JSJie Shen

Jie Shen

*This is an algorithmically generated author record based on publicly available information.

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


Jie Shen has a total of 36 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Contrastive Learning with Dynamic Weighting and Jigsaw Augmentation for Brain Tumor Classification in MRI

    by Guanghua Xiao, Huibin Wang, Jie Shen, Zhe Chen, Zhen Zhang, Xiaomin Ge


  • Open Access

    Lightweight Multi-Scale Asymmetric Attention Network for Image Super-Resolution

    by Min Zhang, Huibin Wang, Zhen Zhang, Zhe Chen, Jie Shen

    Recently, with the development of convolutional neural networks, single-image super-resolution (SISR) has achieved better performance. However, the practical application of image super-resolution is limited by a large number of parameters and calculations. In this work, we present a lightweight multi-scale asymmetric attention network (MAAN), which consists of a coarse-grained feature block (CFB), fine-grained feature blocks (FFBs), and a reconstruction block (RB). MAAN adopts multiple paths to facilitate information flow and accomplish a better balance of performance and parameters. Specifically, the FFB applies a multi-scale attention residual block (MARB) to capture richer features by exploiting the pixel-to-pixel correlation feature. The asymmetric multi-weights attention blocks (AMABs) in MARB are designed to obtain the attention maps for improving SISR efficiency and readiness. Extensive experimental results show that our method has comparable performance with fewer parameters than the current advanced lightweight SISR.


  • Open Access

    Synergy Factorized Bilinear Network with a Dual Suppression Strategy for Brain Tumor Classification in MRI

    by Guanghua Xiao, Huibin Wang, Jie Shen, Zhe Chen, Zhen Zhang, Xiaomin Ge

    Automatic brain tumor classification is a practicable means of accelerating clinical diagnosis. Recently, deep convolutional neural network (CNN) training with MRI datasets has succeeded in computer-aided diagnostic (CAD) systems. To further improve the classification performance of CNNs, there is still a difficult path forward with regards to subtle discriminative details among brain tumors. We note that the existing methods heavily rely on data-driven convolutional models while overlooking what makes a class different from the others. Our study proposes to guide the network to find exact differences among similar tumor classes. We first present a “dual suppression encoding” block tailored to brain tumor MRIs, which diverges two paths from our network to refine global orderless information and local spatial representations. The aim is to use more valuable clues for correct classes by reducing the impact of negative global features and extending the attention of salient local parts. Then we introduce a “factorized bilinear encoding” layer for feature fusion. The aim is to generate compact and discriminative representations. Finally, the synergy between these two components forms a pipeline that learns in an end-to-end way. Extensive experiments exhibited superior classification performance in qualitative and quantitative evaluation on three datasets.


  • A Method for Slope Detection of Planetary Surface in The Autonomous Obstacle Avoidance of Planetary Rover

    by Bo Zheng, Jie Shen, Liang He, Tao Hu, Tao Cao, Muzi Li

    Planetary rover is the most efficient way to explore planets. The exploration area of planetary rover is a complex and unfamiliar environment. Planetary rover needs to perceive surrounding terrain and obstacle information clearly so as to ensure that the planetary rover can effectively and accurately perform autonomous obstacle avoidance and path planning in the unfamiliar environment. There is a problem that the slope is misjudged as an obstacle in autonomous obstacle avoidance, which leads to wrong planning decision. Meanwhile the passable area is treated as restricted area. Therefore, it is necessary to detect and estimate slope and identify the slope passing ability of planetary rover. A method for slope detection of planetary surface in the autonomous obstacle avoidance of planetary rover is presented in this paper. The down-sampling of original point cloud is processed by voxel mesh filtering. Meanwhile the real time 3D point cloud of large-scale planetary surface is clipped and segmented. The ground and obstacle are separated by local ground plane fitting estimation. Then slopes are calculated and classified, through which the slope above the threshold is reserved as obstacle and the slope below the threshold is set as passable area. The method presented in this paper is able to detect and classify the slope accurately in real time, which is shown in the simulation results.


  • Open Access

    A Study on Seizure Detection of EEG Signals Represented in 2D

    by Zhiwen Xiong, Huibin Wang, Lili Zhang, Tanghuai Fan, Jie Shen, Yue Zhao, Yang Liu, Qi Wu

    A seizure is a neurological disorder caused by abnormal neuronal discharges in the brain, which severely reduces the quality of life of patients and often endangers their lives. Automatic seizure detection is an important research area in the treatment of seizure and is a prerequisite for seizure intervention. Deep learning has been widely used for automatic detection of seizures, and many related research works decomposed the electroencephalogram (EEG) raw signal with a time window to obtain EEG signal slices, then performed feature extraction on the slices, and represented the obtained features as input data for neural networks. There are various methods for EEG signal decomposition, feature extraction, and representation, and most of the studies have been based on fixed hardware resources for the design of the scheme, which reduces the adaptability of the scheme in different application scenarios and makes it difficult to optimize the algorithms in the scheme. To address the above issues, this paper proposes a deep learning-based model for seizure detection, mainly characterized by the two-dimensional representation of EEG features and the scalability of neural networks. The model modularizes the main steps of seizure detection and improves the adaptability of the model to different hardware resource constraints, in order to increase the convenience of the algorithm optimization or the replacement of each module. The proposed model consists of five parts, and the model was tested using two epilepsy datasets separately. The experimental results showed that the proposed model has strong generality and good classification accuracy for seizure detection.


  • Open Access

    Real-Time Detection of River Surface Floating Object Based on Improved RefineDet

    by Lili Zhang, Yaxue Wei, Huibin Wang, Yehong Shao, Jie Shen

    Object detection is widely used in robot navigation, intelligent security and industrial detection, but it is rarely used in water conservancy industry. In the aspect of river and lake health management, it is important to clean out the floating objects in time, which prevents water pollution caused by the accumulation of the floating objects. The early methods of water surface object detection, such as background subtraction and frame difference, are greatly affected by the change of object shape and background, resulting in poor robustness. Therefore, we propose a real-time detection method of surface floating objects based on improved RefineDet model, which includes three modules: the anchor refinement module, the transfer connection block and the object detection module. We improve anchor refinement module by adding convolution layers to obtain higher-level semantic, and fuse high-level features with low-level features to improve detection accuracy. Moreover, we adjust the parameters setting of anchors according to the scale and aspect ratio distribution to match the multi-scale object better. Aiming at the foreground-background class imbalance caused by dense anchors sampling, we introduce focal loss function to solve it and make our model more efficient by adjusting the parameters of the function. We verify the performance of the proposed method on different floating object datasets we constructed. The detection accuracies on these different datasets are 83.8%, 88.0%, and 82.3% respectively, and the detection speed is 28 FPS. This shows that the improved RefineDet realizes high-precision and real-time detection.


  • Open Access

    Optical Prior‐Based Underwater Object Detection with Active Imaging

    by Jie Shen, Zhenxin Xu, Zhe Chen, Huibin Wang, Xiaotao Shi

    Underwater object detection plays an important role in research and practice, as it provides condensed and informative content that represents underwater objects. However, detecting objects from underwater images is challenging because underwater environments significantly degenerate image quality and distort the contrast between the object and background. To address this problem, this paper proposes an optical prior‐based underwater object detection approach that takes advantage of optical principles to identify optical collimation over underwater images, providing valuable guidance for extracting object features. Unlike data‐driven knowledge, the prior in our method is independent of training samples. The fundamental novelty of our approach lies in the integration of an image prior and the object detection task. This novelty is fundamental to the satisfying performance of our approach in underwater environments, which is demonstrated through comparisons with state‐of‐the‐art object detection methods.


  • Open Access

    A Ring-Based Routing Scheme for Distributed Energy Resources Management in IIoT

    by Zhiwen Xiong, Huibin Wang, Lili Zhang, Tanghuai Fan, Jie Shen

    Recently, Distributed Energy Resources (DERs) have been utilized with increasing frequency in Industrial Internet of Things (IIoT) to deal with energy and environmental challenges. IIoT with wireless communication technology, which is easy to be intercepted, often facing various attack. For the safety of the network, more complex algorithms need to be run on IIoT, but the action need more energy. In addition, in some application scenarios, the location where the packets were generated indicates that an event occurred. An attacker can find the sensor node through a backtracking attack, which is equivalent to reaching the place where the event occurred. In order to hide the location information of the event, it is necessary to protect source location privacy (SLP), which will also increase the energy consumption of IIoT. If only the traditional battery is used to power the nodes in IIoT, the lifetime of the system will be limited. When IIoT is deployed outdoors, it is often difficult to replace the battery. The existence of lakes make IIoT have coverage holes during deployment. In order to implement SLP and make the system work for a long time in the environment with deployment holes, we use DERs. Herein, we propose an SLP protection scheme based on phantom nodes, rings, and fake paths (PRFs) for IIoT. To increase the safety time of the network, the PRFs dynamically selects the phantom nodes. To adapt to a complex deployment environment, the ring can be flexibly deployed according to the terrain. The PRFs uses fake paths to confuse attackers. We integrate DERs technology into PRFs, such as using solar power modules, looking forward to extending the lifetime of the system.The experimental results proved that the PRFs could efficiently reduce backtracking attacks while maintaining a balance between security and network energy consumption of IIoT.


  • Open Access

    Superresolution Reconstruction of Video Based on Efficient Subpixel Convolutional Neural Network for Urban Computing

    by Jie Shen, Mengxi Xu, Xinyu Du, Yunbo Xiong

    Video surveillance is an important data source of urban computing and intelligence. The low resolution of many existing video surveillance devices affects the efficiency of urban computing and intelligence. Therefore, improving the resolution of video surveillance is one of the important tasks of urban computing and intelligence. In this paper, the resolution of video is improved by superresolution reconstruction based on a learning method. Different from the superresolution reconstruction of static images, the superresolution reconstruction of video is characterized by the application of motion information. However, there are few studies in this area so far. Aimed at fully exploring motion information to improve the superresolution of video, this paper proposes a superresolution reconstruction method based on an efficient subpixel convolutional neural network, where the optical flow is introduced in the deep learning network. Fusing the optical flow features between successive frames can compensate for information in frames and generate high-quality superresolution results. In addition, in order to improve the superresolution, a superpixel convolution layer is added after the deep convolution network. Finally, experimental evaluations demonstrate the satisfying performance of our method compared with previous methods and other deep learning networks; our method is more efficient.