Query：
学者姓名：贾克斌
Refining：
Year
Type
Indexed by
Source
Complex
Former Name
Co-Author
Language
Clean All
Abstract ：
As skeleton data becomes increasingly available, Graph Convolutional Networks (GCNs) are popularly adapted to extract the spatial and temporal features for skeleton-based action recognition. However, there are still limitations to be addressed in GCN-based methods. First, the multi-level semantic features fail to be connected, making fine-grained information loss as the network deepens. Second, the cross-scale spatiotempral features fail to be simultaneously considered and refined to focus on informative areas. These limitations lead to the challenge in distinguishing the confusing actions. To address these issues, we propose a cross-scale connection (CSC) structure and a spatiotemporal refinement focus (STRF) module. The CSC aims to bridge the gap between multi-level semantic features. The STRF module refines the cross-scale spatiotemporal features to focus on informative joints in each frame. Both are embedded into the standard GCNs to form the cross-scale spatiotemporal refinement network (CSR-Net). Our proposed CSR-Net explicitly models the cross-scale spatiotemporal information among multi-level semantic representations to boost the distinguishing capability for ambiguous actions. We conduct extensive experiments to demonstrate the effectiveness of our proposed method and it outperforms state-of-the-art methods on the NTU RGB+D 60, NTU-RGB+D 120 and NW-UCLA datasets.
Keyword ：
Skeleton-based action recognition Skeleton-based action recognition cross-scale fusion cross-scale fusion graph convolutional network graph convolutional network
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhang, Yu , Sun, Zhonghua , Dai, Meng et al. Cross-Scale Spatiotemporal Refinement Learning for Skeleton-Based Action Recognition [J]. | IEEE SIGNAL PROCESSING LETTERS , 2024 , 31 : 441-445 . |
| MLA | Zhang, Yu et al. "Cross-Scale Spatiotemporal Refinement Learning for Skeleton-Based Action Recognition" . | IEEE SIGNAL PROCESSING LETTERS 31 (2024) : 441-445 . |
| APA | Zhang, Yu , Sun, Zhonghua , Dai, Meng , Feng, Jinchao , Jia, Kebin . Cross-Scale Spatiotemporal Refinement Learning for Skeleton-Based Action Recognition . | IEEE SIGNAL PROCESSING LETTERS , 2024 , 31 , 441-445 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
Depression has become the prevailing global mental health concern. The accuracy of traditional depression diagnosis methods faces challenges due to diverse factors, making primary identification a complex task. Thus, the imperative lies in developing a method that fulfills objectivity and effectiveness criteria for depression identification. Current research underscores notable disparities in brain activity between individuals with depression and those without. The Electroencephalogram (EEG), as a biologically reflective and easily accessible signal, is widely used to diagnose depression. This article introduces an innovative depression prediction strategy that merges time-frequency complexity and electrode spatial topology to aid in depression diagnosis. Initially, time-frequency complexity and temporal features of the EEG signal are extracted to generate node features for a graph convolutional network. Subsequently, leveraging channel correlation, the brain network adjacency matrix is employed and calculated. The final depression classification is achieved by training and validating a graph convolutional network with graph node features and a brain network adjacency matrix based on channel correlation. The proposed strategy has been validated using two publicly available EEG datasets, MODMA and PRED+CT, achieving notable accuracy rates of 98.30 and 96.51%, respectively. These outcomes affirm the reliability and utility of our proposed strategy in predicting depression using EEG signals. Additionally, the findings substantiate the effectiveness of EEG time-frequency complexity characteristics as valuable biomarkers for depression prediction.
Keyword ：
brain network brain network depression prediction depression prediction EEG signal EEG signal time-frequency complexity time-frequency complexity spatial topology spatial topology graph convolutional network graph convolutional network
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Liu, Wei , Jia, Kebin , Wang, Zhuozheng . Graph-based EEG approach for depression prediction: integrating time-frequency complexity and spatial topology [J]. | FRONTIERS IN NEUROSCIENCE , 2024 , 18 . |
| MLA | Liu, Wei et al. "Graph-based EEG approach for depression prediction: integrating time-frequency complexity and spatial topology" . | FRONTIERS IN NEUROSCIENCE 18 (2024) . |
| APA | Liu, Wei , Jia, Kebin , Wang, Zhuozheng . Graph-based EEG approach for depression prediction: integrating time-frequency complexity and spatial topology . | FRONTIERS IN NEUROSCIENCE , 2024 , 18 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
The majority of the optical observations collected via spaceborne optical satellites are corrupted by clouds or haze, restraining further applications of Earth observation; thus, exploring an ideal method for cloud removal is of great concern. In this paper, we propose a novel probabilistic generative model named sequential-based diffusion models (SeqDMs) for the cloud-removal task in a remote sensing domain. The proposed method consists of multi-modal diffusion models (MmDMs) and a sequential-based training and inference strategy (SeqTIS). In particular, MmDMs is a novel diffusion model that reconstructs the reverse process of denosing diffusion probabilistic models (DDPMs) to integrate additional information from auxiliary modalities (e.g., synthetic aperture radar robust to the corruption of clouds) to help the distribution learning of main modality (i.e., optical satellite imagery). In order to consider the information across time, SeqTIS is designed to integrate temporal information across an arbitrary length of both the main modality and auxiliary modality input sequences without retraining the model again. With the help of MmDMs and SeqTIS, SeqDMs have the flexibility to handle an arbitrary length of input sequences, producing significant improvements only with one or two additional input samples and greatly reducing the time cost of model retraining. We evaluate our method on a public real-world dataset SEN12MS-CR-TS for a multi-modal and multi-temporal cloud-removal task. Our extensive experiments and ablation studies demonstrate the superiority of the proposed method on the quality of the reconstructed samples and the flexibility to handle arbitrary length sequences over multiple state-of-the-art cloud removal approaches.
Keyword ：
cloud removal cloud removal diffusion models diffusion models multi-modal multi-modal synthetic aperture radar (SAR)-optical synthetic aperture radar (SAR)-optical multi-temporal multi-temporal
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhao, Xiaohu , Jia, Kebin . Cloud Removal in Remote Sensing Using Sequential-Based Diffusion Models [J]. | REMOTE SENSING , 2023 , 15 (11) . |
| MLA | Zhao, Xiaohu et al. "Cloud Removal in Remote Sensing Using Sequential-Based Diffusion Models" . | REMOTE SENSING 15 . 11 (2023) . |
| APA | Zhao, Xiaohu , Jia, Kebin . Cloud Removal in Remote Sensing Using Sequential-Based Diffusion Models . | REMOTE SENSING , 2023 , 15 (11) . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
Vehicle passing angles are critical metrics for evaluating the geometric passability of vehicles. The accurate measurement of these angles is essential for route planning in complex terrain and in guiding the production of specialized vehicles. However, the current measurement methods cannot meet the requirements of efficiency, convenience and robustness. This paper presents a novel measurement method by building and measuring the point cloud of a vehicle chassis. Based on this method, a novel measurement system is designed and its effectiveness is verified. In the system, a wheeled robot acquires and processes data after passing underneath the vehicle. Then, we introduce a new approach to reduce the main sources of error when building point clouds beneath the vehicle, achieved by modifying the extraction algorithm and the proportion of different feature points in each frame. Additionally, we present a fast geometric calculation algorithm for calculating the passing angles. The simulation experiment results demonstrate deviations of 0.06252%, 0.01575%, and 0.003987% when comparing the calculated angles to those of the simulated vehicle. The experimental results show that the method and system are effective at acquiring the point cloud of the vehicle and calculating the parameters of passing angles with good data consistency, exhibiting variances of 0.12407, 0.12407, and 0.69804.
Keyword ：
passing angles passing angles information processing information processing LIDAR LIDAR data acquisition data acquisition point cloud point cloud
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Chen, Jiaping , Jia, Kebin , Wang, Zhiju et al. An Intelligent Measurement Method and System for Vehicle Passing Angles [J]. | APPLIED SCIENCES-BASEL , 2023 , 13 (11) . |
| MLA | Chen, Jiaping et al. "An Intelligent Measurement Method and System for Vehicle Passing Angles" . | APPLIED SCIENCES-BASEL 13 . 11 (2023) . |
| APA | Chen, Jiaping , Jia, Kebin , Wang, Zhiju , Sun, Zhonghua . An Intelligent Measurement Method and System for Vehicle Passing Angles . | APPLIED SCIENCES-BASEL , 2023 , 13 (11) . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
Forests are critical to mitigating global climate change and regulating climate through their role in the global carbon and water cycles. Accurate monitoring of forest cover is, therefore, essential. Image segmentation networks based on convolutional neural networks have shown significant advantages in remote sensing image analysis with the development of deep learning. However, deep learning networks typically require a large amount of manual ground truth labels for training, and existing widely used image segmentation networks struggle to extract details from large-scale high resolution satellite imagery. Improving the accuracy of forest image segmentation remains a challenge. To reduce the cost of manual labelling, this paper proposed a data augmentation method that expands the training data by modifying the spatial distribution of forest remote sensing images. In addition, to improve the ability of the network to extract multi-scale detailed features and the feature information from the NIR band of satellite images, we proposed a high-resolution forest remote sensing image segmentation network by fusing multi-scale features based on double input. The experimental results using the Sanjiangyuan plateau forest dataset show that our method achieves an IoU of 90.19%, which outperforms prevalent image segmentation networks. These results demonstrate that the proposed approaches can extract forests from remote sensing images more effectively and accurately.
Keyword ：
data augmentation data augmentation remote sensing remote sensing image segmentation image segmentation deep learning deep learning multi-scale features extraction multi-scale features extraction
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | He, Yan , Jia, Kebin , Wei, Zhihao . Improvements in Forest Segmentation Accuracy Using a New Deep Learning Architecture and Data Augmentation Technique [J]. | REMOTE SENSING , 2023 , 15 (9) . |
| MLA | He, Yan et al. "Improvements in Forest Segmentation Accuracy Using a New Deep Learning Architecture and Data Augmentation Technique" . | REMOTE SENSING 15 . 9 (2023) . |
| APA | He, Yan , Jia, Kebin , Wei, Zhihao . Improvements in Forest Segmentation Accuracy Using a New Deep Learning Architecture and Data Augmentation Technique . | REMOTE SENSING , 2023 , 15 (9) . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
本发明公开了基于图卷积神经网络的近红外光谱层析成像重建方法，本发明提出一种基于图卷积的深度学习网络框架，该深度学习网络框架对具有不规则结构的成像域建立图模型，并将图结构信息加入到带有注意力机制的图卷积神经网络中，以提取图节点上的光学特征参数的特征，将采集到的光学信号作为网络输入进行端到端的训练，同时恢复出含氧血红蛋白，脱氧血红蛋白和水三种发色团的浓度。实验结果表明，本发明能够实现NIRST图像的准确重建。
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 冯金超 , 苏琳轩 , 魏承朴 et al. 基于图卷积神经网络的近红外光谱层析成像重建方法 : CN202310513333.3[P]. | 2023-05-09 . |
| MLA | 冯金超 et al. "基于图卷积神经网络的近红外光谱层析成像重建方法" : CN202310513333.3. | 2023-05-09 . |
| APA | 冯金超 , 苏琳轩 , 魏承朴 , 贾克斌 , 李哲 , 孙中华 . 基于图卷积神经网络的近红外光谱层析成像重建方法 : CN202310513333.3. | 2023-05-09 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
本发明公开了一种基于深度学习的扩散相关光谱无创血压连续监测方法，具体包括：首先，基于扩散相关光谱技术获取被测试者手臂部位的光强自相关函数数据，利用传统非线性拟合方法计算出组织血流指数；然后，基于所提出的U‑net网络将拟合出的组织血流指数数据进行训练，建立从组织血流指数到血压之间的端到端网络模型；最后，将测试集数据送入训练好的网络模型中，实现血压的预测，从而得到连续血压波形。本发明直接建立了组织血流指数与血压间的端到端关系，为无创血压连续监测提供了新方法，克服了现有无创血压连续监测方法操作繁琐、因袖带充气而导致不适等不足，为人们了解血压的起伏变化提供了方便。
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 李哲 , 白江涛 , 姜敏楠 et al. 一种基于深度学习的扩散相关光谱无创血压连续监测方法 : CN202310317145.3[P]. | 2023-03-26 . |
| MLA | 李哲 et al. "一种基于深度学习的扩散相关光谱无创血压连续监测方法" : CN202310317145.3. | 2023-03-26 . |
| APA | 李哲 , 白江涛 , 姜敏楠 , 冯金超 , 贾克斌 . 一种基于深度学习的扩散相关光谱无创血压连续监测方法 : CN202310317145.3. | 2023-03-26 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
本发明公开了一种基于神经网络的用于压缩视频质量增强的方法，属于视频后处理领域。其特征在于：首先构建了包含多个具有不同分辨率和内容的压缩视频集用于训练；其次设计了时空信息预提取网络，通过3D卷积层对特征图在时空维度上进行编解码，同时在时空维度上提取特征图底层特征和深层特征；最后设计了时空信息融合网络，将连续视频帧分解，在时间域上利用2D卷积层对分解的视频帧单独进行信息提取，然后再融合分解的视频帧特征，有效的对视频帧的信息进行增强，达到对压缩视频质量增强的目的。
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 贾克斌 , 黄威威 , 刘鹏宇 . 一种基于神经网络的用于压缩视频质量增强的方法 : CN202310256616.4[P]. | 2023-03-16 . |
| MLA | 贾克斌 et al. "一种基于神经网络的用于压缩视频质量增强的方法" : CN202310256616.4. | 2023-03-16 . |
| APA | 贾克斌 , 黄威威 , 刘鹏宇 . 一种基于神经网络的用于压缩视频质量增强的方法 : CN202310256616.4. | 2023-03-16 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
Sleep is crucial for human health. Automatic sleep stage classification based on polysomnogram (PSG) is meaningful for the diagnosis of sleep disorders, which has attracted extensive attention in recent years. Most existing methods could not fully consider the different transitions of sleep stages and fit the visual inspection of sleep experts simultaneously. To this end, we propose a temporal multi-scale hybrid attention network, namely TMHAN, to automatically achieve sleep staging. The temporal multi-scale mechanism incorporates short-term abrupt and long-term periodic transitions of the successive PSG epochs. Furthermore, the hybrid attention mechanism includes 1-D local attention, 2-D global attention, and 2-D contextual sparse multi-head self-attention for three kinds of sequence-level representations. The concatenated representation is subsequently fed into a softmax layer to train an end-to-end model. Experimental results on two benchmark sleep datasets show that TMHAN obtains the best performance compared with several baselines, demonstrating the effectiveness of our model. In general, our work not only provides good classification performance, but also fits the actual sleep staging processes, which makes contribution for the combination of deep learning and sleep medicine.
Keyword ：
Attention mechanism Attention mechanism Temporal multi-scale mechanism Temporal multi-scale mechanism Polysomnogram Polysomnogram Sleep stage classification Sleep stage classification Biomedical signal processing Biomedical signal processing
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Jin, Zheng , Jia, Kebin . A temporal multi-scale hybrid attention network for sleep stage classification [J]. | MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING , 2023 , 61 (9) : 2291-2303 . |
| MLA | Jin, Zheng et al. "A temporal multi-scale hybrid attention network for sleep stage classification" . | MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING 61 . 9 (2023) : 2291-2303 . |
| APA | Jin, Zheng , Jia, Kebin . A temporal multi-scale hybrid attention network for sleep stage classification . | MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING , 2023 , 61 (9) , 2291-2303 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
The Three-Dimensional High Efficiency Video Coding standard is a video compression standard developed based on the two-dimensional video coding standard HEVC and used to encode multi-view plus depth format video. This paper proposes an algorithm based on eXtreme Gradient Boosting to solve the problem of high inter-frame coding complexity in 3D-HEVC. Firstly, explore the correlation between the division depth of the inter-frame coding unit and the texture features in the map, as well as the correlation between the coding unit division structure between each map and each viewpoint. After that, based on the machine learning method, a fast selection mechanism for dividing the depth range of the inter-frame coding tree unit based on the eXtreme Gradient Boosting algorithm is constructed. Experimental results show that, compared with the reference software HTM-16.0, this method can save an average of 35.06% of the coding time, with negligible degradation in terms of coding performance. In addition, the proposed algorithm has achieved different degrees of improvement in coding performance compared with the related works.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhang, Ruyi , Jia, Kebin , Yu, Yuan et al. Fast 3D-HEVC inter coding using data mining and machine learning [J]. | IET IMAGE PROCESSING , 2022 , 16 (11) : 3067-3084 . |
| MLA | Zhang, Ruyi et al. "Fast 3D-HEVC inter coding using data mining and machine learning" . | IET IMAGE PROCESSING 16 . 11 (2022) : 3067-3084 . |
| APA | Zhang, Ruyi , Jia, Kebin , Yu, Yuan , Liu, Pengyu , Sun, Zhonghua . Fast 3D-HEVC inter coding using data mining and machine learning . | IET IMAGE PROCESSING , 2022 , 16 (11) , 3067-3084 . |
| Export to | NoteExpress RIS BibTex |
Export
| Results： |
Selected to |
| Format： |
