Authentication email has already been sent, please check your email box: and activate it as soon as possible.
You can login to My Profile and manage your email alerts.
If you haven’t received the email, please:
|
|
There are 84 papers published in subject: since this site started. |
Select Subject |
Select/Unselect all | For Selected Papers |
Saved Papers
Please enter a name for this paper to be shown in your personalized Saved Papers list
|
1. YoloDepth: Yolo with Monocular Depth Estimation for Object Distance Measurement | |||
Chen Fei-Yang,Jiao Ji-Chao | |||
Computer Science and Technology 13 February 2023 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Environmental perception system is an important part of autonomous driving. A high-precision, real-time perception system can help the vehicles make feasible decisions and reasonable plans for the next step while driving. We propose a multi-task environmental perception network (YoloDepth) that can simultaneously perform traffic object detection and distance measurement. It consists of an encoder for feature extraction and two decoders for specific tasks. Our model performs excellently on COCO 2017 object detection dataset and KITTI monocular depth estimation dataset, achieving state-of-the-art speed and accuracy, and can process both visual perception tasks simultaneously on the embedded device Jeston AGX Xavier (18.3 FPS) in real-time and maintain great accuracy. | |||
TO cite this article:Chen Fei-Yang,Jiao Ji-Chao. YoloDepth: Yolo with Monocular Depth Estimation for Object Distance Measurement[OL].[13 February 2023] http://en.paper.edu.cn/en_releasepaper/content/4759099 |
2. Design and Implementation of Handwritten Chinese Characters Recognition Based on Deep Learning | |||
Jingyi Shen | |||
Computer Science and Technology 24 March 2022 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Nowadays, people are increasingly using electronic formats to store data. In order to convert the table in paper into digital information, this project implements a handwritten Chinese character recognition system for table pictures, which releases the pressure of manual workload of typing handwritten Chinese character information. This project pre-processes the scanned images, extracts the handwritten text information from the images . Then segment the cell in the table and cuts the individual Chinese characters. In order to improve the accuracy of character cutting, this project adopts the combination of vertical projection and aspect ratio of character to determine the cutting position. The ResNext50 model is used for model training, and the two models are trained to recognize numbers, letters and handwritten Chinese characters respectively. The accuracy of the Chinese character recognition model is more than 90%, and that of the number and letter recognition model is 98%. Based on the contents filled in the table, the list of proper nouns is used to correct the recognition results and improve the accuracy. By calculating Levenshtein distance find the specific nouns with the highest similarity. The method proposed in this paper effectively complete the separation and recognition of handwritten Chinese characters in the table image. | |||
TO cite this article:Jingyi Shen. Design and Implementation of Handwritten Chinese Characters Recognition Based on Deep Learning[OL].[24 March 2022] http://en.paper.edu.cn/en_releasepaper/content/4756976 |
3. Compressive Hyperspectral Video Reconstruction Via Multitask Nonparametric Bayesian Learning | |||
Yang Man,Gao Zhanchun | |||
Computer Science and Technology 09 February 2022 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Compressive hyperspectral video reconstruction (CHVR) extends snapshot spectral imaging into the temporal dimension, which allows fast hyerspectral observation of dynamic scenes. This paper proposes a multitask learning method for CHVR under the blind compressive sensing framework, characterized by joint inference of the representation atoms and the corresponding coefficients, directly from the compressive measurements. Defining the compressive reconstruction of each frame as a single task, our method employs a common dictionary shared by all tasks, which significantly alleviates the data paucity problem. The complete inference process is fulfilled via a Bayesian nonparametric estimation strategy, which contributes three advantages: reliable generalizability, parameter-tuning free and automatic determination of the model complexity. Simulation results demonstrate the efficacy of the proposed approach. | |||
TO cite this article:Yang Man,Gao Zhanchun. Compressive Hyperspectral Video Reconstruction Via Multitask Nonparametric Bayesian Learning[OL].[ 9 February 2022] http://en.paper.edu.cn/en_releasepaper/content/4756225 |
4. SOFT-AlignUNet: A Lightweight Transformer with Feature Alignment | |||
WU Rui-Jia,ZHANG Hong-Gang | |||
Computer Science and Technology 04 January 2022 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Transformer, the prevalent backbone architecture in natural language processing, has been adopted in various vision tasks since the proposition of vision transformer. The performance of transformer has been proved to be almost the same as CNN's and even be better with large enough dataset. However, the initial vision transformer suffered from the straightforward structure, which requires large parameters and expensive computation cost, especially in the dense prediction task. This paper concentrates on medical image semantic segmentation task. In medical scene, UNet is always the popular backbone and many researchers proposed transformer-CNN or pure transformer UNet model recently. But the inherent feature misalignment caused by resizing feature maps and concatenation is still lack of focus. In this paper, a lightweight transformer-CNN hybrid UNet, SOFT-AlignUNet (SOFT-AU) , is proposed to solve above issues. On one hand, a novel softmax-free transformer, which reduces the calculation cost to be linear to the patch number, is introduced into UNet architecture to alleviate the computation cost at a large extent. On the other hand, the feature misalignment is taken into consideration and a river-like Feature Alignment Flow is proposed to generate spatial deviation and correct the features. The architecture achieves strongly competitive results on public Synapse and DRIVE dataset with pretty light model size and computation requirement. The results show that this is a pretty promising network for future deployment in reality. | |||
TO cite this article:WU Rui-Jia,ZHANG Hong-Gang. SOFT-AlignUNet: A Lightweight Transformer with Feature Alignment[OL].[ 4 January 2022] http://en.paper.edu.cn/en_releasepaper/content/4755984 |
5. Load-Aware Transmission Mechanism for NVMeoF Storage Networks | |||
Qiao Xinghan,Xie Xuchao,Xiao Liquan | |||
Computer Science and Technology 21 October 2021 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:NVMe over TCP is a key technology for building large-scale high-performance storage systems.It can realize NVMeoF (NVMe over Fabrics) storage network based on the existing data center network infrastructure and standard TCP/IP software protocol stack. This article designs and implements the Load-Aware NVMeoF message processing mechanism LANoT (Load-Aware NVMe over TCP). Firstly, the interrupt merging technology based on aggregated PDU is used to alleviate the interrupt storm problem and achieve high throughput. Secondly, matching the special message processing mechanism, which can effectively improve its key performance indicators for applications according to the I/O characteristics of different dedicated queues . This paper implements the LANoT prototype system in the Linux kernel. The performance test results show that compared to the NVMe over TCP implementation in the standard Linux kernel, LANoT can reduce CPU resource consumption by more than 50% and increase IOPS by more than twice. | |||
TO cite this article:Qiao Xinghan,Xie Xuchao,Xiao Liquan. Load-Aware Transmission Mechanism for NVMeoF Storage Networks[OL].[21 October 2021] http://en.paper.edu.cn/en_releasepaper/content/4755658 |
6. Grammar-based Fuzz Testing for Microprocessor RTL Design | |||
LUO Dan,LI Tun,CHEN Liqian,ZOU Hongji,SHI Mingchuan | |||
Computer Science and Technology 24 September 2021 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:The emergence of hardware construction languages (HCLs), such as PyRTL, PyHDL, and PyMTL, for microprocessor RTL design in agile hardware design methodology brings new challenges to design verification. However, most of the existing dynamic verification techniques for microprocessor RTL designs in HCLs are lacking sufficient consideration of constraints of valid instructions in a given instruction-set architecture (ISA). In contrast, such constraints are pervasive in microprocessor RTL design. This may degrade coverage achievements and the efficiency of the verification process. In this paper, we propose to enhance the coverage-directed dynamic verification method for microprocessor RTL design in several aspects. First, we combine grammar-based fuzz testing and symbolic simulation to generate test instructions for improving coverage. Second, we propose to employ a grammar-based fuzz testing technique by exploiting constraints of valid ISA instructions of a microprocessor under verification. Finally, we implement all the enhancements in a test generation tool, named MPFuzz, for testing microprocessor RTL designs in PyRTL. Experimental results show that MPFuzz can efficiently generate test instructions for microprocessor RTL designs in PyRTL. The test instructions generated by MPFuzz can achieve higher coverage at least four times than that by the state-of-the-art fuzzing-based RTL test generation tool. | |||
TO cite this article:LUO Dan,LI Tun,CHEN Liqian, et al. Grammar-based Fuzz Testing for Microprocessor RTL Design[OL].[24 September 2021] http://en.paper.edu.cn/en_releasepaper/content/4755578 |
7. A generality enhanced forensic towards GAN facial images | |||
Xiong Xiao-Fang,Yang Gao-Bo | |||
Computer Science and Technology 13 May 2020 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:\justifying Recent advances in GAN technique have made it much easier than ever to generate believable face images, which brings some potential security issues to the public. Currently a variety of architectures have been proposed to detect these generated fake images, but few works address the problem of generalization ability of forensics models, which means most of them need prior knowledge of the structure of GAN model when detecting a specific GAN fake face images, and unable to detect unseen fake images generated by other GAN models. In this work, we tackle the generality enhanced problem by adding a fixed weight convolutional layer before CNN structure, which contain three designed high-pass filters. Firstly, we convert RGB images to YCbCr color space to get more obvious edge information. Then, EfficientNet is adopted as our basic CNN structure to extract inhenrent features and classify them. Finally, a fixed weight layer is added to the first convolutional layer, which could greatly suppress the semantic image content and magnify microscopic characteristics of images, thus help to enhance the generalization ability of the model. A series of experiments demonstrate that our approach achieve superior performance compare with the state-of-the-art work in terms of the generality of forensics model. | |||
TO cite this article:Xiong Xiao-Fang,Yang Gao-Bo. A generality enhanced forensic towards GAN facial images[OL].[13 May 2020] http://en.paper.edu.cn/en_releasepaper/content/4752048 |
8. Super-resolution Reconstruction of Mosaic Face Images Based on GAN | |||
Xu Yonghui,Yang Gaobo | |||
Computer Science and Technology 11 May 2020 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:With the rapid development of artificial intelligence technologies, image super-resolution which is one of the hottest topics in computer vision community, has achieved attractive progresses. To restore mosaic face images, we present an effective model, namely DemosaicGAN. It combines existing SRGAN and RDN and optimizes the perceptual loss functions. As far as we concerned, our experimental results show that the proposed DemosaicGAN achieves the best results in super-resolution reconstruction of mosaic face images so far. | |||
TO cite this article:Xu Yonghui,Yang Gaobo. Super-resolution Reconstruction of Mosaic Face Images Based on GAN[OL].[11 May 2020] http://en.paper.edu.cn/en_releasepaper/content/4752050 |
9. Class-balanced and Local Median Loss Jointly Supervised for Wild Facial Expression Recognition | |||
Shi Cong-Cong,TIAN,TIAN Mei | |||
Computer Science and Technology 07 February 2020 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Over the past few years, Convolutional Neural Networks (CNNs) have shown effective performance on facial expression recognition. However, it is still a challenge problem for facial expression in the wild. The facial expression recognition dataset in the wild usually has the problem that imbalanced distribution of facial expression data and large intra-class differences caused by factors such as pose, lighting and gender. In order to solve this problem, this paper presents a novel loss function -- CALM Loss (Class-balanced and Local Median Loss). CALM Loss contains two parts. The first part is the class-balanced softmax loss function, which is uesd to solve the problem of data imbalance. The data set is divided into two classes, with two expressions with less data as one class and the other five as one class. During the network training process, the weight of the class with less data is adaptively increased. The second part is the local median loss function, which uses the median of serveral neatest neighbors in the same class as the center of class, weakens the influence of difficult samples on the selection of class center. Finally, the CALM Loss training network was adopted in this paper. The average recognition accuracy on the RAF dataset reaches 77.34$\%$, which proves the effectiveness of the proposed method. | |||
TO cite this article:Shi Cong-Cong,TIAN,TIAN Mei. Class-balanced and Local Median Loss Jointly Supervised for Wild Facial Expression Recognition[OL].[ 7 February 2020] http://en.paper.edu.cn/en_releasepaper/content/4750634 |
10. A Telecom Anti-Fraud Approach Based on Graph | |||
Li Zhengzheng,Wang Chun | |||
Computer Science and Technology 05 February 2020 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Currently, telecommunications fraud is on the rise. Traditional anti-fraud techniques are basically unable to capture various new telecommunication fraud methods. After studying the case of fraud, we proposes a telecom fraud detection method based on graph embedding, which is used to mine the potential features of the call correlation graph between fraudsters and users. First, the proposed approach is based on the embedding of attribute network, which not only saves the network structure information, but also incorporates the statistical features of the nodes extracted for the call behavior, in order to represent the nodes as low-dimensional vectors. Secondly, the proposed approach belongs to semi-supervised learning. In the supervised part, the corresponding labels are predicted. In the unsupervised part, the node context vector is predicted. Both share parameters and optimize the model at the same time. When experimenting on the telecommunications fraud dataset, compared with other baseline approaches., the experimental results prove the effectiveness of the proposed method in countering telecommunications fraud. | |||
TO cite this article:Li Zhengzheng,Wang Chun. A Telecom Anti-Fraud Approach Based on Graph[OL].[ 5 February 2020] http://en.paper.edu.cn/en_releasepaper/content/4750616 |
Select/Unselect all | For Selected Papers |
Saved Papers
Please enter a name for this paper to be shown in your personalized Saved Papers list
|
|
About Sciencepaper Online | Privacy Policy | Terms & Conditions | Contact Us
© 2003-2012 Sciencepaper Online. unless otherwise stated