检索结果-内蒙古大学图书馆

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 availab.e 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

A Dual-band Monopole Antenna with EBG for Wearable Wireless Body Area Networks

引用

Applied Computational Electromagnetics Society Journal 2021年第1期36卷 48-54页

作者： Wang, Chao Zhang, Liang Wu, Shenbing Huang, Shijie Liu, Changqing Wu, Xianliang Key Lab of Ministry of Education of Intelligent Computing & Signal Processing Anhui University Hefei City China AnHui Province Key Laboratory of Simulation and Design Electronic Information System Hefei Normal University Hefei City China

This paper proposes a dual-band wearable monopole antenna adopting an electromagnetic band-gap (EBG) structure, which operates at 2.45 and 5.8 GHz ISM bands and is suitable for wearable applications. Both the monopole antenna and the EBG structure are fabricated on an F4B semi-flexible substrate having a dielectric constant of 2.2. The EBG structure effectively isolates the human body from the radiation of the antenna and reduces the specific absorption rate (SAR) of it by more than 97.5%. This improves the antenna gain and the peak gain reaches 9.1 dBi at 5.8 GHz. The wearable performance of the antenna showed that it can sustain good performance even under realistic human body loading. Besides, the antenna has a small size, which makes it ideal for wearable applications. © ACES

关键词： Monopole antennas

来源：评论

学校读者我要写书评

暂无评论

UHRSNet: A Semantic Segmentation Network Specifically for Ultra-High-Resolution Images

UHRSNet: A Semantic Segmentation Network Specifically for Ul...

引用

International Conference on Pattern Recognition

作者： Lianlei Shan Minglong Li Xiaobin Li Yang Bai Ke Lv Bin Luo Si-Bao Chen Weiqiang Wang University of Chinese Academy of Sciences Beijing China MOE Key Lab of Signal Processing and Intelligent Computing School of Computer Science and Technology Anhui University Hefei China

Semantic segmentation is a basic task in computer vision, but only limited attention has been devoted to the ultra-high-resolution (UHR) image segmentation. Since UHR images occupy too much memory, they cannot be directly put into GPU for training. Previous methods are cropping images to small patches or downsampling the whole images. Cropping and downsampling cause the loss of contexts and details, which is essential for segmentation accuracy. To solve this problem, we improve and simplify the local and global feature fusion method in previous works. Local features are extracted from patches and global features are from downsampled images. Meanwhile, we propose one new fusion called local feature fusion for the first time, which can make patches get information from surrounding patches. We call the network with these two fusions ultra-high-resolution segmentation network (UHRSNet). These two fusions can effectively and efficiently solve the problem caused by cropping and downsampling. Experiments show a remarkable improvement on Deepglobe dataset [1].

关键词： Training Image segmentation Computer vision Semantics Graphics processing units Feature extraction Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

RGB-T Saliency Detection via Robust Graph Learning and Collab.rative Manifold Ranking 14th

RGB-T Saliency Detection via Robust Graph Learning and Colla...

引用

14th International Conference on Bio-inspired computing: Theories and Applications, BIC-TA 2019

作者： Sun, Dengdi Li, Sheng Ding, Zhuanlian Luo, Bin Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei230601 China School of Internet Anhui University Hefei230039 China

ISBN: (纸本)9789811534140

Visual saliency detection inspired by brain cognitive mechanisms is an important component of computer vision, aiming at automatically highlight salient visual objects from the image background. In complex real scenarios, integrating multiple different yet complementary feature representations has been proved to be an effective way for boosting saliency detection performance. In this paper, we propose a novel collab.rative algorithm for saliency detection by adaptively incorporating information from grayscale and thermal images. Specifically, we first construct an affinity graph model via robust graph learning to characterize the feature similarities and location relationships between two different image patches under each modal. Based on these affinity graphs, a collab.rative manifold ranking method cross-modality consistent constraints is designed to effectively and efficiently infer the salient score for each patch. Moreover, we introduce a weight for each modality to describe the reliability, and integrate them into the graph-based manifold ranking scheme to achieve an adaptive weighted fusion of different source data. For optimization, we propose some iterative algorithms to efficiently solve the models with several subproblems. Experiments on the grayscale-thermal datasets demonstrate the superior performance of the new method over the state-of-the-art approaches. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

A Novel Tri-band Frequency Selective Surface 2

A Novel Tri-band Frequency Selective Surface

引用

2020 2nd International Conference on Artificial Intelligence Technologies and Application, ICAITA 2020

作者： Wu, Shenbing Chen, Mingsheng Wang, Chao Wu, Xianliang Key Lab of Ministry of Education of Intelligent Computing and Signal Processing Anhui University Hefei Anhui230601 China School of Electronic Engineering Huainan Normal University Huainan Anhui232001 China

This paper presents a novel tri-band frequency miniaturized frequency selection surface (FSS). The proposed FSS consists of single-node folding and single-node folding bending. The single-layer FSS exhibits three stop bands centered at 2.45, 3.61 and 5.79 GHz, with bandwidths of 0.42, 0.48 and 0.70 GHz, respectively. The proposed FSS has better miniaturization characteristics, and its cell size is 0.126 ?×0.126 ?. The three stop band frequencies of the FSS can be independently controlled by simply changing the length of the corresponding branch. In addition, the proposed FSS is symmetrical about the center and exhibits good resonance stability in both TE and TM polarization. The prototype of the proposed FSS was fabricated and tested, compared with the simulation results, the FSS showed stable performance. This method provides ideas for designing multiband FSS in the future. © 2020 Published under licence by IOP Publishing Ltd.

关键词： Frequency selective surfaces

来源：评论

学校读者我要写书评

暂无评论

Dual-Graph Regularized Sparse Low-Rank Matrix Recovery for Tag Refinement 14th

Dual-Graph Regularized Sparse Low-Rank Matrix Recovery for T...

引用

14th International Conference on Bio-inspired computing: Theories and Applications, BIC-TA 2019

作者： Sun, Dengdi Bao, Yuanyuan Ge, Meiling Ding, Zhuanlian Luo, Bin Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei230601 China School of Internet Anhui University Hefei230039 China

ISBN: (纸本)9789811534140

In recent years, extremely large amounts of images with manual tags are easily availab.e in many social websites such as Twitter, Flickr, and Instagram. However, these user-provided tags are often imprecise and incomplete, which inevitably limits the performances of image retrieval and other related applications. To this end, tag refitment technology aims at improving the quality of images tags automatically, and has been a fundamental challenge in Internet era. In this paper, we propose a novel dual-graph regularized sparse low-rank matrix recovery method, referred to as DGSLR briefly, to infer and improve the manual tags. Specifically, our DGSLR model first suppress the sparse noisy tags by norm, and decompose simultaneously the residual low-rank matrix to learning the low-dimensional vector representations of images and tags. Moreover, the visual similarities and the tag pairwise correlation are fully exploited to smooth the decomposition results by using the dual lapalcian graph regularization terms. For optimization, an improved alternative iteration strategy is designed to solve the resulting objective function. Extensive experiments on the tasks of tag refinement demonstrate the superior performance of the proposed algorithms over several representative methods, especially when the manual tag data is highly noisy and sparse. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Wideband 10-port mimo antenna array for 5g metal-frame smartphone applications

引用

Progress In Electromagnetics Research C 2020年 104卷 229-240页

作者： Liu, Peng Sun, Yufa Liu, Tao Li, Qing Wang, Xuefeng Key Lab of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei230601 China

A wideband 10-port multiple input multiple output (MIMO) antenna array operated below 6 GHz for the fifth generation (5G) metal-frame smartphones is presented and discussed in this paper. The proposed MIMO antenna array element is composed of a microstrip line with a tuning stub and rectangular slot. The size of the rectangular slot is only 15 mm × 2 mm (0.211λ0 × 0.028λ0, and λ0 is the wavelength with the resonance frequency of 4.2 GHz). U-shaped slots on the substrate are used to reduce the mutual coupling between the antenna elements. At the same time, in order to improve the radiation characteristics of the antenna arrays, narrow slits are etched in the metal-frame. The proposed antenna covers 3.3–5.5 GHz (S11 © 2020, Electromagnetics Academy. All rights reserved.

关键词： Antenna arrays

来源：评论

学校读者我要写书评

暂无评论

A BVP signal Detection Method of Anti-Motion Interference 12

A BVP Signal Detection Method of Anti-Motion Interference

引用

12th International Congress on Image and signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019

作者： Wan, Qing Wu, Xiaopei Zhang, Chao Anhui University Intelligent Computing and Signal Processing Key Lab Hefei China

ISBN: (纸本)9781728148526

The noncontact detection methods of blood volume pulse (BVP) based on facial videos have become a hot spot in recent years. However, these kinds of methods are highly sensitive to face movement. To address this problem, a novel BVP detection method based on kanade-Iucas-tomasi (KLT) and independent component analysis (ICA) was proposed, in which, KLT method was employed for tracking and locating the region of interest (ROI) in facial images, and ICA method was used to improve the signal to noise ratio (SNR) of BVP signal. Based on 120 recorded facial videos, we carried out the comparative study of the proposed method and other commonly-used methods, the experimental results show that our method has obvious advantages in eliminating motion interference. In the implementation of the blind source separation method, we also conducted four separation methods. The results show that the second order blind identification (SOBI) algorithm is the best one to separate the BVP signal. © 2019 IEEE.

关键词： Blind source separation

来源：评论

学校读者我要写书评

暂无评论

The minority matters: a diversity-promoting collab.rative metric learning algorithm 22

The minority matters: a diversity-promoting collaborative me...

引用

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

作者： Shilong Bao Qianqian Xu Zhiyong Yang Yuan He Xiaochun Cao Qingming Huang State Key Laboratory of Information Security Institute of Information Engineering CAS and School of Cyber Security University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS School of Computer Science and Tech. University of Chinese Academy of Sciences Alibaba Group School of Cyber Science and Technology Shenzhen Campus Sun Yat-sen University Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Laboratory of Big Data Mining and Knowledge Management CAS and Peng Cheng Laboratory

ISBN: (纸本)9781713871088

Collab.rative Metric Learning (CML) has recently emerged as a popular method in recommendation systems (RS), closing the gap between metric learning and Collab.rative Filtering. Following the convention of RS, existing methods exploit unique user representation in their model design. This paper focuses on a challenging scenario where a user has multiple categories of interests. Under this setting, we argue that the unique user representation might induce preference bias, especially when the item category distribution is imbalanced. To address this issue, we propose a novel method called Diversity-Promoting Collab.rative Metric Learning (DPCML), with the hope of considering the commonly ignored minority interest of the user. The key idea behind DPCML is to include a multiple set of representations for each user in the system. Based on this embedding paradigm, user preference toward an item is aggregated from different embeddings by taking the minimum item-user distance among the user embedding set. Furthermore, we observe that the diversity of the embeddings for the same user also plays an essential role in the model. To this end, we propose a Diversity Control Regularization Scheme (DCRS) to accommodate the multi-vector representation strategy better. Theoretically, we show that DPCML could generalize well to unseen test data by tackling the challenge of the annoying operation that comes from the minimum value. Experiments over a range of benchmark datasets speak to the efficacy of DPCML.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features

arXiv

引用

arXiv 2024年

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management CAS China

Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative tasks such as semantic segmentation. Given numerous activations, selecting a small yet effective subset poses a fundamental problem. To this end, the early study of this field performs a large-scale quantitative comparison of the discriminative ability of the activations. However, we find that many potential activations have not been evaluated, such as the queries and keys used to compute attention scores. Moreover, recent advancements in diffusion architectures bring many new activations, such as those within embedded ViT modules. Both combined, activation selection remains unresolved but overlooked. To tackle this issue, this paper takes a further step with a much broader range of activations evaluated. Considering the significant increase in activations, a full-scale quantitative comparison is no longer operational. Instead, we seek to understand the properties of these activations, such that the activations that are clearly inferior can be filtered out in advance via simple qualitative evaluation. After careful analysis, we discover three properties universal among diffusion models, enabling this study to go beyond specific models. On top of this, we present effective feature selection solutions for several popular diffusion models. Finally, the experiments across multiple discriminative tasks validate the superiority of our method over the SOTA competitors. Our code is availab.e at this url. © 2024, CC BY.

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：