检索结果-内蒙古大学图书馆

29th International Conference on Computational Linguistics, COLING 2022

作者： Gui, Xiangyu Zhao, Feng Jin, Langjunqing Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China

Knowledge representation learning is a key step required for link prediction tasks with knowledge graphs (KGs). During the learning process, the semantics of each entity are embedded by a vector or a point in a feature space. The distance between these points is a measure of semantic similarity. However, in a KG, while two entities may have similar semantics in some relations, they have different semantics in others. It is ambiguous to assign a fixed distance to depict the variant semantic similarity of entities. To alleviate the semantic ambiguity in KGs, we design a new embedding approach named OpticE, which is derived from the well-known physical phenomenon of optical interference. It is a lightweight and relation-adaptive model based on coherence theory, in which each entity’s semantics vary automatically regarding different relations. In addition, a unique negative sampling method is proposed to combine the multimapping properties and self-adversarial learning during the training process. The experimental results obtained on practical KG benchmarks show that the OpticE model, with elegant structures, can compete with existing link prediction methods. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

DarkSAM: fooling segment anything model to segment nothing 24

DarkSAM: fooling segment anything model to segment nothing

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Ziqi Zhou Yufei Song Minghui Li Shengshan Hu Xianlong Wang Leo Yu Zhang Dezhong Yao Hai Jin National Engineering Research Center for Big Data Technology and System and Services Computing Technology and System Lab and Cluster and Grid Computing Lab and School of Computer Science and Technology Huazhong University of Science and Technology School of Cyber Science and Engineering Huazhong University of Science and Technology School of Software Engineering Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System and Services Computing Technology and System Lab and Hubei Engineering Research Center on Big Data Security and Hubei Key Laboratory of Distributed System Security and School of Cyber Science and Engineering Huazhong University of Science and Technology School of Information and Communication Technology Griffith University

ISBN: (纸本)9798331314385

Segment Anything Model (SAM) has recently gained much attention for its outstanding generalization to unseen data and tasks. Despite its promising prospect, the vulnerabilities of SAM, especially to universal adversarial perturbation (UAP) have not been thoroughly investigated yet. In this paper, we propose DarkSAM, the first prompt-free universal attack framework against SAM, including a semantic decoupling-based spatial attack and a texture distortion-based frequency attack. We first divide the output of SAM into foreground and background. Then, we design a shadow target strategy to obtain the semantic blueprint of the image as the attack target. DarkSAM is dedicated to fooling SAM by extracting and destroying crucial object features from images in both spatial and frequency domains. In the spatial domain, we disrupt the semantics of both the foreground and background in the image to confuse SAM. In the frequency domain, we further enhance the attack effectiveness by distorting the high-frequency components (i.e., texture information) of the image. Consequently, with a single UAP, DarkSAM renders SAM incapable of segmenting objects across diverse images with varying prompts. Experimental results on four datasets for SAM and its two variant models demonstrate the powerful attack capability and transferability of DarkSAM. Our codes are available at: https://***/CGCL-codes/DarkSAM.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A data DRIVEN TOOL TO SUPPORT DESIGN TEAM COMPOSITION MEASURING SKILLS DIVERSITY 24

A DATA DRIVEN TOOL TO SUPPORT DESIGN TEAM COMPOSITION MEASUR...

引用

24th International Conference on engineering Design, ICED 2023

作者： Chiarello, Filippo Spada, Irene Barandoni, Simone Giordano, Vito Fantoni, Gualtiero School of Engineering Department of Energy Systems Land and Construction Engineering University of Pisa Italy School of Engineering Department of Civil and Industrial Engineering University of Pisa Italy School of Engineering Department of Engineering Informatics University of Pisa Italy Department of Informatics University of Pisa Italy B4DS - Business Engineering for Data Science Lab University of Pisa Italy

Team composition in Project Based Learning is the first task for the class and has a great impact on the learning experience. Anyway, little space is dedicated in literature about team composition, considering their personal inclinations towards design tasks. For these reasons we propose a tool that aims to map the design skills of students to optimise team composition. The tool is based on a questionnaire grounded in the design theory and aims at measuring the willingness of students at performing certain design tasks. The results of the questionnaires are analysed using Principal Component Analysis to normalise each students' answers to the whole class, and to show the distribution of students in the space of engineering design skills. We present the design process of the tool, and a first experimentation on two classes of master's degree students in Management engineering and data science, testing the tool on a total of 72 students. The results are promising and demonstrate the robusteness of the questionnaire and of the analytical method. Also, we propose next steps for our research activity, calling for other researchers to test our method in different contexts. © The Author(s), 2023. Published by Cambridge University Press.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

AsT: An Asymmetric-Sensitive Transformer for Osteonecrosis of the Femoral Head Detection 37

AsT: An Asymmetric-Sensitive Transformer for Osteonecrosis o...

引用

37th AAAI Conference on Artificial Intelligence, AAAI 2023

作者： Chen, Haoyang Liu, Shuai Lu, Feng Li, Wei Sheng, Bin Li, Mi Jin, Hai Zomaya, Albert Y. National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China Centre for Distributed and High Performance Computing School of Computer Science The University of Sydney Australia Department of Computer Science and Engineering Shanghai Jiao Tong University China Tongji Hospital Tongji Medical College Huazhong University of Science and Technology China

ISBN: (纸本)9781577358800

Early diagnosis of osteonecrosis of the femoral head (ONFH) can inhibit the progression and improve femoral head preservation. The radiograph difference between early ONFH and healthy ones is not apparent to the naked eye. It is also hard to produce a large dataset to train the classification model. In this paper, we propose Asymmetric-Sensitive Transformer (AsT) to capture the uneven development of the bilateral femoral head to enable robust ONFH detection. Our ONFH detection is realized using the self-attention mechanism to femoral head regions while conferring sensitivity to the uneven development by the attention-shared transformer. The real-world experiment studies show that AsT achieves the best performance of AUC 0.9313 in the early diagnosis of ONFH and can find out misdiagnosis cases firmly. Copyright © 2023, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

MatchPrompt: Prompt-based Open Relation Extraction with Semantic Consistency Guided Clustering

MatchPrompt: Prompt-based Open Relation Extraction with Sema...

引用

2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022

作者： Wang, Jiaxin Zhang, Lingling Liu, Jun Liang, Xi Zhong, Yujie Wu, Yaqiang Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering School of Computer Science and Technology Xi'an Jiaotong University China National Engineering Lab for Big Data Analytics Xi'an Jiaotong University China Lenovo Research Beijing China

Relation clustering is a general approach for open relation extraction (OpenRE). Current methods have two major problems. One is that their good performance relies on large amounts of labeled and pre-defined relational instances for pre-training, which are costly to acquire in reality. The other is that they only focus on learning a high-dimensional metric space to measure the similarity of novel relations and ignore the specific relational representations of clusters. In this work, we propose a new prompt-based framework named MatchPrompt, which can realize OpenRE with efficient knowledge transfer from only a few predefined relational instances as well as mine the specific meanings for cluster interpretability. To our best knowledge, we are the first to introduce a prompt-based framework for unlabeled clustering. Experimental results on different datasets show that MatchPrompt achieves the new SOTA results for OpenRE. © 2022 Association for Computational Linguistics.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Markerless Motion Capture System for Stroke Gait Analysis 2

Markerless Motion Capture System for Stroke Gait Analysis

引用

2nd International Conference on Biomedical and Intelligent Systems, IC-BIS 2023

作者： Xu, Shengqian Wang, Daoyuan Huang, Xiongang Yang, Zhihao Lin, Jian Ning, Gangmin Department of Biomedical Engineering Zhejiang University Hangzhou310027 China Department of Rehabilitation Zhejiang Hospital Hangzhou310013 China Research Center for Healthcare Data Science Zhejiang Lab. Hangzhou311121 China

ISBN: (纸本)9781510666733

Stroke patients commonly suffered from motor impairments, and gait analysis is crucial for the effective guidance of post-stroke rehabilitation. However, most existing 3D gait analysis systems require the attachment of optical markers to the body, and the systems are costly and spatially intensive. These restricted the use of the systems in general hospitals and communities. To address this issue, this study developed an affordable and markerless system to examine the gait characteristics of stroke patients, which was constructed by depth camera of Microsoft Azure Kinect, instrumented walkway, and analysis software. Spatiotemporal and kinematic parameters were measured directly, while kinetic parameters were derived via inverse dynamics using a 14-segment human body model. Sixteen healthy individuals and eight stroke patients were recruited for tests. The results showed that due to weakened lower limb strength in stroke patients, their peak joint moments, joint angles, and joint angular velocities decreased compared with healthy individuals. Consequently, stroke patients walked with reduced stride length, cadence, and single support time. Furthermore, the differences between the paretic and non-paretic sides of stroke patients were primarily observed at the knee joint (peak joint angle, angular velocity, and moment were significantly smaller compared to the non-paretic side) during swing phase. This suggests that rehabilitation training for stroke patients should place importance on knee joint. These findings demonstrate the significant potential of the present system in the gait analysis for stroke patients. © 2023 SPIE.

关键词： Kinematics

来源：评论

学校读者我要写书评

暂无评论

Intersecting-boundary-sensitive fingerprinting for tampering detection of DNN models 24

Intersecting-boundary-sensitive fingerprinting for tampering...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Xiaofan Bai Chaoxiang He Xiaojing Ma Bin Benjamin Zhu Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System and Services Computing Technology and System Lab and Hubei Engineering Research Center on Big Data Security and Hubei Key Laboratory of Distributed System Security Microsoft School of Computer Science and Technology Huazhong University of Science and Technology and National Engineering Research Center for Big Data Technology and System and Services Computing Technology and System Lab and Cluster and Grid Computing Lab.

Cloud-based AI services offer numerous benefits but also introduce vulnerabilities, allowing for tampering with deployed DNN models, ranging from injecting malicious behaviors to reducing computing resources. Fingerprint samples are generated to query models to detect such tampering. In this paper, we present Intersecting-Boundary-Sensitive Fingerprinting (IBSF), a novel method for black-box integrity verification of DNN models using only top-1 labels. Recognizing that tampering with a model alters its decision boundary, IBSF crafts fingerprint samples from normal samples by maximizing the partial Shannon entropy of a selected subset of categories to position the fingerprint samples near decision boundaries where the categories in the subset intersect. These fingerprint samples are almost indistinguishable from their source samples. We theoretically establish and confirm experimentally that these fingerprint samples' expected sensitivity to tampering increases with the cardinality of the subset. Extensive evaluation demonstrates that IBSF surpasses existing state-of-the-art fingerprinting methods, particularly with larger subset cardinality, establishing its state-of-the-art performance in black-box tampering detection using only top-1 labels. The IBSF code is available at: https://***/CGCL-codes/IBSF.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring Potential Risks of Cross-Legged Sitting for Adolescent Idiopathic Scoliosis Patients by Assessing Buttock Pressure Distribution 2

Exploring Potential Risks of Cross-Legged Sitting for Adoles...

引用

2nd International Conference on Biomedical and Intelligent Systems, IC-BIS 2023

作者： Wang, Daoyuan Tang, Yang Yang, Zhihao Lin, Jian Ning, Gangmin Department of Biomedical Engineering Zhejiang University Hangzhou310027 China Department of Rehabilitation Zhejiang Hospital Hangzhou310013 China Research Center for Healthcare Data Science Zhejiang Lab. Hangzhou311121 China

ISBN: (纸本)9781510666733

In cases of prolonged sitting, cross-legged posture is commonly used. Cross-legged sitting's causes, benefits, and drawbacks have been studied in the general population, but not in adolescent idiopathic scoliosis (AIS) patients. To address this issue, the buttock pressure distributions of 11 healthy participants and 27 AIS patients were acquired by piezo-resistive sensor array. Pressure parameters, asymmetry index and equilibrium parameters were compared between upright sitting and cross-legged sitting. The results demonstrated that crossing legs promoted relaxation but could also result in high-pressure regions, pelvic deformities and unstable seated postures. These effects were more significant in the AIS group, indicating that AIS patients could receive a higher degree of harm when crossing their legs. According to our research, cross-legged sitting should be avoided, due it can have both short- and long-term negative effects. © 2023 SPIE.

关键词： Pressure distribution

来源：评论

学校读者我要写书评

暂无评论

A Scalable, Efficient, and Robust Dynamic Memory Management Library for HLS-based FPGAs 57

A Scalable, Efficient, and Robust Dynamic Memory Management ...

引用

57th Annual IEEE/ACM International Symposium on Microarchitecture, MICRO 2024

作者： Wang, Qinggang Zheng, Long An, Zhaozeng Xiong, Shuyi Wang, Runze Huang, Yu Yao, Pengcheng Liao, Xiaofei Jin, Hai Xue, Jingling School of Computer Science and Technology Huazhong University of Science and Technology Natl. Eng. Res. Ctr. for Big Data Technol. and Syst./Serv. Comp. Technol. and Syst. Lab/Cluster and Grid Comp. Lab Wuhan430074 China Zhejiang Lab Hangzhou311121 China School of Computer Science and Engineering University of New South Wales SydneyNSW2052 Australia

ISBN: (纸本)9798350350579

Nowadays, high-level synthesis (HLS) has gained prominence for FPGA-based architecture prototyping, enhancing productivity significantly. Despite this advancement, HLS tools are impeded by a critical drawback: They lack support for dynamic memory management (DMM), leading to static mem-ory allocation and suboptimal use of memory resources. In response, numerous efforts have been made to develop DMM solutions compatible with HLS. However, our analysis indicates that existing solutions fail to concurrently meet the desired trifecta of scalability (efficient management of memory of any size), efficiency (minimal latency in memory (de-)allocation), and robustness (low allocation failure rates). This limitation hampers their applicability in real-world scenarios. In this paper, we introduce GraDMM, a 'three-birds-one-stone' solution that comprehensively enhances the scalability, efficiency, and robustness of DMM. The key insight is to formulate memory (de-)allocation as graph analytics and lever-Age sophisticated FPGA-based graph processing techniques. To achieve scalability, GraDMM specializes a simplified pipeline that significantly suppresses resource utilization expansion caused by managed memory scaling. This is crucial for managing arbitrarily sized memory on resource-limited FPGA platforms. For efficiency, GraDMM implements a data-centric concurrent traversal scheme and a shortcut-Assisted fast traversal policy to accelerate (de-)allocation-guided graph traversal, reducing mem-ory (de-)allocation latency. To enhance robustness, GraDMM incorporates an adaptive memory defragmenter that defragments managed memory to minimize fragmentation-induced allocation failures. GraDMM is encapsulated as a library, providing high-level interfaces for users and ensuring synthesizability with Vi-vado HLS. Experimental results demonstrate that GraDMM out-performs three state-of-The-Art HLS-compatible DMM solutions by significant margins: 56.71 %-85.59% in resource consumption savin

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

SELFORMER: MOLECULAR REPRESENTATION LEARNING VIA SELFIES LANGUAGE MODELS

arXiv

引用

arXiv 2023年

作者： Yüksel, Atakan Ulusoy, Erva Ünlü, Atabey Dogan, Tunca Biological Data Science Lab Dept. of Computer Engineering Hacettepe University Turkey

Automated computational analysis of the vast chemical space is critical for numerous fields of research such as drug discovery and material science. Representation learning techniques have recently been employed with the primary objective of generating compact and informative numerical expressions of complex data, for efficient usage in subsequent prediction tasks. One approach to efficiently learn molecular representations is processing string-based notations of chemicals via natural language processing (NLP) algorithms. Majority of the methods proposed so far utilize SMILES notations for this purpose, which is the most extensively used string-based encoding for molecules. However, SMILES is associated with numerous problems related to validity and robustness, which may prevent the model from effectively uncovering the knowledge hidden in the data. In this study, we propose SELFormer, a transformer architecture-based chemical language model that utilizes a 100% valid, compact and expressive notation, SELFIES, as input, in order to learn flexible and high-quality molecular representations. SELFormer is pre-trained on two million drug-like compounds and fine-tuned for diverse molecular property prediction tasks. Our performance evaluation has revealed that, SELFormer outperforms all competing methods, including graph learning-based approaches and SMILES-based chemical language models, on predicting aqueous solubility of molecules and adverse drug reactions, while producing comparable results for the remaining tasks. We also visualized molecular representations learned by SELFormer via dimensionality reduction, which indicated that even the pretrained model can discriminate molecules with differing structural properties. We shared SELFormer as a programmatic tool, together with its datasets and pre-trained models. Overall, our research demonstrates the benefit of using the SELFIES notations in the context of chemical language modeling and opens up new possibilities fo

关键词： Molecules

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：