检索结果-内蒙古大学图书馆

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zijian Zhu Yichi Zhang Hai Chen Yinpeng Dong Shu Zhao Wenbo Ding Jiachen Zhong Shibao Zheng Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Dept. of Comp. Sci. and Tech. THBI Lab Institute for AI Tsinghua University BNRist Center Zhongguancun Laboratory Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Information Materials and Intelligent Sensing Laboratory of Anhui Province School of Computer Science and Technology Anhui University SAIC Motor AI Lab

3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird's-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with camera inputs on popular benchmarks. However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems. In this paper, we evaluate the natural and adversarial robustness of various representative models under extensive settings, to fully understand their behaviors influenced by explicit BEV features compared with those without BEV. In addition to the classic settings, we propose a 3D consistent patch attack by applying adversarial patches in the 3D space to guarantee the spatiotemporal consistency, which is more realistic for the scenario of autonomous driving. With substantial experiments, we draw several findings: 1) BEV models tend to be more stable than previous methods under different natural conditions and common corruptions due to the expressive spatial representations; 2) BEV models are more vulnerable to adversarial noises, mainly caused by the redundant BEV features; 3) Camera-LiDARfusion models have superior performance under different settings with multi-modal inputs, but BEV fusion model is still vulnerable to adversarial noises of both point cloud and image. These findings alert the safety issue in the applications of BEV detectors and could facilitate the development of more robust models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Technical Analysis on Application Layer Error Control in IPTV

引用

ZTE communications 2010年第1期000卷

作者： Xia Hongfei Lü Xiaopeng Liu Feng ZTE Corporation Nanjing 210012P.R.China Image Processing and Image Communication Laboratory of Jiangsu Province Nanjing University of Posts and TelecommunicationsNanjing 210003P. R. China

When they provide Internet Protocol Television (IPTV) services, IP networks face difficulties such as reduced transmission bandwidth, delay, jitter, and packet loss. A terminal-centric solution can improve the image quality by adding control policies like congestion control and error control to the receiving terminal and source code. An end-to-end application layer reliability method is usually required to satisfy IPTV requirements in the IP network. Application Layer Forward Error Correction (AL-FEC) technology solves the problem of packet loss, and can ensure the end-to-end reliability for IPTV services.

关键词：差错控制分析应用 IPTV 技术接收终端 IP网络服务终端互联网协议

来源：评论

学校读者我要写书评

暂无评论

Understanding the Robustness of 3D Object Detection with Bird’s-Eye-View Representations in Autonomous Driving

arXiv

引用

arXiv 2023年

作者： Zhu, Zijian Zhang, Yichi Chen, Hai Dong, Yinpeng Zhao, Shu Ding, Wenbo Zhong, Jiachen Zheng, Shibao Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China Dept. of Comp. Sci. and Tech. Institute for AI THBI Lab BNRist Center Tsinghua University China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education School of Computer Science and Technology Anhui University Information Materials and Intelligent Sensing Laboratory of Anhui Province China SAIC Motor AI Lab China Zhongguancun Laboratory China

3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird’s-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with camera inputs on popular benchmarks. However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems. In this paper, we evaluate the natural and adversarial robustness of various representative models under extensive settings, to fully understand their behaviors influenced by explicit BEV features compared with those without BEV. In addition to the classic settings, we propose a 3D consistent patch attack by applying adversarial patches in the 3D space to guarantee the spatiotemporal consistency, which is more realistic for the scenario of autonomous driving. With substantial experiments, we draw several findings: 1) BEV models tend to be more stable than previous methods under different natural conditions and common corruptions due to the expressive spatial representations;2) BEV models are more vulnerable to adversarial noises, mainly caused by the redundant BEV features;3) Camera-LiDAR fusion models have superior performance under different settings with multi-modal inputs, but BEV fusion model is still vulnerable to adversarial noises of both point cloud and image. These findings alert the safety issue in the applications of BEV detectors and could facilitate the development of more robust models. Code available at https: //***/zzj403/BEV_Robust. Copyright © 2023, The Authors. All rights reserved.

关键词： Birds

来源：评论

学校读者我要写书评

暂无评论

Lightweight Real-time Semantic Segmentation Network with Efficient Transformer and CNN

arXiv

引用

arXiv 2023年

作者： Xu, Guoan Li, Juncheng Gao, Guangwei Lu, Huimin Yang, Jian Yue, Dong The Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing210023 China The Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou215006 China The School of Communication and Information Engineering Shanghai University Shanghai200444 China Jiangsu Key Laboratory of Image and Video Understanding for Social Safety Nanjing University of Science and Technology Nanjing210049 China The Kyushu Institute of Technology Kitakyushu804-8550 Japan The School of Computer Science and Technology Nanjing University of Science and Technology Nanjing210049 China

In the past decade, convolutional neural networks (CNNs) have shown prominence for semantic segmentation. Although CNN models have very impressive performance, the ability to capture global representation is still insufficient, which results in suboptimal results. Recently, Transformer achieved huge success in NLP tasks, demonstrating its advantages in modeling long-range dependency. Recently, Transformer has also attracted tremendous attention from computer vision researchers who reformulate the image processing tasks as a sequence-to-sequence prediction but resulted in deteriorating local feature details. In this work, we propose a lightweight real-time semantic segmentation network called LETNet. LETNet combines a U-shaped CNN with Transformer effectively in a capsule embedding style to compensate for respective deficiencies. Meanwhile, the elaborately designed Lightweight Dilated Bottleneck (LDB) module and Feature Enhancement (FE) module cultivate a positive impact on training from scratch simultaneously. Extensive experiments performed on challenging datasets demonstrate that LETNet achieves superior performances in accuracy and efficiency balance. Specifically, It only contains 0.95M parameters and 13.6G FLOPs but yields 72.8% mIoU at 120 FPS on the Cityscapes test set and 70.5% mIoU at 250 FPS on the CamVid test dataset using a single RTX 3090 GPU. Source code will be available at https://***/IVIPLab/LETNet. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Enhancing emission performance of red TADF emitters via the introduction of electronically inert pendant

引用

Organic Electronics 2024年 126卷

作者： Tang, Yukun He, Jian-Li Zhang, Kai Zhao, Yue Lin, Yu-Ching Chen, Chia-Hsun Chiu, Tien-Lung Lee, Jiun-Haw Wang, Chuan-Kui Fan, Jian Wu, Chung-Chih Department of Electrical Engineering Graduate Institute of Electronics Engineering and Graduate Institute of Photonics and Optoelectronics National Taiwan University Taipei 10617 Taiwan Jiangsu Key Laboratory for Carbon-Based Functional Materials & Devices Soochow University Jiangsu Suzhou215123 China Shandong Province Key Laboratory of Medical Physics and Image Processing Technology School of Physics and Electronics Shandong Normal University Jinan250014 China Coordination Chemistry Institute State Key Laboratory of Coordination Chemistry School of Chemistry and Chemical Engineering Nanjing National Laboratory of Microstructures Nanjing University Nanjing210023 China Department of Chemistry National Taiwan University Taipei10617 Taiwan Department of Electrical Engineering Yuan Ze University Taoyuan32003 Taiwan Graduate Institute of Photonics and Optoelectronics and Department of Electrical Engineering National Taiwan University Taipei10617 Taiwan State Key Laboratory of Structural Chemistry Fujian Institute of Research on Structure of Matter Chinese Academy of Sciences Fujian Fuzhou35002 China

In addition to emission efficiency and colors, emission characteristics such as preferentially horizontal emitting dipole orientation and resistance against concentration quenching are also highly desired for high-performance thermally activated delayed fluorescence (TADF) emitters. In this work, we report a simple and yet effective strategy for enhancing such emission performance of the pure red-to-near infrared (NIR) TADF emitter by introducing bulky aryl derivatives (m-xylene) to the efficient emission core. Incorporating m-xylene groups as the electronically inert pendants to the acceptor unit of the TADF emitter TPA–CN–N4-CH3 successfully retains favorable emission properties (e.g., pure red color chromaticity, nearly unitary photoluminescence quantum yield etc.) of the parent compound TPA–CN–N4 and yet also renders significantly higher horizontal emitting dipole ratio Θ// of ∼85 % with the more extended molecular configuration and reduced concentration quenching at very high concentrations in thin films. As a result, OLEDs adopting TPA–CN–N4-CH3 can demonstrate rather high EQEs of 29.8–32.1 % for pure red emission (625–650 nm) at low doping concentrations and decent EQEs of 18.9–27.5 % in the deep red to NIR range (650–700 nm) at higher doping concentrations. The results of this work shall provide a useful reference for development of efficient TADF emitters. © 2024 Elsevier B.V.

关键词： Fluorescence

来源：评论

学校读者我要写书评

暂无评论

EWT: Efficient Wavelet-Transformer for Single image Denoising

arXiv

引用

arXiv 2023年

作者： Li, Juncheng Cheng, Bodong Chen, Ying Gao, Guangwei Zeng, Tieyong The School of Communication & Information Engineering Shanghai University Shanghai China Jiangsu Key Laboratory of Image and Video Understanding for Social Safety Nanjing University of Science and Technology Nanjing China The School of Computer Science and Technology Xidian University Xian China The Department of Cyberspace Security Beijing Electronic Science & Technology Institute Beijing China The Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing China The Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou China The Department of Mathematics The Chinese University of Hong Kong New Territories Hong Kong

Transformer-based image denoising methods have achieved encouraging results in the past year. However, it must uses linear operations to model long-range dependencies, which greatly increases model inference time and consumes GPU storage space. Compared with convolutional neural network-based methods, current Transformer-based image denoising methods cannot achieve a balance between performance improvement and resource consumption. In this paper, we propose an Efficient Wavelet Transformer (EWT) for image denoising. Specifically, we use Discrete Wavelet Transform (DWT) and Inverse Wavelet Transform (IWT) for downsampling and upsampling, respectively. This method can fully preserve the image features while reducing the image resolution, thereby greatly reducing the device resource consumption of the Transformer model. Furthermore, we propose a novel Dual-stream Feature Extraction Block (DFEB) to extract image features at different levels, which can further reduce model inference time and GPU memory usage. Experiments show that our method speeds up the original Transformer by more than 80%, reduces GPU memory usage by more than 60%, and achieves excellent denoising results. All code will be public. © 2023, CC BY.

关键词： image denoising

来源：评论

学校读者我要写书评

暂无评论

CTCNet: A CNN-Transformer Cooperation Network for Face image Super-Resolution

arXiv

引用

arXiv 2022年

作者： Gao, Guangwei Xu, Zixiang Li, Juncheng Yang, Jian Zeng, Tieyong Qi, Guo-Jun The Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing China The Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou China The School of Communication & Information Engineering Shanghai University Shanghai China Jiangsu Key Laboratory of Image and Video Understanding for Social Safety Nanjing University of Science and Technology Nanjing China The School of Computer Science and Technology Nanjing University of Science and Technology Nanjing China The Center for Mathematical Artificial Intelligence Department of Mathematics The Chinese University of Hong Kong Hong Kong Research Center for Industries of the Future School of Engineering Westlake University OPPO Research Seattle United States

Recently, deep convolution neural networks (CNNs) steered face super-resolution methods have achieved great progress in restoring degraded facial details by joint training with facial priors. However, these methods have some obvious limitations. On the one hand, multi-task joint learning requires additional marking on the dataset, and the introduced prior network will significantly increase the computational cost of the model. On the other hand, the limited receptive field of CNN will reduce the fidelity and naturalness of the reconstructed facial images, resulting in suboptimal reconstructed images. In this work, we propose an efficient CNN-Transformer Cooperation Network (CTCNet) for face super-resolution tasks, which uses the multi-scale connected encoder-decoder architecture as the backbone. Specifically, we first devise a novel Local-Global Feature Cooperation Module (LGCM), which is composed of a Facial Structure Attention Unit (FSAU) and a Transformer block, to promote the consistency of local facial detail and global facial structure restoration simultaneously. Then, we design an efficient Feature Refinement Module (FRM) to enhance the encoded features. Finally, to further improve the restoration of fine facial details, we present a Multi-scale Feature Fusion Unit (MFFU) to adaptively fuse the features from different stages in the encoder procedure. Extensive evaluations on various datasets have assessed that the proposed CTCNet can outperform other state-of-the-art methods significantly. Source code will be available at https://***/IVIPLab/CTCNet. Copyright © 2022, The Authors. All rights reserved.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

13.2% EQE near-infrared TADF OLED with emission peak at 761 nm

引用

Chemical Engineering Journal 2023年第Part4期452卷

作者： Tai, Jing-Wen Tang, Yukun Zhang, Kai Yang, Chen-Zong Pan, Ze-Hui Lin, Yu-Ching Shih, Yu-Wei Chen, Chia-Hsun Chiu, Tien-Lung Lee, Jiun-Haw Wang, Chuan-Kui Wu, Chung-Chih Fan, Jian Jiangsu Key Laboratory for Carbon-Based Functional Materials & Devices Soochow University Jiangsu Suzhou215123 China Department of Electrical Engineering Graduate Institute of Electronics Engineering and Graduate Institute of Photonics and Optoelectronics National Taiwan University Taipei10617 Taiwan Shandong Province Key Laboratory of Medical Physics and Image Processing Technology School of Physics and Electronics Shandong Normal University Jinan250014 China Department of Chemistry National Taiwan University Taipei10617 Taiwan Department of Electrical Engineering Yuan Ze University Taoyuan32003 Taiwan Graduate Institute of Photonics and Optoelectronics and Department of Electrical Engineering National Taiwan University Taipei10617 Taiwan State Key Laboratory of Structural Chemistry Fujian Institute of Research on Structure of Matter Chinese Academy of Sciences Fujian Fuzhou35002 China

Near infrared (NIR) emitters have attracted much attention due to their advanced application in biomedical sensing/imaging, and telecommunications. However, the development of efficient NIR thermally activated delayed fluorescence (TADF) emitters with the emission over 750 nm is still a challenge. Herein two Y-shaped NIR TADF molecules (Py-TPA and Py-CN-TPA) were introduced. The inclusion of pyridine unit in these two emitters not only extended the conjugated system but also increased the molecular aspect ratios, thereby leading to their high horizontal ratio of emitting dipole orientation (Θ//). In addition, the NIR emitter showed a low Huang-Rhys (HR) factor in thin film relative to that in solution, indicating a low non-radiative transition rate and a high photoluminescent quantum yield (PLQY). Consequently, TADF OLED based on Py-TPA demonstrated a record-high external quantum efficiency (EQE) of 22.2% at 726 nm, 16.3% at 747 nm, and 13.2% at 761 nm. © 2022 Elsevier B.V.

关键词： Aspect ratio

来源：评论

学校读者我要写书评

暂无评论

Tigc-Net: Transformer-Improved Graph Convolution Network for Spatio-Temporal Prediction

SSRN

引用

SSRN 2022年

作者： Chen, Kai Yang, Chunfeng Zhou, Zhengyuan Liu, Yao Ji, Tianjiao Sun, Weiya Chen, Yang School of Cyber Science and Engineering Southeast University Nanjing210096 China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing210096 China The College of Software Engineering Southeast University Nanjing210096 China Laboratory of Image Science and Technology The School of Computer Science and Engineering Southeast University Nanjing210096 China Jiangsu Key Laboratory of Molecular and Functional Imaging Department of Radiology Zhongda Hospital Southeast University Nanjing210009 China Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing School of Computer Science and Engineering Southeast University Nanjing210096 China NHC Key Laboratory of Medical Virology and Viral Diseases National Institute for Viral Disease Control and Prevention Chinese Center for Disease Control and Prevention Beijing China Beijing Institute of Tracking and Communication Technology Beijing100094 China

Modeling spatio-temporal sequences is an important topic yet challenging for existing neural networks. Most of the current spatio-temporal sequence prediction methods usually capture features separately in temporal and spatial dimensions or employ multiple mutually independent local spatio-temporal graphs to represent a spatio-temporal sequence. The first kind of method mentioned above is difficult to mine the complex spatio-temporal correlations, while the other is limited for the accuracy of long-term predictions. To handle these issues, this paper proposes a Transformer-Improved Graph Convolution Network for spatio-temporal prediction. Specifically, the temporal location encoding method is exploited to derive the spatio-temporal characteristics of the sequence utilizing a spatio-temporal feature fusion network. In addition, a spatio-temporal attention network is developed to enhance the spatio-temporal correlation of the sequence, and the dynamic spatial features of sequence are further extracted through the adaptive graph convolution network. A private dataset and a public dataset are employed to demonstrate the performance of the proposed TIGC-Net. The qualitative and quantitative results show that the proposed TIGC-Net can extract dynamic spatiotemporal properties more effectively, enhance the spatio-temporal correlation of sequences and improve the prediction accuracy compared with four stateof-the-art. © 2022, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Cross-receptive Focused Inference Network for Lightweight image Super-Resolution

arXiv

引用

arXiv 2022年

作者： Li, Wenjie Li, Juncheng Gao, Guangwei Deng, Weihong Zhou, Jiantao Yang, Jian Qi, Guo-Jun The Intelligent Visual Information Perception Laboratory Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing210046 China The Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou215006 China The School of Communication and Information Engineering Shanghai University Shanghai200444 China Jiangsu Key Laboratory of Image and Video Understanding for Social Safety Nanjing University of Science and Technology Nanjing210094 China The Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China The State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science Faculty of Science and Technology University of Macau 999078 China The School of Computer Science and Technology Nanjing University of Science and Technology Nanjing210094 China The Research Center for Industries of the Future The School of Engineering Westlake University Hangzhou310024 China OPPO Research SeattleWA98101 United States

Recently, Transformer-based methods have shown impressive performance in single image super-resolution (SISR) tasks due to the ability of global feature extraction. However, the capabilities of Transformers that need to incorporate contextual information to extract features dynamically are neglected. To address this issue, we propose a lightweight Cross-receptive Focused Inference Network (CFIN) that consists of a cascade of CT Blocks mixed with CNN and Transformer. Specifically, in the CT block, we first propose a CNN-based Cross-Scale Information Aggregation Module (CIAM) to enable the model to better focus on potentially helpful information to improve the efficiency of the Transformer phase. Then, we design a novel Cross-receptive Field Guided Transformer (CFGT) to enable the selection of contextual information required for reconstruction by using a modulated convolutional kernel that understands the current semantic information and exploits the information interaction within different self-attention. Extensive experiments have shown that our proposed CFIN can effectively reconstruct images using contextual information, and it can strike a good balance between computational cost and model performance as an efficient model. Source codes will be available at https://***/IVIPLab/CFIN. 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

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：