Resource Type

Journal Article 765

Conference Videos 27

Conference Information 22

Year

2024 1

2023 87

2022 113

2021 107

2020 85

2019 77

2018 55

2017 68

2016 50

2015 19

2014 5

2013 4

2012 7

2011 7

2010 4

2009 7

2008 16

2007 20

2006 15

2005 15

open ︾

Keywords

Machine learning 42

Deep learning 34

Artificial intelligence 21

neural network 16

Reinforcement learning 14

Neural network 8

Software-defined networking (SDN) 7

cyberspace 5

cyberspace security 5

6G 4

Active learning 4

ANN 3

Attention mechanism 3

Autonomous driving 3

Game theory 3

Multi-agent system 3

Network security 3

fuzzy sets 3

5G 2

open ︾

Search scope:

排序： Display mode:

Aggregated context network for crowd counting

Si-yue Yu, Jian Pu,51174500148@stu.ecnu.edu.cn,jianpu@fudan.edu.cn

Frontiers of Information Technology & Electronic Engineering 2020, Volume 21, Issue 11,   Pages 1535-1670 doi: 10.1631/FITEE.1900481

Abstract: has been applied to a variety of applications such as video surveillance, traffic monitoring, assembly control, and other public safety applications. Context information, such as perspective distortion and background interference, is a crucial factor in achieving high performance for . While traditional methods focus merely on solving one specific factor, we aggregate sufficient context information into the network to tackle these problems simultaneously in this study. We build a fully convolutional network with two tasks, i.e., main density map estimation and auxiliary . The main task is to extract the multi-scale and spatial context information to learn the density map. The auxiliary task gives a comprehensive view of the background and foreground information, and the extracted information is finally incorporated into the main task by late fusion. We demonstrate that our network has better accuracy of estimation and higher robustness on three challenging datasets compared with state-of-the-art methods.

Keywords： 人群计数；卷积神经网络；密度估计；语义分割；多任务学习    

HTML PDF Collect

A novel convolutional neural network method for crowd counting Research Articles

Jie-hao Huang, Xiao-guang Di, Jun-de Wu, Ai-yue Chen,18s004055@hit.edu.cn,dixiaoguang@hit.edu.cn

Frontiers of Information Technology & Electronic Engineering 2020, Volume 21, Issue 8,   Pages 1119-1266 doi: 10.1631/FITEE.1900282

Abstract: Crowd , in general, is a challenging task due to the large variation of head sizes in the crowds. Existing methods always use a multi-column convolutional neural network (MCNN) to adapt to this variation, which results in an average effect in areas with different densities and brings a lot of noise to the density map. To address this problem, we propose a new method called the segmentation-aware prior network (SAPNet), which generates a high-quality density map without noise based on a coarse head-segmentation map. SAPNet is composed of two networks, i.e., a foreground-segmentation convolutional neural network (FS-CNN) as the front end and a crowd-regression convolutional neural network (CR-CNN) as the back end. With only the single dot annotation, we generate the ground truth of segmentation masks in heads. Then, based on the ground truth, FS-CNN outputs a coarse head-segmentation map, which helps eliminate the noise in regions without people in the density map. By inputting the head-segmentation map generated by the front end, CR-CNN performs accurate estimation and generates a high-quality density map. We demonstrate SAPNet on four datasets (i.e., ShanghaiTech, UCF-CC-50, WorldExpo’10, and UCSD), and show the state-of-the-art performances on ShanghaiTech part and UCF-CC-50 datasets.

Keywords： Crowd counting     Density estimation     Segmentation prior map     Uniform function    

HTML PDF Collect

Estimating Rainfall Intensity Using an Image-Based Deep Learning Model Article

Hang Yin, Feifei Zheng, Huan-Feng Duan, Dragan Savic, Zoran Kapelan

Engineering 2023, Volume 21, Issue 2,   Pages 162-174 doi: 10.1016/j.eng.2021.11.021

Abstract:

Urban flooding is a major issue worldwide, causing huge economic losses and serious threats to public safety. One promising way to mitigate its impacts is to develop a real-time flood risk management system; however, building such a system is often challenging due to the lack of high spatiotemporal rainfall data. While some approaches (i.e., ground rainfall stations or radar and satellite techniques) are available to measure and/or predict rainfall intensity, it is difficult to obtain accurate rainfall data with a desirable spatiotemporal resolution using these methods. This paper proposes an image-based deep learning model to estimate urban rainfall intensity with high spatial and temporal resolution. More specifically, a convolutional neural network (CNN) model called the image-based rainfall CNN (irCNN) model is developed using rainfall images collected from existing dense sensors (i.e., smart phones or transportation cameras) and their corresponding measured rainfall intensity values. The trained irCNN model is subsequently employed to efficiently estimate rainfall intensity based on the sensors' rainfall images. Synthetic rainfall data and real rainfall images are respectively utilized to explore the irCNN's accuracy in theoretically and practically simulating rainfall intensity. The results show that the irCNN model provides rainfall estimates with a mean absolute percentage error ranging between 13.5% and 21.9%, which exceeds the performance of other state-of-the-art modeling techniques in the literature. More importantly, the main feature of the proposed irCNN is its low cost in efficiently acquiring high spatiotemporal urban rainfall data. The irCNN model provides a promising alternative for estimating urban rainfall intensity, which can greatly facilitate the development of urban flood risk management in a real-time manner.

Keywords： Urban flooding     Rainfall images     Deep learning model     Convolutional neural networks (CNNs)     Rainfall intensity    

HTML PDF Collect

Processing and analysis of data from microwave humidity sounder onboard FY-3A satellite

He Jieying,Zhang Shengwei

Strategic Study of CAE 2013, Volume 15, Issue 10,   Pages 47-53

Abstract:

Microwave humidity sounder (MWHS) is one of payloads on the Fengyun-3A (FY-3A) satellite. This paper introduces its structure, operation status and data receiving and processing. The paper constructs an inversion model using artificial neural network (ANN) algorithm, and makes comparison with advanced microwave sounding unit advanced microwave sounding unit-B(AMSU-B). The results demonstrate that the model can be operated successfully. Using the simulated brightness temperatures from MWHS from July to December in 2008 in Beijing, the paper derives water vapor density profiles and gives analysis of root mean square. Meanwhile, the paper focuses on brightness temperature values of different scanning lines when the typhoon comes. The paper demonstrates that FY-3A satellite MWHS can retrieve the water vapor density profiles, cloud liquid water and other related information. Also, in the process of monitoring the tropical typhoon and cyclone and judging the trend of them, FY-3A satellite MWHS also plays a very important role.

Keywords： MWHS     FY-3A     ANN     water vapor density    

HTML PDF Collect

Deep 3D reconstruction: methods, data, and challenges Review Article

Caixia Liu, Dehui Kong, Shaofan Wang, Zhiyong Wang, Jinghua Li, Baocai Yin,lcxxib@emails.bjut.edu.cn,wangshaofan@bjut.edu.cn

Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 5,   Pages 615-766 doi: 10.1631/FITEE.2000068

Abstract: Three-dimensional (3D) reconstruction of shapes is an important research topic in the fields of computer vision, computer graphics, pattern recognition, and virtual reality. Existing 3D reconstruction methods usually suffer from two bottlenecks: (1) they involve multiple manually designed states which can lead to cumulative errors, but can hardly learn semantic features of 3D shapes automatically; (2) they depend heavily on the content and quality of images, as well as precisely calibrated cameras. As a result, it is difficult to improve the reconstruction accuracy of those methods. 3D reconstruction methods based on deep learning overcome both of these bottlenecks by automatically learning semantic features of 3D shapes from low-quality images using deep networks. However, while these methods have various architectures, in-depth analysis and comparisons of them are unavailable so far. We present a comprehensive survey of 3D reconstruction methods based on deep learning. First, based on different deep learning model architectures, we divide 3D reconstruction methods based on deep learning into four types, , , , and based methods, and analyze the corresponding methodologies carefully. Second, we investigate four representative databases that are commonly used by the above methods in detail. Third, we give a comprehensive comparison of 3D reconstruction methods based on deep learning, which consists of the results of different methods with respect to the same database, the results of each method with respect to different databases, and the robustness of each method with respect to the number of views. Finally, we discuss future development of 3D reconstruction methods based on deep learning.

Keywords： 深度学习模型；三维重建；循环神经网络；深度自编码器；生成对抗网络；卷积神经网络    

HTML PDF Collect

Marine target detection based on Marine-Faster R-CNN for navigation radar plane position indicator images Research Article

Xiaolong CHEN, Xiaoqian MU, Jian GUAN, Ningbo LIU, Wei ZHOU,cxlcxl1209@163.com,guanjian_68@163.com

Frontiers of Information Technology & Electronic Engineering 2022, Volume 23, Issue 4,   Pages 630-643 doi: 10.1631/FITEE.2000611

Abstract: As a classic deep learning target detection algorithm, Faster R-CNN (region convolutional neural network) has been widely used in high-resolution synthetic aperture radar (SAR) and inverse SAR (ISAR) image detection. However, for most common low-resolution radar , it is difficult to achieve good performance. In this paper, taking PPI images as an example, a method based on the Marine-Faster R-CNN algorithm is proposed in the case of complex background (e.‍g., sea clutter) and target characteristics. The method performs feature extraction and target recognition on PPI images generated by radar echoes with the . First, to improve the accuracy of detecting marine targets and reduce the false alarm rate, Faster R-CNN was optimized as the Marine-Faster R-CNN in five respects: new backbone network, anchor size, dense target detection, data sample balance, and scale normalization. Then, JRC (Japan Radio Co., Ltd.) was used to collect echo data under different conditions to build a marine target dataset. Finally, comparisons with the classic Faster R-CNN method and the constant false alarm rate (CFAR) algorithm proved that the proposed method is more accurate and robust, has stronger generalization ability, and can be applied to the detection of marine targets for . Its performance was tested with datasets from different observation conditions (sea states, radar parameters, and different targets).

Keywords： Marine target detection     Navigation radar     Plane position indicator (PPI) images     Convolutional neural network (CNN)     Faster R-CNN (region convolutional neural network) method    

HTML PDF Collect

Two-level hierarchical feature learning for image classification Article

Guang-hui SONG,Xiao-gang JIN,Gen-lang CHEN,Yan NIE

Frontiers of Information Technology & Electronic Engineering 2016, Volume 17, Issue 9,   Pages 897-906 doi: 10.1631/FITEE.1500346

Abstract: In some image classification tasks, similarities among different categories are different and the samples are usually misclassified as highly similar categories. To distinguish highly similar categories, more specific features are required so that the classifier can improve the classification performance. In this paper, we propose a novel two-level hierarchical feature learning framework based on the deep convolutional neural network (CNN), which is simple and effective. First, the deep feature extractors of different levels are trained using the transfer learning method that fine-tunes the pre-trained deep CNN model toward the new target dataset. Second, the general feature extracted from all the categories and the specific feature extracted from highly similar categories are fused into a feature vector. Then the final feature representation is fed into a linear classifier. Finally, experiments using the Caltech-256, Oxford Flower-102, and Tasmania Coral Point Count (CPC) datasets demonstrate that the expression ability of the deep features resulting from two-level hierarchical feature learning is powerful. Our proposed method effectively increases the classification accuracy in comparison with flat multiple classification methods.

Keywords： Transfer learning     Feature learning     Deep convolutional neural network     Hierarchical classification     Spectral clustering    

HTML PDF Collect

Binary neural networks for speech recognition Regular Papers

Yan-min QIAN, Xu XIANG

Frontiers of Information Technology & Electronic Engineering 2019, Volume 20, Issue 5,   Pages 701-715 doi: 10.1631/FITEE.1800469

Abstract:

Recently, deep neural networks (DNNs) significantly outperform Gaussian mixture models in acoustic modeling for speech recognition. However, the substantial increase in computational load during the inference stage makes deep models difficult to directly deploy on low-power embedded devices. To alleviate this issue, structure sparseness and low precision fixed-point quantization have been applied widely. In this work, binary neural networks for speech recognition are developed to reduce the computational cost during the inference stage. A fast implementation of binary matrix multiplication is introduced. On modern central processing unit (CPU) and graphics processing unit (GPU) architectures, a 5–7 times speedup compared with full precision floatingpoint matrix multiplication can be achieved in real applications. Several kinds of binary neural networks and related model optimization algorithms are developed for large vocabulary continuous speech recognition acoustic modeling. In addition, to improve the accuracy of binary models, knowledge distillation from the normal full precision floating-point model to the compressed binary model is explored. Experiments on the standard Switchboard speech recognition task show that the proposed binary neural networks can deliver 3–4 times speedup over the normal full precision deep models. With the knowledge distillation from the normal floating-point models, the binary DNNs or binary convolutional neural networks (CNNs) can restrict the word error rate (WER) degradation to within 15.0%, compared to the normal full precision floating-point DNNs or CNNs, respectively. Particularly for the binary CNN with binarization only on the convolutional layers, the WER degradation is very small and is almost negligible with the proposed approach.

Keywords： Speech recognition     Binary neural networks     Binary matrix multiplication     Knowledge distillation     Population count    

HTML PDF Collect

Diffractive Deep Neural Networks at Visible Wavelengths Article

Hang Chen, Jianan Feng, Minwei Jiang, Yiqun Wang, Jie Lin, Jiubin Tan, Peng Jin

Engineering 2021, Volume 7, Issue 10,   Pages 1485-1493 doi: 10.1016/j.eng.2020.07.032

Abstract:

Optical deep learning based on diffractive optical elements offers unique advantages for parallel processing, computational speed, and power efficiency. One landmark method is the diffractive deep neural network (D2NN) based on three-dimensional printing technology operated in the terahertz spectral range. Since the terahertz bandwidth involves limited interparticle coupling and material losses, this paper
extends D2NN to visible wavelengths. A general theory including a revised formula is proposed to solve any contradictions between wavelength, neuron size, and fabrication limitations. A novel visible light D2NN classifier is used to recognize unchanged targets (handwritten digits ranging from 0 to 9) and targets that have been changed (i.e., targets that have been covered or altered) at a visible wavelength of 632.8 nm. The obtained experimental classification accuracy (84%) and numerical classification accuracy (91.57%) quantify the match between the theoretical design and fabricated system performance. The presented framework can be used to apply a D2NN to various practical applications and design other new applications.

Keywords： Optical computation     Optical neural networks     Deep learning     Optical machine learning     Diffractive deep neural networks    

HTML PDF Collect

Shot classification and replay detection for sports video summarization Research Article

Ali JAVED, Amen ALI KHAN,ali.javed@uettaxila.edu.pk

Frontiers of Information Technology & Electronic Engineering 2022, Volume 23, Issue 5,   Pages 790-800 doi: 10.1631/FITEE.2000414

Abstract: Automated analysis of sports is challenging due to variations in cameras, replay speed, illumination conditions, editing effects, game structure, genre, etc. To address these challenges, we propose an effective framework based on and for field sports videos. Accurate is mandatory to better structure the input video for further processing, i.e., key events or . Therefore, we present a based method for . Then we analyze each shot for and specifically detect the successive batch of logo transition frames that identify the replay segments from the sports videos. For this purpose, we propose local octa-pattern features to represent video frames and train the for classification as replay or non-replay frames. The proposed framework is robust to variations in cameras, replay speed, shot speed, illumination conditions, game structure, sports genre, broadcasters, logo designs and placement, frame transitions, and editing effects. The performance of our framework is evaluated on a dataset containing diverse YouTube sports videos of soccer, baseball, and cricket. Experimental results demonstrate that the proposed framework can reliably be used for and to summarize field sports videos.

Keywords： Extreme learning machine     Lightweight convolutional neural network     Local octa-patterns     Shot classification     Replay detection     Video summarization    

HTML PDF Collect

A novel method based on convolutional neural networks for deriving standard 12-lead ECG from serial 3-lead ECG Regular Papers

Lu-di WANG, Wei ZHOU, Ying XING, Na LIU, Mahmood MOVAHEDIPOUR, Xiao-guang ZHOU

Frontiers of Information Technology & Electronic Engineering 2019, Volume 20, Issue 3,   Pages 405-413 doi: 10.1631/FITEE.1700413

Abstract:

Reconstruction of a 12-lead electrocardiogram (ECG) from a serial 3-lead ECG has been researched in the past to satisfy the need for more wearing comfort and ambulatory situations. The accuracy and real-time performance of traditional methods need to be improved. In this study, we present a novel method based on convolutional neural networks (CNNs) for the synthesis of missing precordial leads. The results show that the proposed method receives better similarity and consumes less time using the PTB database. Particularly, the presented method shows outstanding performance in reconstructing the pathological ECG signal, which is crucial for cardiac diagnosis. Our CNN-based method is shown to be more accurate and time-saving for deployment in non-hospital situations to synthesize a standard 12-lead ECG from a reduced lead-set ECG recording. This is promising for real cardiac care.

Keywords： Convolutional neural networks (CNNs)     Electrocardiogram (ECG) synthesis     E-health    

HTML PDF Collect

Learning and Applications of Procedure Neural Networks

He Xingui,Liang Jiuzhen,Xu Shaohua

Strategic Study of CAE 2001, Volume 3, Issue 4,   Pages 31-35

Abstract:

This paper deals with learning algorithms for procedure neural networks (PNN) and its applications in aggregation chemical reaction and seepage test in oil geology. Weight bases selection rules and pattern curve standard problems are also discussed. These examples show that PNN have extensive applications.

Keywords： procedure neural networks     learning algorithm     pattern recognition     chemical reaction     seepage    

HTML PDF Collect

Recent advances in efficient computation of deep convolutional neural networks Review

Jian CHENG, Pei-song WANG, Gang LI, Qing-hao HU, Han-qing LU

Frontiers of Information Technology & Electronic Engineering 2018, Volume 19, Issue 1,   Pages 64-77 doi: 10.1631/FITEE.1700789

Abstract: Deep neural networks have evolved remarkably over the past few years and they are currently the fundamental tools of many intelligent systems. At the same time, the computational complexity and resource consumption of these networks continue to increase. This poses a significant challenge to the deployment of such networks, especially in real-time applications or on resource-limited devices. Thus, network acceleration has become a hot topic within the deep learning community. As for hardware implementation of deep neural networks, a batch of accelerators based on a field-programmable gate array (FPGA) or an application-specific integrated circuit (ASIC) have been proposed in recent years. In this paper, we provide a comprehensive survey of recent advances in network acceleration, compression, and accelerator design from both algorithm and hardware points of view. Specifically, we provide a thorough analysis of each of the following topics: network pruning, low-rank approximation, network quantization, teacher–student networks, compact network design, and hardware accelerators. Finally, we introduce and discuss a few possible future directions.

Keywords： Deep neural networks     Acceleration     Compression     Hardware accelerator    

HTML PDF Collect

Associative affinity network learning for multi-object tracking Research Articles

Liang Ma, Qiaoyong Zhong, Yingying Zhang, Di Xie, Shiliang Pu,maliang6@hikvision.com,zhongqiaoyong@hikvision.com,zhangyingying7@hikvision.com,xiedi@hikvision.com,pushiliang.hri@hikvision.com

Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 9,   Pages 1194-1206 doi: 10.1631/FITEE.2000272

Abstract: We propose a joint feature and metric learning architecture, called the associative affinity network (AAN), as an affinity model for (MOT) in videos. The AAN learns the associative affinity between tracks and detections across frames in an end-to-end manner. Considering flawed detections, the AAN jointly learns bounding box regression, classification, and affinity regression via the proposed multi-task loss. Contrary to networks that are trained with ranking loss, we directly train a binary classifier to learn the associative affinity of each track-detection pair and use a matching cardinality loss to capture information among candidate pairs. The AAN learns a discriminative affinity model for data association to tackle MOT, and can also perform single-object tracking. Based on the AAN, we propose a simple multi-object tracker that achieves competitive performance on the public MOT16 and MOT17 test datasets.

Keywords： 多目标跟踪；深度神经网络；相似度学习    

HTML PDF Collect

A Review of Recent Advances and Application for Spiking Neural Networks

Liu Hao , Chai Hongfeng , Sun Quan , Yun Xin , Li Xin

Strategic Study of CAE 2023, Volume 25, Issue 6,   Pages 61-79 doi: 10.15302/J-SSCAE-2023.06.011

Abstract:

Spiking neural network (SNN) is a new generation of artificial neural network. It is more biologically plausible and has been widely concerned by scholars owing to its unique information coding schemes, rich spatiotemporal dynamics, and event-driven operating mode with low power. In recent years, SNN has been explored and applied in many fields such as medical health, industrial detection, and intelligent driving. First, the basic elements and learning algorithms of SNN are introduced, including classical spiking neuron models, spike-timing dependent plasticity (STDP), and common information coding methods. The advantages and disadvantages of the learning algorithms are also analyzed. Then, the mainstream software simulators and neuromorphic hardware of SNN are  summarized. Subsequently, the research progress and application scenarios of SNN in terms of computer vision, natural language processing, and reasoning decision are introduced. Particularly, SNN has shown strong potentials in tasks such as object detection, action recognition, semantic cognition, and speech recognition, significantly improving computational performance. Future research and application of SNN should focus on strengthening the research on key core technologies, promoting the application of technological achievements, and continuously optimizing the industrial ecology, thus to catch up with the advanced international level. Moreover, continuous research and breakthroughs of brain-inspired systems and control theories will promote the establishment of large-scale SNN models and are expected to broaden the application prospect of artificial intelligence.

Keywords： spiking neural network     brain-inspired computing     learning algorithm     neuromorphic chip     application scenario    

HTML PDF Collect

Title Author Date Type Operation

Aggregated context network for crowd counting

Si-yue Yu, Jian Pu,51174500148@stu.ecnu.edu.cn,jianpu@fudan.edu.cn

Journal Article

A novel convolutional neural network method for crowd counting

Jie-hao Huang, Xiao-guang Di, Jun-de Wu, Ai-yue Chen,18s004055@hit.edu.cn,dixiaoguang@hit.edu.cn

Journal Article

Estimating Rainfall Intensity Using an Image-Based Deep Learning Model

Hang Yin, Feifei Zheng, Huan-Feng Duan, Dragan Savic, Zoran Kapelan

Journal Article

Processing and analysis of data from microwave humidity sounder onboard FY-3A satellite

He Jieying,Zhang Shengwei

Journal Article

Deep 3D reconstruction: methods, data, and challenges

Caixia Liu, Dehui Kong, Shaofan Wang, Zhiyong Wang, Jinghua Li, Baocai Yin,lcxxib@emails.bjut.edu.cn,wangshaofan@bjut.edu.cn

Journal Article

Marine target detection based on Marine-Faster R-CNN for navigation radar plane position indicator images

Xiaolong CHEN, Xiaoqian MU, Jian GUAN, Ningbo LIU, Wei ZHOU,cxlcxl1209@163.com,guanjian_68@163.com

Journal Article

Two-level hierarchical feature learning for image classification

Guang-hui SONG,Xiao-gang JIN,Gen-lang CHEN,Yan NIE

Journal Article

Binary neural networks for speech recognition

Yan-min QIAN, Xu XIANG

Journal Article

Diffractive Deep Neural Networks at Visible Wavelengths

Hang Chen, Jianan Feng, Minwei Jiang, Yiqun Wang, Jie Lin, Jiubin Tan, Peng Jin

Journal Article

Shot classification and replay detection for sports video summarization

Ali JAVED, Amen ALI KHAN,ali.javed@uettaxila.edu.pk

Journal Article

A novel method based on convolutional neural networks for deriving standard 12-lead ECG from serial 3-lead ECG

Lu-di WANG, Wei ZHOU, Ying XING, Na LIU, Mahmood MOVAHEDIPOUR, Xiao-guang ZHOU

Journal Article

Learning and Applications of Procedure Neural Networks

He Xingui,Liang Jiuzhen,Xu Shaohua

Journal Article

Recent advances in efficient computation of deep convolutional neural networks

Jian CHENG, Pei-song WANG, Gang LI, Qing-hao HU, Han-qing LU

Journal Article

Associative affinity network learning for multi-object tracking

Liang Ma, Qiaoyong Zhong, Yingying Zhang, Di Xie, Shiliang Pu,maliang6@hikvision.com,zhongqiaoyong@hikvision.com,zhangyingying7@hikvision.com,xiedi@hikvision.com,pushiliang.hri@hikvision.com

Journal Article

A Review of Recent Advances and Application for Spiking Neural Networks

Liu Hao , Chai Hongfeng , Sun Quan , Yun Xin , Li Xin

Journal Article