC can separate the distance distribution of positive and negative sample pairs in a global scope. In addition, considering that model performance is very sensitive to probability parameters when source domain memory is reconsolidated, we designed a dynamic memory reconsolidation (DMR) method to reduce the influence of parameters on performance. Extensive experiments on large-scale datasets (Market-1501, DukeMTMC-reID and MSMT17) demonstrate the superior performance of MSC-GDC over the state-of-the-art methods.
- 9 August 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 32 (5) , 3164-3177
Median Stable Clustering and Global Distance Classification for Cross-Domain Person Re-Identification
The person re-identification (ReID) method in a single-domain achieves appealing performance, but its reliance on label information greatly limits its extensibility. Therefore, the unsupervised cross-domain ReID method has received extensive attention. Its purpose is to optimize the model by using the labelled source domain and the unlabelled target domain and finally make the model well generalized in the target domain. We propose an unsupervised cross-domain ReID method based on median stable clustering (MSC) and global distance classification (GDC). Specifically, the measurement method used by MSC comprehensively considers the similarity between clusters, the number of samples in a cluster, and the combined similarity within a cluster. Different from the method based on triple loss, GDC can separate the distance distribution of positive and negative sample pairs in a global scope. In addition, considering that model performance is very sensitive to probability parameters when source domain memory is reconsolidated, we designed a dynamic memory reconsolidation (DMR) method to reduce the influence of parameters on performance. Extensive experiments on large-scale datasets (Market-1501, DukeMTMC-reID and MSMT17) demonstrate the superior performance of MSC-GDC over the state-of-the-art methods.