检索结果-内蒙古大学图书馆

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

FST-Net: Facial Soft Tissue Landmark Localization on 3dMD Scans Using Feature Fusion and Local Coordinate Regression

FST-Net: Facial Soft Tissue Landmark Localization on 3dMD Sc...

引用

IEEE International Symposium on Biomedical Imaging

作者： Zhidong He Han Bao Mingzhang Chen Jiasong Wu Luwei Liu Lotfi Senhadji Huazhong Shu Bin Yan Laboratory of Image Science and Technology Southeast University Nanjing China Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Ministry of Education) Southeast University Nanjing China Department of Orthodontics The Affiliated Stomatological Hospital of Nanjing Medical University Nanjing China Centre de Recherche en Information Biomédicale Sino-Français Rennes France INSERM LTSI-UMR 1099 Univ-Rennes Rennes France

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

Landmark localization of facial soft tissue (FST) is a basic step in 3D morphometric analysis of human face. However, there are few studies on landmark localization of 3D scan images based on deep learning. The methods based on 2D images cannot be directly applied due to the non-Euclidean data structure. In this paper, we propose an end-to-end learning framework to automatically localize 28 landmarks on 3dMD scans, called FST-Net. Our method extracts features from texture images and mesh models. New texture mappings for 3dMD scans are generated by projection to fuse texture and structure features. A dual-branch network integrating transformers is applied to predict the landmark heatmaps from coarse to fine. A local coordinate regression module based on probabilistic distance and heatmap predictions is proposed to compute the landmark coordinates. We collect and annotate 297 3dMD face scans from the clinic to evaluate our model. Experiments show that the average localization error of the model is 1.204mm (the clinically acceptable precision range is 1.5 mm), and the correct landmark detection rate equals to 70.89%. Our model outperforms the current state-of-the-art deep learning methods for landmark localization on the mesh model.

关键词： Location awareness Deep learning Heating systems Three-dimensional displays Accuracy Computational modeling Biological tissues

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'View Representations in Autonomous Driving

Understanding the Robustness of 3D Object Detection with Bir...

引用

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

Vision-Language Consistency Guided Multi-modal Prompt Learning for Blind AI Generated image Quality Assessment

arXiv

引用

arXiv 2024年

作者： Fu, Jun Zhou, Wei Jiang, Qiuping Liu, Hantao Zhai, Guangtao The CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China The School of Computer Science and Informatics Cardiff University CardiffCF24 4AG United Kingdom The School of Information Science and Engineering Ningbo University Ningbo315211 China The Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai200240 China

Recently, textual prompt tuning has shown inspirational performance in adapting Contrastive Language-image Pre-training (CLIP) models to natural image quality assessment. However, such uni-modal prompt learning method only tunes the language branch of CLIP models. This is not enough for adapting CLIP models to AI generated image quality assessment (AGIQA) since AGIs visually differ from natural images. In addition, the consistency between AGIs and user input text prompts, which correlates with the perceptual quality of AGIs, is not investigated to guide AGIQA. In this letter, we propose vision-language consistency guided multi-modal prompt learning for blind AGIQA, dubbed CLIP-AGIQA. Specifically, we introduce learnable textual and visual prompts in language and vision branches of CLIP models, respectively. Moreover, we design a text-to-image alignment quality prediction task, whose learned vision-language consistency knowledge is used to guide the optimization of the above multi-modal prompts. Experimental results on two public AGIQA datasets demonstrate that the proposed method outperforms state-of-the-art quality assessment models. The source code is available at https://***/JunFu1995/CLIP-AGIQA. © 2024, CC BY-NC-ND.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Transclaw U-net: Claw U-net with transformers for medical image segmentation

arXiv

引用

arXiv 2021年

作者： Yao, Chang Hu, Menghan Zhai, Guangtao Zhang, Xiao-Ping Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University Institute of Image Communication and Information Processing Shanghai Jiao Tong University Department of Electrical Computer and Biomedical Engineering Ryerson University

In recent years, computer-aided diagnosis has become an increasingly popular topic. Methods based on convolutional neural networks have achieved good performance in medical image segmentation and classification. Due to the limitations of the convolution operation, the long-term spatial features are often not accurately obtained. Hence, we propose a TransClaw U-Net network structure, which combines the convolution operation with the transformer operation in the encoding part. The convolution part is applied for extracting the shallow spatial features to facilitate the recovery of the image resolution after upsampling. The transformer part is used to encode the patches, and the self-attention mechanism is used to obtain global information between sequences. The decoding part retains the bottom upsampling structure for better detail segmentation performance. The experimental results on Synapse Multi-organ Segmentation Datasets show that the performance of TransClaw U-Net is better than other network structures. The ablation experiments also prove the generalization performance of TransClaw U-Net. © 2021, CC BY.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Infectious Probability Analysis on COVID-19 Spreading with Wireless Edge Networks

arXiv

引用

arXiv 2022年

作者： Li, Xuran Guo, Shuaishuai Dai, Hong-Ning Li, Dengwang Shandong Key Laboratory of Medical Physics and Image Processing School of Physics and Electronics Shandong Normal University Jinan250061 China School of Control Science and Engineering Shandong University Jinan250061 China Shandong Provincial Key Laboratory of Wireless Communication Technologies Jinan China The Department of Computer Science Hong Kong Baptist University Hong Kong

The emergence of infectious disease COVID-19 has challenged and changed the world in an unprecedented manner. The integration of wireless networks with edge computing (namely wireless edge networks) brings opportunities to address this crisis. In this paper, we aim to investigate the prediction of the infectious probability and propose precautionary measures against COVID-19 with the assistance of wireless edge networks. Due to the availability of the recorded detention time and the density of individuals within a wireless edge network, we propose a stochastic geometry-based method to analyze the infectious probability of individuals. The proposed method can well keep the privacy of individuals in the system since it does not require to know the location or trajectory of each individual. Moreover, we also consider three types of mobility models and the static model of individuals. Numerical results show that analytical results well match with simulation results, thereby validating the accuracy of the proposed model. Moreover, numerical results also offer many insightful implications. Thereafter, we also offer a number of countermeasures against the spread of COVID-19 based on wireless edge networks. This study lays the foundation toward predicting the infectious risk in realistic environment and points out directions in mitigating the spread of infectious diseases with the aid of wireless edge networks. Copyright © 2022, The Authors. All rights reserved.

关键词： Stochastic systems

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

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

Smoothing Energy Transfer Enabling Efficient Large-Area Qusai-2d Perovskite Light-Emitting Diodes

SSRN

引用

SSRN 2022年

作者： Lei, Cai Zang, Jiaqing Jiangyu, Chen Jungui, Zhou Yatao, Zou Guilin, Bai Zhewei, Chen Song, Tao Chuan-Kui, Wang Sun, Baoquan Shandong Province Key Laboratory of Medical Physics and Image Processing Technology School of Physics and Electronics Shandong Normal University Shandong Jinan250014 China Soochow University Jiangsu Suzhou215123 China Jiangsu Key Laboratory for Carbon-Based Functional Materials & Devices Soochow University Jiangsu Suzhou215123 China MUST-SUDA Joint Research Center for Advanced Functional Materials Macau University of Science and Technology Taipa999078 China

Electroluminescence (EL) efficiency of perovskite light-emitting diodes (PeLEDs) based on a few square millimeters has improved significantly in recent years. Nevertheless, the EL efficiency of PeLEDs would be plunged once the active area was enlarged from millimeter to even sub-centimeter due to the unsmooth energy transfer process among the edge region with numerous nonradiative recombination centers. Herein, we developed an intriguing strategy to realize high-quality quasi-two-dimensional (quasi-2D) perovskite thin film via tuning perovskite precursor rheological properties as well as modulating the substrate surface tension. The perovskite crystallization process was retarded by incorporating a strong chelating ligand into its precursor. Hydroxylamine-O-sulfonic acid (ASC), containing a sulfonic acid group and an amino group acted as a strong chelating agent with lead ions (Pb 2+ ), which exhibited a great synergistic potential in defect passivation and crystallization modulation. An atop ultrathin lithium fluoride interlayer was pre-deposited to boost the substrate surface tension resulting in full coverage on a large-area substrate. ASC-anchored quasi-2D intermediate phases delayed the crystallization due to the strong chemical interaction between ASC and perovskite and then suppressed small-nanoplatelet phase formation in quasi-2D perovskite. ASC additives can also suppress nonradiative recombination, which is ascribed to the high binding energy between high electro positivity of the amino group with negatively charged defects as well as the elimination of uncoordinated Pb 2+ by the electron-rich sulfonic acid group. As a result, a large-area (25 cm 2 ) quasi-2D PeLED achieves an external quantum efficiency of 20.7% with uniform emitting characteristics, a record value among analogous same-size PeLEDs. Our work may pave the way to realizing high-performance large-area perovskite optoelectronic devices. © 2022, The Authors. All rights reserved.

关键词： Light emitting diodes

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：