检索结果-内蒙古大学图书馆

2022 IEEE International Conference on Multimedia and Expo, ICME 2022

作者： Ma, Bole Tong, Chao School of Computer Science and Engineering Beihang University China Beihang University State Key Laboratory of Software Development Environment China Yunnan Key Laboratory of Blockchain Application Technology China

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

Multimodal networks that juxtapose visual and linguistic modalities are currently widely adopted for solving vision-and-language tasks. They perform well in simple and intu-itive tasks, but are prone to mistakes in tasks involving latent or implicit details, due to the difficulty of capturing crucial but imperceptible visual signals in the real world. Perception errors lead to nonsensical results, but can be corrected by commonsense knowledge. To this end, we combine visual perception and linguistic commonsense to solve the challenging daily events causality reasoning task. We propose a novel Object-Aware Reasoning Network to focus on object inter-action while ignoring distracting information to refine visual perception. Further, a language branch with an independent prediction head is supervised to learn causality commonsense to help correct obvious perception errors, resulting in more plausible conclusions. Extensive experiments demonstrate that our method achieves new state-of-the-art results on Vis-Causal dataset. © 2022 IEEE.

关键词： Linguistics

来源：评论

学校读者我要写书评

暂无评论

Model learning:a survey of foundations,tools and applications

引用

Frontiers of computer science 2021年第5期15卷 71-92页

作者： Shahbaz ALI Hailong SUN Yongwang ZHAO Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing 100191China SKLSDE School of Computer Science and EngineeringBeihang UniversityBeijing 100191China School of Software Beihang UniversityBeijing 100191China School of Cyber Science and Technology College of Computer ScienceZhejiang UniversityHangzhou 310058China

software systems are present all around us and playing their vital roles in our daily *** correct functioning of these systems is of prime *** addition to classical testing techniques,formal techniques like model checking are used to reinforce the quality and reliability of software ***,obtaining of behavior model,which is essential for model-based techniques,of unknown software systems is a challenging *** mitigate this problem,an emerging black-box analysis technique,called Model Learning,can be *** complements existing model-based testing and verification approaches by providing behavior models of blackbox systems fully *** paper surveys the model learning technique,which recently has attracted much attention from researchers,especially from the domains of testing and ***,we review the background and foundations of model learning,which form the basis of subsequent ***,we present some well-known model learning tools and provide their merits and shortcomings in the form of a comparison ***,we describe the successful applications of model learning in multidisciplinary fields,current challenges along with possible future works,and concluding remarks.

关键词： model learning active automata learning automata learning libraries/tools inferring behavior models testing and formal verification

来源：评论

学校读者我要写书评

暂无评论

Stealthy and Robust Backdoor Attack against 3D Point Clouds through Additional Point Features

arXiv

引用

arXiv 2024年

作者： Ning, Xiaoyang Xie, Qing Xu, Jinyu Jiang, Wenbo Li, Jiachen Ma, Yanchun School of Computer Science and Artificial Intelligence Wuhan University of Technology China Engineering Research Center of Intelligent Service Technology for Digital Publishing Ministry of Education China School of Computer Science and Engineering University of Electronic Science and Technology of China China Wuhan Vocational College of Software and Engineering China

Recently, 3D backdoor attacks have posed a substantial threat to 3D Deep Neural Networks (3D DNNs) designed for 3D point clouds, which are extensively deployed in various security-critical applications. Although the existing 3D backdoor attacks achieved high attack performance, they remain vulnerable to preprocessing-based defenses (e.g., outlier removal and rotation augmentation) and are prone to detection by human inspection. In pursuit of a more challenging-to-defend and stealthy 3D backdoor attack, this paper introduces the Stealthy and Robust Backdoor Attack (SRBA), which ensures robustness and stealthiness through intentional design considerations. The key insight of our attack involves applying a uniform shift to the additional point features of point clouds (e.g., reflection intensity) widely utilized as part of inputs for 3D DNNs as the trigger. Without altering the geometric information of the point clouds, our attack ensures visual consistency between poisoned and benign samples, and demonstrate robustness against preprocessing-based defenses. In addition, to automate our attack, we employ Bayesian Optimization (BO) to identify the suitable trigger. Extensive experiments suggest that SRBA achieves an attack success rate (ASR) exceeding 94% in all cases, and significantly outperforms previous SOTA methods when multiple preprocessing operations are applied during training. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

GNNMF-ATAC: A Web Server-Based ATAC-seq Motif Finding and Annotation Analysis 25

GNNMF-ATAC: A Web Server-Based ATAC-seq Motif Finding and An...

引用

Proceedings of the 2025 5th International Conference on Bioinformatics and Intelligent Computing

作者： Shuangquan Zhang Jinxin Jia Peng Gao Xuan Li Yan Wang School of Cyber Science and Engineering Nanjing University of Science and Technology Nanjing Jiangsu China College of Software Jilin University Changchun Jilin China College of Computer Science and Technology Jilin University Changchun Jilin China

ISBN: (纸本)9798400712203

Transcription Factor Binding Sites (TFBSs) are specific DNA sequences that promote or inhibit gene expression via binding regions, thereby affecting protein synthesis. TFBSs play a crucial role in gene regulatory networks, complex diseases, and the growth of humans. Assay for Transposase-Accessible Chromatin with high-throughput Sequencing (ATAC-seq) is a high-throughput sequencing technology, providing a new perspective for studying transcription factor binding patterns (motifs). Different from sequencing ChIP-seq technologies, ATAC-seq is more efficient in detecting binding sites. Methods based on graph neural network have success on ATAC-seq motifs, but researchers make considerable effort to deploy these models. To address this issue, we developed a web server named GNNMF-ATAC for users. GNNMF-ATAC provides TFBSs prediction, motif finding, and enrichment analysis via deploying tools. Moreover, GNNMF-ATAC provides motif finding results and visualizations of 200 humans and 80 mouse ENCODE ATAC-seq datasets. GNNMF-ATAC is a valuable resource for experimental biologists seeking a user-friendly tool to find ATAC-seq motifs without programming expertise. GNNMF-ATAC is freely available at http://***.

关键词： ATAC-seq

来源：评论

学校读者我要写书评

暂无评论

Pipeline Representation Using Generic Parallel Algorithms in Heterogeneous Parallel Computing. A comparative analysis 36

Pipeline Representation Using Generic Parallel Algorithms in...

引用

36th European Modeling and Simulation Symposium, EMSS 2024, Held at the 21st International Multidisciplinary Modeling and Simulation Multiconference, I3M 2024

作者： Rossainz-López, Mario Sánchez-Rinza, Bárbara López-Sosa, Zuriel Capel-Tuñon, Manuel Faculty of Computer Science Autonomous University of Puebla Av. San Claudio and 14 Sur Street San Manuel PueblaC.P. 72570 Mexico Software Engineering Department College of Informatics and Telecommunications ETSIIT University of Granada Daniel Saucedo Aranda s/n Granada18071 Spain

ISBN: (纸本)9791281988026

Using Parallel Objects and Structured Parallel Programming, the parallel representation of the Communication Pattern between Processes called Pipeline is shown, whose implementation is carried out through different models of Generic Parallel Algorithms within Heterogeneous Parallel Computing (HPC): As a Parallel Design Pattern or PDP, as High-Level Parallel Composition or HLPC and as Flow Graph Interfaces or FGI through programming with message passing. An original and effective development methodology for new programmers in parallelism is proposed for each of them. In these three proposals for Generic Parallel Algorithms, the same problem-example is solved as a case study, and a comparative analysis of their models and designs is carried out, as well as the performance obtained in the execution of said proposals and demonstrate their usefulness, programmability, and performance. The objective of this work is to provide the programmer and/or novice user with different multicore programming approaches so that without much effort they can develop their programs according to a sequential programming style, obtaining automatically, easily and the counterpart parallelization of your code with the help of a specific programming environment like the one proposed. © 2024 The Authors.

关键词： Structured programming

来源：评论

学校读者我要写书评

暂无评论

UniSleepPos: Sleep Posture Identification System Utilizing Millimeter-wave Radar

UniSleepPos: Sleep Posture Identification System Utilizing M...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Kun Liu Min Li Chu He Xu Tian Junbin Mao Min Zeng Jin Liu Xinjiang Engineering Research Center of Big Data and Intelligent Software School of Software Xinjiang University Urumqi China Hunan Provincial Key Lab on Bioinformatics School of Computer Science and Engineering Central South University Changsha China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Sleep posture identification is crucial for accurately assessing sleep quality and diagnosing related diseases. In the realm of non-intrusive sleep monitoring, non-contact technologies are becoming increasingly mainstream. Millimeter-wave radar is frequently utilized in sleep posture identification due to its high resolution, strong penetration, and excellent sensitivity. However, traditional radar-based methods for sleep posture identification often struggle with reliability when dealing with diverse individuals and complex sleep environments. To address these challenges, we propose UniSleepPos, which designs a novel dual-view fusion mechanism to integrate depression and elevation angle signals obtained from radar, thus accurately capturing the posture information of the monitored subject in three-dimensional space. Furthermore, we combine sleep posture identification with individual characteristics, utilizing existing individual labels as prior knowledge to assist in sleep posture identification. The integration of prior knowledge provides a valuable information source for the model, helping to enhance its understanding of the data and improve its performance. We collected sleep posture data from eight volunteers using millimeter-wave radar devices under various environmental conditions. Leave-one-subject-out experiments were conducted to validate the effectiveness of UniSleepPos. The results indicated that UniSleepPos significantly outperforms existing methods, demonstrating its potential for practical applications.

关键词： Performance evaluation Sensitivity Spaceborne radar Millimeter wave radar Depression Data models Reliability Monitoring Signal resolution Diseases

来源：评论

学校读者我要写书评

暂无评论

ROTATION HAS TWO SIDES: EVALUATING DATA AUGMENTATION FOR DEEP ONE-CLASS CLASSIFICATION 12

ROTATION HAS TWO SIDES: EVALUATING DATA AUGMENTATION FOR DEE...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Wang, Guodong Wang, Yunhong Bao, Xiuguo Huang, Di State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China Natl. Comp. Net. Emer. Resp. Tech. Team/Coord. Ctr. of China Beijing China

One-class classification (OCC) involves predicting whether a new data is normal or anomalous based solely on the data from a single class during training. Various attempts have been made to learn suitable representations for OCC within a self-supervised framework. Notably, discriminative methods that use geometric visual transformations, such as rotation, to generate pseudo-anomaly samples have exhibited impressive detection performance. Although rotation is commonly viewed as a distribution-shifting transformation and is widely used in the literature, the cause of its effectiveness remains a mystery. In this study, we are the first to make a surprising observation: there exists a strong linear relationship (Pearson's Correlation, r > 0.9) between the accuracy of rotation prediction and the performance of OCC. This suggests that a classifier that effectively distinguishes different rotations is more likely to excel in OCC, and vice versa. The root cause of this phenomenon can be attributed to the transformation bias in the dataset, where representations learned from transformations already present in the dataset tend to be less effective, making it essential to accurately estimate the transformation distribution before utilizing pretext tasks involving these transformations for reliable self-supervised representation learning. To the end, we propose a novel two-stage method to estimate the transformation distribution within the dataset. In the first stage, we learn general representations through standard contrastive pre-training. In the second stage, we select potentially semantics-preserving samples from the entire augmented dataset, which includes all rotations, by employing density matching with the provided reference distribution. By sorting samples based on semantics-preserving versus shifting transformations, we achieve improved performance on OCC benchmarks. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Rotation

来源：评论

学校读者我要写书评

暂无评论

A Probabilistic Framework for Pruning Transformers Via a Finite Admixture of Keys 48

A Probabilistic Framework for Pruning Transformers Via a Fin...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Nguyen, Tan M. Nguyen, Tam Bui, Long Do, Hai Nguyen, Duy Khuong Le, Dung D. Tran-The, Hung Ho, Nhat Osher, Stan J. Baraniuk, Richard G. University of California Department of Mathematics Los Angeles United States Rice University Department of Electrical and Computer Engineering Houston United States Fpt Software Ai Center Ha Noi Viet Nam Vin University College of Engineering and Computer Science Viet Nam Deakin University Applied Artificial Intelligence Institute Geelong Australia The University of Texas Department of Statistics and Data Sciences Austin United States

ISBN: (纸本)9781728163277

Pairwise dot product-based self-attention is key to the success of transformers which achieve state-of-the-art performance across a variety of applications in language and vision, but are costly to compute. It has been shown that most attention scores and keys in transformers are redundant and can be removed without loss of accuracy. In this paper, we develop a novel probabilistic framework for pruning attention scores and keys in transformers. We first formulate an admixture model of attention keys whose input data to be clustered are attention queries. We show that attention scores in self-attention correspond to the posterior distribution of this model when attention keys admit a uniform prior distribution. We then relax this uniform prior constraint and let the model learn these priors from data, resulting in a new Finite Admixture of Keys (FiAK). The learned priors are used for pruning away redundant attention scores and keys in the baseline transformers, improving the diversity of attention patterns that the models capture. We corroborate the efficiency of transformers pruned with FiAK on the ImageNet object classification and WikiText-103 language modeling tasks. Our experiments demonstrate that transformers pruned with FiAK yield similar or better accuracy than the baseline dense transformers while being much more efficient in terms of memory and computational cost. © 2023 IEEE.

关键词： admixture models pruning Transformers

来源：评论

学校读者我要写书评

暂无评论

Combining State-of-The-Art Pre-Trained Deep Learning Models: A Noble Approach for Bangla Sign Language Recognition Using Max Voting Ensemble

SSRN

引用

SSRN 2024年

作者： Humaun, Md. Kabir Musa Miah, Abu Saleh Hadiuzzaman, Md. Shin, Jungpil Department of Computer Science and Engineering Bangamata Sheikh Fojilatunnesa Mujib Science & Technology University Jamalpur2012 Bangladesh School of Computer Science and Engineering The University of Aizu Aizuwakamatsu Fukushima965-8580 Japan Software Engineer at HeavyTask LLC DallasTX United States

Sign language is a crucial medium of communication for individuals with hearing impairments. Recently, many researchers have been working to develop an automatic sign language recognition system for English, Arabic, and Japanese languages to ease communication complexity between deaf and non-deaf communities. However, few systems have been developed for Bangla sign language(BdSL), and most of the existing ones may face difficulties in achieving satisfactory performance. While recent advances in deep learning have dramatically improved image classification tasks, including sign language recognition, ensemble methods offer a pathway for further enhancing BdSL accuracy. This study introduces a cutting-edge approach employing the Max Voting Ensemble Technique for robust BdSL recognition. We incorporate a range of cutting-edge, pre-trained deep neural networks, including Xception, InceptionV3, DenseNet121, ResNet50, and MobileNetV2. These models have been extensively trained on BdSL datasets, achieving individual accuracies ranging from 90.20% to 99.00%. Our method leverages the synergistic capabilities of these models by combining their complementary features to elevate classification performance further. In our approach, input images undergo preprocessing for model compatibility. The ensemble integrates the pre-trained models with their architectures and weights preserved. For each skin lesion image under examination, every model produces a prediction. These are subsequently aggregated using the Max Voting Ensemble Technique to yield the final classification, with the majority-voted class serving as the conclusive prediction through comprehensive testing on a diverse dataset. Our ensemble outperformed individual models, attaining 96.52%, thus demonstrating superior BdSL reliability and accuracy. We evaluated the effectiveness of our proposed method on the BdSL-49 and BdSL-38 datasets to ensure its generalizability. Our ensemble method delivers a robust, reliable and ef

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Survey on the Emerging Trend of Human Microchip Implants And Their Potential

A Survey on the Emerging Trend of Human Microchip Implants A...

引用

Advances in science and engineering Technology International Conferences (ASET)

作者： Ltifa Mohammed Khalifa Al Mansouri Fady Alnajjar Department of Computer Science and Software Engineering College of IT United Arab Emirates University Al Ain UAE

Human microchip implants are small devices that are implanted into the body for various purposes including storing and transmitting information, monitoring health or location, and providing access to facilities or systems. Although human microchip implants offer numerous advantages, their adoption remains low in the public sector. This article presents a comprehensive survey on the emerging trend of human microchip implants and their potential uses in various fields. In addition to introducing the general concept of microchip implants, the work discusses their current and potential future applications. To better understand the direction of this trend, recent case studies of existing applications of human microchip implants are analyzed and presented. The article also explores the barriers to the adoption of human microchip implants and discusses their potential impact on humans, whether positive or negative.

关键词：

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：