检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Tu, Danyang Sun, Wei Min, Xiongkuo Zhai, Guangtao Shen, Wei Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China

We present a novel vision Transformer, named TUTOR, which is able to learn tubelet tokens, served as highly-abstracted spatiotemporal representations, for video-based human-object interaction (V-HOI) detection. The tubelet tokens structurize videos by agglomerating and linking semantically-related patch tokens along spatial and temporal domains, which enjoy two benefits: 1) Compactness: each tubelet token is learned by a selective attention mechanism to reduce redundant spatial dependencies from others;2) Expressiveness: each tubelet token is enabled to align with a semantic instance, i.e., an object or a human, across frames, thanks to agglomeration and linking. The effectiveness and efficiency of TUTOR are verified by extensive experiments. Results shows our method outperforms existing works by large margins, with a relative mAP gain of 16.14% on VidHOI and a 2 points gain on CAD-120 as well as a 4× speedup. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Signal detection in severely heavy-tailed radar clutter

Signal detection in severely heavy-tailed radar clutter

引用

Asilomar Conference on Signals, Systems & Computers

作者： G.A. Tsihrintzis P. Tsakalides C.L. Nikias Communication Systems Lab Department of Electrical Engineering University of Virginia Charlottesville VA USA Signal and Image Processing Institute Department of Electrical Engineering-Systems University of Southern California Los Angeles CA USA

Alpha-stable distributions have been recognized in the signal processing community as simple, yet very accurate, two-parameter statistical models for signals and noise that contain an impulsive component of various degrees of severity. On the basis of this finding, several signal processing problems have been addressed and solved within the framework of alpha-stable distributions and with the use of fractional, lower-order statistics. We attempt to popularize these new signal processing tools within the radar community. In particular, we evaluate the goodness-of-fit of alpha-stable models in the radar environment and test the performance of new signal processing algorithms for signal detection and classification on real radar, sea-clutter data.

关键词： Signal detection Radar signal processing Interference Signal processing Object detection Radar clutter Sensor arrays Signal processing algorithms Testing Statistics

来源：评论

学校读者我要写书评

暂无评论

A Research of Heart Rate Prediction Model Based on Evolutionary Neural Network

A Research of Heart Rate Prediction Model Based on Evolution...

引用

International Conference on Intelligent Computation and Bio-Medical Instrumentation (ICBMI)

作者： Feng Xiao Ming Yuchi Mingyue Ding Jun Jo Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Life College of Science and Technology Huazhong University of Science and Technology Wuhan China School of Information and Communication Technology Griffith University QLD Australia

Heart rate (HR) signal analysis is widely used in the medicine and medical research area. Physical activities (PA) are commonly recognized to greatly affect the changes of heart rate. A method of Evolutionary Neural Network - Neuro-evolution of Augmenting Topologies (NEAT) is used to build a PA-based HR predictor model. Through special coding, crossover and mutation operator, NEAT can implement network topology and connectivity weights evolution simultaneously. The common problem in evolutionary neural network, like competing conventions, how to protect the new innovation are effectively solved. The experimental results demonstrated the application potential of the approach.

关键词： Heart rate Biological neural networks Training Monitoring Neurons Encoding Biomedical monitoring

来源：评论

学校读者我要写书评

暂无评论

CageNeRF: cage-based neural radiance field for generalized 3D deformation and animation 22

CageNeRF: cage-based neural radiance field for generalized 3...

引用

Proceedings of the 36th International Conference on Neural Information processing Systems

作者： Yicong Peng Yichao Yan Shenqi Liu Yuhao Cheng Shanyan Guan Bowen Pan Guangtao Zhai Xiaokang Yang Institute of Image Communication and Network Engineering Shanghai Jiao Tong University MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Alibaba Group

ISBN: (纸本)9781713871088

While implicit representations have achieved high-fidelity results in 3D rendering, it remains challenging to deforming and animating the implicit field. Existing works typically leverage data-dependent models as deformation priors, such as SMPL for human body animation. However, this dependency on category-specific priors limits them to generalize to other objects. To solve this problem, we propose a novel framework for deforming and animating the neural radiance field learned on arbitrary objects. The key insight is that we introduce a cage-based representation as deformation prior, which is category-agnostic. Specifically, the deformation is performed based on an enclosing polygon mesh with sparsely defined vertices called cage inside the rendering space, where each point is projected into a novel position based on the barycentric interpolation of the deformed cage vertices. In this way, we transform the cage into a generalized constraint, which is able to deform and animate arbitrary target objects while preserving geometry details. Based on extensive experiments, we demonstrate the effectiveness of our framework in the task of geometry editing, object animation and deformation transfer.

关键词：

来源：评论

学校读者我要写书评

暂无评论

94 GHz Three-Dimensional Imaging Radar for Environmental Detection 8

94 GHz Three-Dimensional Imaging Radar for Environmental Det...

引用

8th Asia-Pacific Conference on Antennas and Propagation, APCAP 2019

作者： Wu, HongMing Qi, Feng Wang, Jinkuan Northeastern University College of Information Science and Engineering Shenyang110819 China Chinese Academy of Sciences Shenyang Institute of Automation Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110016 China Key Laboratory of Opto-Electronic Information Processing Chinese Academy of Sciences Shenyang110016 China Key Lab of Image Understanding and Computer Vision Liaoning Province Shenyang110016 China

ISBN: (纸本)9781665400541

At present, With the development of technology, the high resolution of millimeter wave (terahertz) can be applied to environmental sensing imaging. In this paper, Using the frequency-modulated continuous-wave (FMCW) radar technique with a 1GHz bandwidth, we show experimentally that a high-resolution real time imaging radar operating at 93.5-94.5GHz is capable of detecting different car models at standoff ranges of 12 m. We also achieved 3D high-resolution imaging of the building. at 140 meters. © 2019 IEEE.

关键词： Millimeter waves

来源：评论

学校读者我要写书评

暂无评论

Vehicle Color Recognition Using Monocular camera

Vehicle Color Recognition Using Monocular camera

引用

2011年无线通信与信号处理国际会议(WCSP 2011)

作者： Mengjie Yang Xiuchang Zhu Liang Li Guang Han Xiaofei Li Jiangsu Provincial Key Lab of Image Processing and ImageCommunication Nanjing Univ. of P&TNanjing Engineering Research Center of Wideband Wireless Communication and Display Technique Ministry of Ed Engineering Research Center of Wideband WirelessCommunication and Display Technique Ministry ofEduc

This paper introduces a novel moving vehicle color recognition method. By processing videos recorded by monocular camera on traffic, we get single color image of vehicles which are crossed the traffic in any direction. First, paper employed a H-S two dimension histogram method to detect the color of the vehicles, and distinguish red, yellow, green and blue four color vehicles. Due to deal with the vehicles that do not satisfy above 4 colors, Regional Color Judgment method is proposed. This method consists of the following five steps: Firstly, position the color detection region by identifying the travelling direction of the vehicle. Then pick out the candidate color extraction region used to vehicle recognition. At last extract the color of the candidate region and match the color with the templates we predefined, the color of the best fit template is the color of the vehicle.

关键词： vehicle color recognition region choice HSV space vehicle detection

来源：评论

学校读者我要写书评

暂无评论

On the Training of DNN-based Average Voice Model for Speech Synthesis

On the Training of DNN-based Average Voice Model for Speech ...

引用

Asia-Pacific Signal and Information processing Association Annual Summit and Conference

作者： Shan Yang Zhizheng Wu Lei Xie Shaanxi Provincial Key Lab of Speech and Image Information Processing School of Computer Science Northwestern Polytechnical University Xi'an China The Centre for Speech Technology Research University of Edinburgh UK

ISBN: (纸本)9781509024018

Adaptability and controllability are the major advantages of statistical parametric speech synthesis (SPSS) over unit-selection synthesis. Recently, deep neural networks (DNNs) have significantly improved the performance of SPSS. However, current studies are mainly focusing on the training of speaker-dependent DNNs, which generally requires a significant amount of data from a single speaker. In this work, we perform a systematic analysis of the training of multi-speaker average voice model (AVM), which is the foundation of adaptability and controllability of a DNN-based speech synthesis system. Specifically, we employ the i-vector framework to factorise the speaker specific information, which allows a variety of speakers to share all the hidden layers. And the speaker identity vector is augmented with linguistic features in the DNN input. We systematically analyse the impact of the implementations of ivectors and speaker normalisation.

关键词： Training DNN-based Average Voice Model Speech Synthesis

来源：评论

学校读者我要写书评

暂无评论

EEP-3DQA: EFFICIENT AND EFFECTIVE PROJECTION-BASED 3D MODEL QUALITY ASSESSMENT

arXiv

引用

arXiv 2023年

作者： Zhang, Zicheng Sun, Wei Zhou, Yingjie Lu, Wei Zhu, Yucheng Min, Xiongkuo Zhai, Guangtao Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China

Currently, great numbers of efforts have been put into improving the effectiveness of 3D model quality assessment (3DQA) methods. However, little attention has been paid to the computational costs and inference time, which is also important for practical applications. Unlike 2D media, 3D models are represented by more complicated and irregular digital formats, such as point cloud and mesh. Thus it is normally difficult to perform an efficient module to extract quality-aware features of 3D models. In this paper, we address this problem from the aspect of projection-based 3DQA and develop a no-reference (NR) Efficient and Effective Projectionbased 3D Model Quality Assessment (EEP-3DQA) method. The input projection images of EEP-3DQA are randomly sampled from the six perpendicular viewpoints of the 3D model and are further spatially downsampled by the grid-mini patch sampling strategy. Further, the lightweight Swin-Transformer tiny is utilized as the backbone to extract the quality-aware features. Finally, the proposed EEP-3DQA and EEP-3DQA-t (tiny version) achieve the best performance than the existing state-of-the-art NR-3DQA methods and even outperforms most full-reference (FR) 3DQA methods on the point cloud and mesh quality assessment databases while consuming less inference time than the compared 3DQA methods. © 2023, CC BY.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

GANHead: Towards Generative Animatable Neural Head Avatars

GANHead: Towards Generative Animatable Neural Head Avatars

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Sijing Wu Yichao Yan Yunhao Li Yuhao Cheng Wenhan Zhu Ke Gao Xiaobo Li Guangtao Zhai Institute of Image Communication and Network Engineering Shanghai Jiao Tong University MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Alibaba Group

To bring digital avatars into people's lives, it is highly demanded to efficiently generate complete, realistic, and animatable head avatars. This task is challenging, and it is difficult for existing methods to satisfy all the requirements at once. To achieve these goals, we propose GANHead (Generative Animatable Neural Head Avatar), a novel generative head model that takes advantages of both the fine-grained control over the explicit expression parameters and the realistic rendering results of implicit representations. Specifically, GANHead represents coarse geometry, fine-gained details and texture via three networks in canonical space to obtain the ability to generate complete and realistic head avatars. To achieve flexible animation, we define the deformation filed by standard linear blend skinning (LBS), with the learned continuous pose and expression bases and LBS weights. This allows the avatars to be directly animated by FLAME [22] parameters and generalize well to unseen poses and expressions. Compared to state-of-the-art (SOTA) methods, GANHead achieves superior performance on head avatar generation and raw scan fitting.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GENERATIVE COMPRESSION FOR FACE VIDEO: A HYBRID SCHEME

arXiv

引用

arXiv 2022年

作者： Tang, Anni Huang, Yan Ling, Jun Zhang, Zhiyu Zhang, Yiwei Xie, Rong Song, Li Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China MOE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China

As the latest video coding standard, versatile video coding (VVC) has shown its ability in retaining pixel quality. To excavate more compression potential for video conference scenarios under ultra-low bitrate, this paper proposes a bitrate-adjustable hybrid compression scheme for face video. This hybrid scheme combines the pixel-level precise recovery capability of traditional coding with the generation capability of deep learning based on abridged information, where Pixel-wise Bi-Prediction, Low-Bitrate-FOM and Lossless keypoint Encoder collaborate to achieve PSNR up to 36.23 dB at a low bitrate of 1.47 KB/s. Without introducing any additional bitrate, our method has a clear advantage over VVC under a completely fair comparative experiment, which proves the effectiveness of our proposed scheme. Moreover, our scheme can adapt to any existing encoder/configuration to deal with different encoding requirements, and the bitrate can be dynamically adjusted according to the network condition. Copyright © 2022, The Authors. All rights reserved.

关键词： image compression

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：