检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Yang, Zhiyong 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 Computer Science and Tech. University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management CAS China School of Cyber Science and Tech. Sun Yat-sen University Shenzhen Campus China

Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely, diffusion feature. We discover that diffusion feature has been hindered by a hidden yet universal phenomenon that we call content shift. To be specific, there are content differences between features and the input image, such as the exact shape of a certain object. We locate the cause of content shift as one inherent characteristic of diffusion models, which suggests the broad existence of this phenomenon in diffusion feature. Further empirical study also indicates that its negative impact is not negligible even when content shift is not visually perceivable. Hence, we propose to suppress content shift to enhance the overall quality of diffusion features. Specifically, content shift is related to the information drift during the process of recovering an image from the noisy input, pointing out the possibility of turning off-the-shelf generation techniques into tools for content shift suppression. We further propose a practical guideline named GATE to efficiently evaluate the potential benefit of a technique and provide an implementation of our methodology. Despite the simplicity, the proposed approach has achieved superior results on various tasks and datasets, validating its potential as a generic booster for diffusion features. Our code is available at this url. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generating Action-conditioned Prompts for Open-vocabulary Video Action Recognition 24

Generating Action-conditioned Prompts for Open-vocabulary Vi...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Jia, Chengyou Luo, Minnan Chang, Xiaojun Dang, Zhuohang Han, Mingfei Wang, Mengmeng Dai, Guang Dang, Sizhe Wang, Jingdong School of Computer Science and Technology MOEKLINNS Lab Xi'an Jiaotong University Shaanxi Xi'an China University of Science and Technology of China Anhui Hefei China School of Computer Science and Technology Xi'an Jiaotong University Shaanxi Xi'an China ReLER Lab AAII University of Technology Sydney SydneyNSW Australia Zhejiang University of Technology College of Computer Science and Technology China SGIT AI Lab State Grid Corporation of China Beijing China Baidu Inc Beijing China United Arab Emirates Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Xi'an710049 China SGIT AI Lab State Grid Corporation of China China School of Computer Science and Technology Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi'an Jiaotong University Xi'an710049 China

ISBN: (纸本)9798400706868

Exploring open-vocabulary video action recognition is a promising venture, which aims to recognize previously unseen actions within any arbitrary set of categories. Existing methods typically adapt pretrained image-text models to the video domain, capitalizing on their inherent strengths in generalization. A common thread among such methods is the augmentation of visual embeddings with temporal information to improve the recognition of seen actions. Yet, they compromise with standard less-informative action descriptions, thus faltering when confronted with novel actions. Drawing inspiration from human cognitive processes, we argue that augmenting text embeddings with human prior knowledge is pivotal for open-vocabulary video action recognition. To realize this, we innovatively blend video models with Large Language Models (LLMs) to devise Action-conditioned Prompts. Specifically, we harness the knowledge in LLMs to produce a set of descriptive sentences that contain distinctive features for identifying given actions. Building upon this foundation, we further introduce a multi-modal action knowledge alignment mechanism to align concepts in video and textual knowledge encapsulated within the prompts. Extensive experiments on various video benchmarks, including zero-shot, few-shot, and base-to-novel generalization settings, demonstrate that our method not only sets new SOTA performance but also possesses excellent interpretability. © 2024 ACM.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Global context aware RCNN for object detection

arXiv

引用

arXiv 2020年

作者： Zhang, Wenchao Fu, Chong Xie, Haoyu Zhu, Mai Tie, Ming Chen, Junxin School of Computer Science and Engineering Northeastern University Shenyang110819 China Engineering Research Center of Security Technology of Complex Network System Ministry of Education China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang110819 China Science and Technology on Space Physics Laboratory Beijing100076 China College of Medicine and Biological Information Engineering Northeastern University Shenyang110819 China

RoIPool/RoIAlign is an indispensable process for the typical two-stage object detection algorithm, it is used to rescale the object proposal cropped from the feature pyramid to generate a fixed size feature map. However, these cropped feature maps of local receptive fields will heavily lose global context information. To tackle this problem, we propose a novel end-to-end trainable framework, called Global Context Aware (GCA) RCNN, aiming at assisting the neural network in strengthening the spatial correlation between the background and the foreground by fusing global context information. The core component of our GCA framework is a context aware mechanism, in which both global feature pyramid and attention strategies are used for feature extraction and feature refinement, respectively. Specifically, we leverage the dense connection to improve the information flow of the global context at different stages in the top-down process of FPN, and further use the attention mechanism to refine the global context at each level in the feature pyramid. In the end, we also present a lightweight version of our method, which only slightly increases model complexity and computational burden. Experimental results on COCO benchmark dataset demonstrate the significant advantages of our approach. Copyright © 2020, The Authors. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Sample hardness based gradient loss for long-tailed cervical cell detection

arXiv

引用

arXiv 2022年

作者： Liu, Minmin Li, Xuechen Gao, Xiangbo Chen, Junliang Shen, Linlin Wu, Huisi Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence of Robotics of Society Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China University of California Irvine United States

Due to the difficulty of cancer samples collection and annotation, cervical cancer datasets usually exhibit a long-tailed data distribution. When training a detector to detect the cancer cells in a WSI (Whole Slice Image) image captured from the TCT (Thinprep Cytology Test) specimen, head categories (e.g. normal cells and inflammatory cells) typically have a much larger number of samples than tail categories (e.g. cancer cells). Most existing state-of-the-art long-tailed learning methods in object detection focus on category distribution statistics to solve the problem in the long-tailed scenario, without considering the "hardness" of each sample. To address this problem, in this work we propose a Grad-Libra Loss that leverages the gradients to dynamically calibrate the degree of hardness of each sample for different categories, and re-balance the gradients of positive and negative samples. Our loss can thus help the detector to put more emphasis on those hard samples in both head and tail categories. Extensive experiments on a long-tailed TCT WSI image dataset show that the mainstream detectors, e.g. RepPoints, FCOS, ATSS, YOLOF, etc. trained using our proposed Gradient-Libra Loss, achieved much higher (7.8%) mAP than that trained using cross-entropy classification loss. Copyright © 2022, The Authors. All rights reserved.

关键词： Cytology

来源：评论

学校读者我要写书评

暂无评论

Progressive Refinement Bilateral Filter

Progressive Refinement Bilateral Filter

引用

IEEE International Conference on Automation, Electronics and Electrical Engineering (AUTEEE)

作者： Chanyi Lu Yong Zhao Lin Wang Guiying Zhang Fujian Feng Li Zhang College of Data Science and Information Engineering Guizhou Minzu University Guiyang China School of Electronic and Computer Engineering Shenzhen Graduate School of Peking University Shenzhen China Guizhou Key Laboratory of Pattern Recognition and Intelligent System Guizhou Minzu University Guiyang China Department of Medical Information Engineering Zunyi Medical University Zunyi China

ISBN: (纸本)9781538678626;9781538678619

In this paper, a coarse-to-fine framework for image noise removal is proposed. The bilateral filter is redefined by the manner of progressive refining to effectively eliminate noise, thus forming progressive refinement bilateral filter (PRBF), which estimates the pixel values of a noisy image through the method of progressive refinement with gradual recursion and its result retains more details, infinite close to the original image. PRBF is further integrated into the denoising model for the details processing again after denoising of the major part of the image. Our algorithm is evaluated and compared on two large standardized datasets and a number of selected images. The experimental results show that our algorithm consistently outperforms other approaches for image denoising and demonstrates the effectiveness of our framework for stereo matching.

关键词： Noise reduction Image denoising Mathematical model Filtering Filtering algorithms Kernel Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

How to respond to emerging threats of cyberspace security via social engineering? A novel paradigm to solve cyberspace security issues

TechRxiv

引用

TechRxiv 2022年

作者： Lin, Hao Wang, Chun-Dong Gao, Hao-Yu School of Computer Science and Engineering Tianjin University of Technology Tianjin China Tianjin Key Laboratory of Intelligence Computing Novel Software Technology Ministry of Education Tianjin China Engineering Research Center of Learning-Based Intelligent System Ministry of Education Tianjin China College of Data Science and Application Inner Mongolia University of Technology Hohhot China

Cybersecurity researchers always ignore the "people" behind the issues when dealing with cyberspace security issues. The human and technological aspects of cyberspace security must be simultaneously addressed to enable a secure cyber environment. Social engineering is a discipline whose research object is people, and the combination of social engineering and cyberspace security can provide new solution ideas for lots of cyberspace security issues. This paper attempts to answer the question —— "How to solve cyberspace security issues via social engineering?" We briefly review existing frameworks for social engineering attacks and propose a novel, recursive, and iterative framework for social engineering attacks in cyberspace. The existing research achievements of combination of social engineering and cyberspace security were reviewed in the order of cyber personality, hacker psychology, human flesh search, and social engineering defense. To answer this question, we summarized four "guidelines" for using social engineering. Finally, we look ahead, give our thoughts, and discuss answers of the question and future research. It is aimed at getting more researchers of cyberspace security and social science to pay attention to this field. © 2022, CC BY.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

SFDA-rPPG: Source-Free Domain Adaptive Remote Physiological Measurement with Spatio-Temporal Consistency

arXiv

引用

arXiv 2024年

作者： Xie, Yiping Yu, Zitong Wu, Bingjie Xie, Weicheng Shen, Linlin Computer Vision Institute School of Computer Science & Software Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Singapore

Remote Photoplethysmography (rPPG) is a non-contact method that uses facial video to predict changes in blood volume, enabling physiological metrics measurement. Traditional rPPG models often struggle with poor generalization capacity in unseen domains. Current solutions to this problem is to improve its generalization in the target domain through Domain Generalization (DG) or Domain Adaptation (DA). However, both traditional methods require access to both source domain data and target domain data, which cannot be implemented in scenarios with limited access to source data, and another issue is the privacy of accessing source domain data. In this paper, we propose the first Source-free Domain Adaptation benchmark for rPPG measurement (SFDA-rPPG), which overcomes these limitations by enabling effective domain adaptation without access to source domain data. Our framework incorporates a Three-Branch Spatio-Temporal Consistency Network (TSTC-Net) to enhance feature consistency across domains. Furthermore, we propose a new rPPG distribution alignment loss based on the Frequency-domain Wasserstein Distance (FWD), which leverages optimal transport to align power spectrum distributions across domains effectively and further enforces the alignment of the three branches. Extensive cross-domain experiments and ablation studies demonstrate the effectiveness of our proposed method in source-free domain adaptation settings. Our findings highlight the significant contribution of the proposed FWD loss for distributional alignment, providing a valuable reference for future research and applications. The source code is available at https://***/XieYiping66/SFDA-rPPG. Copyright © 2024, The Authors. All rights reserved.

关键词： Photoplethysmography

来源：评论

学校读者我要写书评

暂无评论

基于污点和概率的逃逸恶意软件多路径探索

引用

security and Safety 2023年第3期2卷 83-106页

作者：徐钫洲张网羌卫中金海 National Engineering Research Center for Big Data Technology and System Wuhan 430074China Services Computing Technology and System Lab Cluster and Grid Computing LabWuhan 430074China Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data SecurityWuhan 430074China School of Cyber Science and Engineering Huazhong University of Science and TechnologyWuhan 430074China School of Computer Science and Technology Huazhong University of Science and TechnologyWuhan 430074China Jinyinhu Laboratory Wuhan 430040China

Static analysis is often impeded by malware obfuscation techniques,such as encryption and packing,whereas dynamic analysis tends to be more resistant to obfuscation by leveraging concrete execution ***,malware can employ evasive techniques to detect the analysis environment and alter its behavior *** known evasive techniques can be explicitly dismantled,the challenge lies in generically dismantling evasions without full knowledge of their conditions or implementations,such as logic bombs that rely on uncertain conditions,let alone unsupported evasive techniques,which contain evasions without corresponding dismantling strategies and those leveraging unknown *** this paper,we present Antitoxin,a prototype for automatically exploring evasive *** utilizes multi-path exploration guided by taint analysis and probability calculations to effectively dismantle evasive *** probabilities of branch execution are derived from dynamic coverage,while taint analysis helps identify paths associated with evasive techniques that rely on uncertain ***,Antitoxin prioritizes branches with lower execution probabilities and those influenced by taint analysis for multi-path *** is achieved through forced execution,which forcefully sets the outcomes of branches on selected ***,Antitoxin employs active anti-evasion countermeasures to dismantle known evasive techniques,thereby reducing exploration ***,Antitoxin provides valuable insights into sensitive behaviors,facilitating deeper manual *** experiments on a set of highly evasive samples demonstrate that Antitoxin can effectively dismantle evasive techniques in a generic *** probability calculations guide the multi-path exploration of evasions without requiring prior knowledge of their conditions or implementations,enabling the dismantling of unsupported techniques such as C2 and signific

关键词： Malware analysis dynamic binary instrumentation forced execution taint analysis evasion detection

来源：评论

学校读者我要写书评

暂无评论

Acoustic and Kinematic Examination of Dysarthria in Cantonese Patients of Parkinson’s Disease

Acoustic and Kinematic Examination of Dysarthria in Cantones...

引用

International Symposium on Chinese Spoken Language Processing

作者： Yue Sun Manwa L. Ng Chongyuan Lian Lan Wang Feng Yang Nan Yan College of Big Data and Information Engineering Guizhou University Guiyang China Speech Science Laboratory University of Hong Kong Hong Kong China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China Department of Speech Therapy Shenzhen Children’s Hospital Shenzhen China Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Instimtes of Advanced Technology Chinese Academy of Sciences Shenzhen China

ISBN: (纸本)9781538656280;9781538656273

Hypokinetic dysarthria is one of the core symptoms of Parkinson's disease, characterized by reduced loudness, slurred speech and distorted consonant productions. Dopaminergic medication for Parkinson's disease (PD) has been proven to be effective in treating limb and gross motor movement problems. However, the literature sees contradictory findings regarding dopaminergic effects on speech problems associated with PD. Previous perceptual and acoustic studies of PD hypokinetic dysarthria mostly involved heterogeneous population and variations of speech tasks which complicated data interpretation. Also, the lack of kinematic data limited our understanding of the details of articulation errors associated with PD, as well as the medication effects. Electromagnetic articulography (EMA) enabled the examination of PD articulatory patterns with high degree of accuracy and safety. The aim of the present study was to address these inconsistencies by providing an integrative description of basic kinematic and acoustic parameters of speech production about the dopaminergic effect on early PD speech by using EMA. The results revealed a significant improvement of articulatory function on dopaminergic effects for PD speech, evidenced by increased vowel space, the velocity and accelerated velocity initiation and coordination of articulation during bilabial or alveolar productions.

关键词： Kinematics Acoustics Auditory system Sun Parameter extraction Schedules Lips

来源：评论

学校读者我要写书评

暂无评论

An extraction method of road structure for surveillance Video

An extraction method of road structure for surveillance Vide...

引用

11th International Conference of Chinese Transportation Professionals: Towards Sustainable Transportation systems, ICCTP 2011

作者： Luo, Dong-Hua Zhao, Jian-Hua Li, Xi-Ying Wang, Zhen-Bo School of Information Sciences and Technology Sun Yat-sen University Guangzhou Higher Education Mega Center No. 132 East Outer Ring Road Guangzhou 510006 China Traffic Management Bureau Guangdong Provincial Public Security Department NO.388 Jianpeng Road Baiyun District Guangzhou 510440 China School of Engineering Sun Yat-sen University Guangzhou Higher Education Mega Center No.132 East Outer Ring Road Guangzhou 510006 China Guangdong Provincial Key Laboratory of Intelligent Transportation System Building 312 NO.135 West Xingang Road Guangzhou 510275 China

ISBN: (纸本)9780784411865

The scene of surveillance video is usually wide and variable, and the target vehicles inside it are often small. Surveillance videos usually are not suitable for intelligent video applications, such as video vehicle detection. To solve this problem, an extraction method of road structure for surveillance video is proposed for intelligent applications. The principle of the method is developed to first extract road regions of surveillance videos by accumulating movement regions in video image sequences. Based on it, the left and right borderlines of road regions are pulled out using the Hough transform according to the statistical characteristics of road structure in surveillance video. Experiment results have shown that the road structure can be extracted precisely and effectively from the surveillance video of freeway and city expressway. © 2011 ASCE.

关键词： Hough transforms

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：