检索结果-内蒙古大学图书馆

Weakly-Supervised Crowd Counting Learns from Sorting Rather Than Locations 1

16th European Conference on computer Vision, ECCV 2020

作者： Yang, Yifan Li, Guorong Wu, Zhe Su, Li Huang, Qingming Sebe, Nicu School of Computer Science and Technology UCAS Beijing China Key Lab of Big Data Mining and Knowledge Management UCAS Beijing China Key Lab of Intelligent Information Processing ICT CAS Beijing China University of Trento Trento Italy

ISBN: (数字)9783030585983

ISBN: (纸本)9783030585976

In crowd counting datasets, the location labels are costly, yet, they are not taken into the evaluation metrics. Besides, existing multi-task approaches employ high-level tasks to improve counting accuracy. This research tendency increases the demand for more annotations. In this paper, we propose a weakly-supervised counting network, which directly regresses the crowd numbers without the location supervision. Moreover, we train the network to count by exploiting the relationship among the images. We propose a soft-label sorting network along with the counting network, which sorts the given images by their crowd numbers. The sorting network drives the shared backbone CNN model to obtain density-sensitive ability explicitly. Therefore, the proposed method improves the counting accuracy by utilizing the information hidden in crowd numbers, rather than learning from extra labels, such as locations and perspectives. We evaluate our proposed method on three crowd counting datasets, and the performance of our method plays favorably against the fully supervised state-of-the-art approaches. © 2020, Springer Nature Switzerland AG.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

Unified Density-Aware Image Dehazing and Object Detection in Real-World Hazy Scenes 15th

Unified Density-Aware Image Dehazing and Object Detection in...

引用

15th Asian Conference on computer Vision, ACCV 2020

作者： Zhang, Zhengxi Zhao, Liang Liu, Yunan Zhang, Shanshan Yang, Jian PCA Lab Key Lab of Intelligent Perception and Systems for High -Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9783030695378

It is an important yet challenging task to detect objects on hazy images in real-world applications. The major challenge comes from low visual quality and large haze density variations. In this work, we aim to jointly solve the image dehazing and the object detection tasks in real hazy scenarios by using haze density as prior knowledge. Our proposed Unified Dehazing and Detection (UDnD) framework consists of three parts: a residual-aware haze density classifier, a density-aware dehazing network, and a density-aware object detector. First, the classifier exploits the residuals of hazy images to accurately predict density levels, which provide rich domain knowledge for the subsequent two tasks. Then, we design respectively a High-Resolution Dehazing Network (HRDN) and a Faster R-CNN-based multi-domain object detector to leverage the extracted density information and tackle hazy object detection. Experiments demonstrate that UDnD performs favorably against other methods for object detection in real-world hazy scenes. Also, HRDN achieves better results than state-of-the-art dehazing methods in terms of PSNR and SSIM. Hence, HRDN can conduct haze removal effectively, based on which UDnD is able to provide high-quality detection results. © 2021, Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Signal processing for the 5G Revolution

引用

IEEE SIGNAL processing MAGAZINE 2014年第6期31卷 12-13页

作者： Heath, Robert W., Jr. Leus, Geert Quek, Tony Q. S. Talwar, Shilpa Zhou, Peiying Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China Department of Computer Systems University of São Paulo - USP São Carlos Brazil IRISA Research Institute University of South Brittany - IRISA/UBS Vannes France

The articles in this special section provide an overview of recent advances in signal processing for communication with an emphasis on signal processing techniques that will be relevant for 5G cellular systems. It covers a wide range of topics including modulation, beamforming, cross-layer optimization based on different performance metrics, location-aware communication, cloud computing, and cloud radio access networks. The articles provide a diverse perspective on the potential challenges in 5G cellular systems.

关键词： Special issues and sections 5G mobile communication Next generation networking Wireless communication Cellular networks Wireless cellular networks

来源：评论

学校读者我要写书评

暂无评论

OMEG: Oulu multi-pose eye gaze dataset 19th

OMEG: Oulu multi-pose eye gaze dataset

引用

19th Scandinavian Conference on Image Analysis, SCIA 2015

作者： He, Qiuhai Hong, Xiaopeng Chai, Xiujuan Holappa, Jukka Zhao, Guoying Chen, Xilin Pietikäinen, Matti Department of Computer Science and Engineering University of Oulu Oulu Finland Key Lab of Intelligent Information Processing of the Chinese Academy of Sciences The Institute of Computing Technology of the Chinese Academy of Sciences Beijing China

ISBN: (纸本)9783319196640

Data is in a very important position for pattern recognition tasks including eye gaze estimation. In the literature, most researchers used normal face datasets, which are not specifically designed for eye gaze estimation. As a result, it is difficult to obtain fine labeled eye gaze direction. Therefore large datasets with well-defined gaze directions are desired. To facilitate related researches, we collect and establish the Oulu Multi-pose Eye Gaze Dataset. Inspired by the psychological observation that gaze direction is intrinsically linked with the head orientation, we are devoted to a new data set of eye gaze images captured under multiple head poses. It finally results in a dataset containing over 40K images from 50 subjects, who were asked to fixate on 10 special points on screen under different poses respectively. We investigate a new eye gaze estimation approach by using the IGO based description, and compare it with other popular eye gaze estimation approaches to provide the baseline results on our dataset. © Springer International Publishing Switzerland 2015.

关键词： Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Data-Free Network Debiasing for Long-Tailed Visual Recognition

Data-Free Network Debiasing for Long-Tailed Visual Recogniti...

引用

2022 IEEE International Conference on Multimedia and Expo, ICME 2022

作者： Cai, Jinmian Wang, Zheng Fu, Huazhu Chen, Jingjing Jiang, Yu-Gang School of Computer Science Fudan University Shanghai Key Lab of Intelligent Information Processing China Shanghai Collaborative Innovation Center on Intelligent Visual Computing China Biren Technology IHPC A-STAR

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

Real-world data is often unbalanced and exhibits long-tailed distribution over classes. Vanilla classification models trained on imbalanced datasets inherently exhibit bias towards dominant classes. Existing debiasing methods mostly balance the data or the loss during training. Nevertheless, these data-acquiring methods are not suitable for situations where training data are unavailable. In this paper, we appeal to solutions without access to training data and propose a datafree debiasing (Free-D) method that serves as a plug-and-play module for any standard classification model. Specifically, our method adjusts both the feature representation via feature representation shifting and the classifier weight via class prior compensation in a data-free manner. We evaluate and compare our methods on four long-tailed visual recognition datasets, i.e., long-tailed CIFAR-10/-100, ImageNet-LT, and Places-LT. Extensive experiments demonstrate that the proposed data-free method achieves comparable results of other data-acquired methods. © 2022 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Developing software using a novel event-condition-state pattern framework: Taking mobile input method system As A Case Study

Journal of Software

引用

Journal of Software 2011年第8期6卷 1506-1512页

作者： Zhu, Fei Diao, Hongjun Huang, Wei School of Computer Science and Technology Soochow University Suzhou Jiangsu 215006 China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou Jiangsu 215006 China

Design patterns add more reliability, flexibility and reusability to a software system. Taking advantage of design patterns is usually beneficial to software design and makes software development relatively easier. The state pattern proposed by GoF is not a determined design and can hardly be transformed into implementation code directly. It is disable to cope with sophisticated response event either. Hereby we propose a novel event-conditionstate pattern framework, an event-based finite state machine. The framework improves GoF state pattern by resegmenting Context into two classes, one for management and the other for operation interface. Essential components for implementation, such as management, state transferring, and event triggering mechanism, are also taken into consideration in the framework. We use pattern framework to develop a thirty party input method system which has a Windows Mobile system version and a Symbian system version separately. We rewrote Context part related with system interfaces in the two different systems, and encapsulated the part related with internal logic of input method by concrete subclasses, thus avoiding redundant developing work in both systems and providing convenience for later synchronous updating and maintenance of two input methods. With the pattern framework, much effort during software development is saved. The development logic seems simpler and clearer. As a result, the whole development process is simplified. © 2011 ACADEMY PUBLISHER.

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

Advances in Data and Web Management 1

引用

丛书名： Lecture Notes in computer Science

1000年

作者： Qing Li Ling Feng Jian Pei Sean X. Wang Xiaofang Zhou Qiao-Ming Zhu

ISBN: (数字)9783642006722

ISBN: (纸本)9783642006715

This book constitutes the proceedings of the joint International Conference APWeb/WAIM 2009 which was held in Suzhou, China, during April 1-4, 2009. The 42 full papers presented together with 26 short papers and the abstracts of 2 keynote speeches were carefully reviewed and selected for inclusion in the book. The topics covered are query processing, topic-based techniques, Web data processing, multidimensional data analysis, stream data processing, data mining and its applications, and data management support to advanced applications.

关键词： computer Communication Networks Data Mining and Knowledge Discovery information Systems Applications (incl. Internet) information Storage and Retrieval Pattern Recognition information Systems and Communication Service

来源：评论

学校读者我要写书评

暂无评论

A prompt-based approach to adversarial example generation and robustness enhancement

引用

Frontiers of computer Science 2024年第4期18卷 85-96页

作者： Yuting YANG Pei HUANG Juan CAO Jintao LI Yun LIN Feifei MA Key Lab of Intelligent Information Processing of Chinese Academy of Sciences(CAS) Institute of Computing TechnologyCASBeijing 100190China School of Computer Science and Technology University of Chinese Academy of SciencesBeijing 100049China Department of Computer Science Stanford UniversityCA 94305USA School of Computing National University of SingaporeSingapore 119077Singapore Laboratory of Parallel Software and Computational Science Institute of SoftwareChinese Academy of SciencesBeijing 100190China

Recent years have seen the wide application of natural language processing(NLP)models in crucial areas such as finance,medical treatment,and news media,raising concerns about the model robustness and *** find that prompt paradigm can probe special robust defects of pre-trained language *** prompt texts are first constructed for inputs and a pre-trained language model can generate adversarial examples for victim models via *** results show that prompt paradigm can efficiently generate more diverse adversarial examples besides synonym ***,we propose a novel robust training approach based on prompt paradigm which incorporates prompt texts as the alternatives to adversarial examples and enhances robustness under a lightweight minimax-style optimization *** on three real-world tasks and two deep neural models show that our approach can significantly improve the robustness of models to resist adversarial attacks.

关键词： robustness adversarial example prompt learning pre-trained language model

来源：评论

学校读者我要写书评

暂无评论

An online semantic tree for link detection

引用

Journal of Convergence information technology 2012年第5期7卷 147-157页

作者： He, Ruifang Hong, Yu Information System and Software Engineering Lab School of Computer Science and Technology Tianjin University Tianjin 15001 China Jiangsu Provincial Key Laboratory of Computer Information Processing Technology School of Computer Science and Technology Soochow University Suzhou 215006 China

Link Detection (abbr. LDT) is to determine whether two stories discuss the same topic in Topic Detection and Tracking (abbr. TDT) track. The key issue is to correctly measure the relevance between two stories. Most researches on LDT use a series of independent words to describe stories (each story is a text specially discussing news), and the relevance between two stories is determined based on the percentage and weight of overlapping words between them. Although substantial improvement has been achieved, inadequate descriptions of word sense and semantics still have negative influences on the accuracy of LDT. In this paper we propose an online semantic tree, which is hierarchically constructed by the most relevant words extracted from previous story streams. In online semantic tree, word sense is described by a series of words in a sense closed-loop, and semantic relation among words is measured by depth and width of level that words locate in. In LDT, online semantic tree is built for each story, and the relevance between two stories is determined by measuring the KL divergence between their online semantic trees. The method performs quite well on TDT4 corpus. The Min Norm CDet of the method in testing is 0.2274 lower than that of the baseline.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Secure and efficient VSS scheme based on partial broadcast channels

引用

Journal of Computational information Systems 2009年第3期5卷 1149-1155页

作者： Wang, Jialing Zhu, Yanqin Luo, Xizhao School of Computer Science and Technology Soochow University Suzhou 215006 China Jiangsu Provincial Key Laboratory of Computer Information Processing Technology Suzhou 215006 China

In the conventional verifiable secret sharing scheme, a dealer uses point-to-point secure channels to distribute the shares of a secret to a number of participants. Rei and Wang proposed a secret sharing scheme based on partial broadcast channels, which reduced the number of the channels. But it supposed that both the dealer and participants were honest. In this paper, we present a secure and efficient verifiable secret sharing (VSS) scheme based on partial broadcast channels, which solves the problem in Rei and Wang's scheme. Through the analysis of the scheme, we get that it is secure and efficient, and has the advantage of the number of channels and the total communications needed compared with the conventional verifiable secret sharing scheme. 1553-9105/ Copyright © 2009 Binary information Press.

关键词： Codes (symbols)

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：