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 4 papers published in subject: > since this site started. |
Results per page: |
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. P-SANET: A HIGH-PRECISION REALTIME POINT CLOUD SEMANTIC SEGMENTATION FRAMEWORK | |||
GOU Xiaofeng,JIAO Jichao,ZHANG Chengkai | |||
Computer Science and Technology 10 January 2022 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Perception in autonomous system is an important task to guide decision execu-tion. Lidar point cloud is a type of dataset to complete perception task, it is rich in original information, easy to collect, and convenient to store. Compared to camera image, point cloud contains precise spatial information and adapts to various en-vironments, nevertheless, more information means more computing power con-sumption. The processing speed and accuracy are two key metrics of neural net-work framework. The traditional methods have to pay the price of reducing accu-racy for increasing processing speed. Though some frameworks preprocess point cloud into projected image, the 2D image tensor also contains a large number of redundant channel features in the traditional 2Dconvolution operation. In this pa-per, we propose a point clouds semantic segmentation framework, we replace the standard convolutional layer with a new sub-module, and it greatly reduces the amount of computation, besides, we introduce a sub-module to fuse the coordi-nate values and middle tensors. The framework in this paper is divided into three parts: spherical projection preprocessing module, En-Decoder module and data post-processing module. We use the SemanticKITTI dataset to conduct experi-ments, and the results show that our framework outperforms other frameworks both in prediction accuracy and prediction speed. We also use sparse point cloud dataset to test the generalization of our framework, and the experiments show that it performs better than other frameworks. Code is available at: https://github.com/windtries/P-SANet | |||
TO cite this article:GOU Xiaofeng,JIAO Jichao,ZHANG Chengkai. P-SANET: A HIGH-PRECISION REALTIME POINT CLOUD SEMANTIC SEGMENTATION FRAMEWORK[OL].[10 January 2022] http://en.paper.edu.cn/en_releasepaper/content/4755947 |
2. LCPN: Lightweight Single-Person Pose Estimation Based on Cascaded Pyramid Network | |||
Meng Ruoli,Fang Wei | |||
Computer Science and Technology 26 February 2021 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:he task of human pose estimation has been largely improved most recently. However, there are still a lot of challenges to apply it in practice, such as the limited network bandwidth, the privacy and security risks and so on. In this paper, we propose a lightweight human pose estimation model called LCPN, which takes depthwise separable convolution instead of standard convolution to lighten the network. Besides, we try to combine the heatmap prediction and coordinate regression in the keypoint prediction stage, which will further improve the efficiency of the network. The proposed approach achieves an excellent trade-off between speed and accuracy on the LSP and MPII datasets, and is very suitable to run on edge devices with lower computing power. | |||
TO cite this article:Meng Ruoli,Fang Wei. LCPN: Lightweight Single-Person Pose Estimation Based on Cascaded Pyramid Network[OL].[26 February 2021] http://en.paper.edu.cn/en_releasepaper/content/4753756 |
3. Anomaly Detection Based on Locality-preferred Recoding of GAN Network | |||
Wei Huang,WANG Jianzhu,DONG Bangyi,MENG Qinglong,SHI Chuan,LI Qingyong | |||
Computer Science and Technology 26 March 2020 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Deep neural networks, including deep auto-encoder (DAE) and generative adversarial networks (GAN), have been extensively applied for anomaly detection. These models generally assume that reconstruction errors should be lower for normal samples but higher for anomalies. However, it has been found that DAE based models can sometimes reconstruct anomalies very well and thus result in miss detection. To address this problem, we propose an anomaly detection model using GAN with locality-preferred recoding, named LRGAN. LRGAN is inspired by the observation that both normal and abnormal samples are not scattered throughout the latent space but clustered separately at some local regions. Therefore, a locality-preferred recoding (LR) module is designed to compulsively represent the latent vectors of anomalies by normal ones, making the reconstructions approach to normal samples and thereby enlarging the residuals. To partly avoid latent vectors of normal samples being recoded, we further put forward to detect anomalies using GAN with an adaptive LR ($ALR$), named LRGAN+. Our proposed method is evaluated on two public datasets (i.e., MNIST and CIFAR-10) and one Fasteners dataset from practical application, considering both one-class anomaly detection and multi-class anomaly detection scenarios. Experimental results demonstrate that LRGAN is comparable with state-of-the-art methods and LRGAN+ outperforms these methods on all datasets. | |||
TO cite this article:Wei Huang,WANG Jianzhu,DONG Bangyi, et al. Anomaly Detection Based on Locality-preferred Recoding of GAN Network[OL].[26 March 2020] http://en.paper.edu.cn/en_releasepaper/content/4751373 |
4. MFPNet:Multi Frame Propagation Network For Video Instance-level Human Parsing | |||
Zhou Du,Li Wei | |||
Computer Science and Technology 14 January 2020 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Video instance-level human parsing can easily implement functions such as background replacement, adding decorations and scaling human part. In this paper, the spatial features from the current frame and the temporal features from the previous k frames are unified into a network, and a Multi Frame Propagation Net (MFPNet) is proposed to solve this task. The main contributions are shown below. First, we propose two blocks Position-Squeeze-and-Excitation (P-SE) and Global Attention Module (GAM). P-SE applies the idea of Squeeze-and-Excitation (SE) to spatial locations. It can learn a spatial attention map, which represent the correlation degree of body parts. GAM is a combination of SE and P-SE, which can extract global structured features. Second, a propagation module is proposed to obtain the temporal features between video frames. This module consists of 3D convolution and Convolutional Gated Recurrent Unit (ConvGRU). 3D convolution can better obtain the spatiotemporal features between consecutive frames, and ConvGRU further obtains the temporal features. Third, MFPNet has achieved the state of the art in the Video Instance-level Parsing (VIP) dataset. | |||
TO cite this article:Zhou Du,Li Wei. MFPNet:Multi Frame Propagation Network For Video Instance-level Human Parsing[OL].[14 January 2020] http://en.paper.edu.cn/en_releasepaper/content/4750488 |
Select/Unselect all | For Selected Papers |
Saved Papers
Please enter a name for this paper to be shown in your personalized Saved Papers list
|
Results per page: |
About Sciencepaper Online | Privacy Policy | Terms & Conditions | Contact Us
© 2003-2012 Sciencepaper Online. unless otherwise stated