检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Wang, Nan Li, Jiwei Meng, Yuxian Sun, Xiaofei Qiu, Han Wang, Ziyao Wang, Guoyin He, Jun Key Laboratory of Data Engineering and Knowledge Engineering of MOE School of Information Renmin University of China China Shannon.AI China Zhejiang University China Tsinghua University China University of Leeds United Kingdom Amazon Alexa AI United States

Semantic Role Labeling (SRL) aims at recognizing the predicate-argument structure of a sentence and can be decomposed into two subtasks: predicate disambiguation and argument labeling. Prior work deals with these two tasks independently, which ignores the semantic connection between the two tasks. In this paper, we propose to use the machine reading comprehension (MRC) framework to bridge this gap. We formalize predicate disambiguation as multiple-choice machine reading comprehension, where the descriptions of candidate senses of a given predicate are used as options to select the correct sense. The chosen predicate sense is then used to determine the semantic roles for that predicate, and these semantic roles are used to construct the query for another MRC model for argument labeling. In this way, we are able to leverage both the predicate semantics and the semantic role semantics for argument labeling. We also propose to select a subset of all the possible semantic roles for computational efficiency. Experiments show that the proposed framework achieves state-of-the-art or comparable results to previous work. Code is available at https://***/ShannonAI/MRC-SRL. © 2021, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Static vulnerabilities detection method based on security state tracing and checking

引用

Jisuanji Xuebao/Chinese Journal of Computers 2009年第5期32卷 899-909页

作者： Liang, Bin Hou, Kan-Kan Shi, Wen-Chang Liang, Zhao-Hui School of Information Renming University of China Beijing 100872 China MOE Key Laboratory of Data Engineering and Knowledge Engineering Beijing 100872 China

The main problem of existing static vulnerability detection methods based source code analysis is their high false positive and false negative rates. One main reason is lack of accurate and effective identification and analysis of security-related program elements, e.g. data validation checking, tainted data source, etc. A static vulnerability detection method based on data security state tracing and checking is proposed. In this method, the state space of state machine model is extended;the security state of a variable is identified by a vector that may correspond to multiple security-related properties rather than by a single property;Fine-grained state transition is provided to support accurate recognition of program security-related behaviors;The recognition of validation checking is introduced in vulnerability state machine to reduce false positives;and a systematic discrimination mechanism for tainted data is constructed to prevent false negatives result from neglecting tainted data sources. The experimental results of a prototype system show that this method can effectively detect buffer overflow and other type's vulnerabilities in software systems, and with obviously lower false positive than existing mainstream static detection methods and avoid some serious false negatives of these methods.

关键词： Static analysis

来源：评论

学校读者我要写书评

暂无评论

Generalized Category Discovery with Large Language Models in the Loop

arXiv

引用

arXiv 2023年

作者： An, Wenbin Shi, Wenkai Tian, Feng Lin, Haonan Wang, QianYing Wu, Yaqiang Cai, Mingxiang Wang, Luyan Chen, Yan Zhu, Haiping Chen, Ping School of Automation Science and Engineering Xi’an Jiaotong University China School of Computer Science and Technology Xi’an Jiaotong University China Ministry of Education Key Laboratory of Intelligent Networks and Network Security China Shaanxi Province Key Laboratory of Big Data Knowledge Engineering China Lenovo Research China University of Massachusetts Boston United States

Generalized Category Discovery (GCD) is a crucial task that aims to recognize both known and novel categories from a set of unlabeled data by utilizing a few labeled data with only known categories. Due to the lack of supervision and category information, current methods usually perform poorly on novel categories and struggle to reveal semantic meanings of the discovered clusters, which limits their applications in the real world. To mitigate the above issues, we propose Loop, an end-to-end active-learning framework that introduces Large Language Models (LLMs) 1 into the training loop, which can boost model performance and generate category names without relying on any human efforts. Specifically, we first propose Local Inconsistent Sampling (LIS) to select samples that have a higher probability of falling to wrong clusters, based on neighborhood prediction consistency and entropy of cluster assignment probabilities. Then we propose a Scalable Query strategy to allow LLMs to choose true neighbors of the selected samples from multiple candidate samples. Based on the feedback from LLMs, we perform Refined Neighborhood Contrastive Learning (RNCL) to pull samples and their neighbors closer to learn clustering-friendly representations. Finally, we select representative samples from clusters corresponding to novel categories to allow LLMs to generate category names for them. Extensive experiments on three benchmark datasets show that Loop outperforms SOTA models by a large margin and generates accurate category names for the discovered clusters. Code and data are available at https://***/Lackel/LOOP. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Enabling Efficient Random Access to Hierarchically-Compressed data

Enabling Efficient Random Access to Hierarchically-Compresse...

引用

International Conference on data engineering

作者： Feng Zhang Jidong Zhai Xipeng Shen Onur Mutlu Xiaoyong Du Key Laboratory of Data Engineering and Knowledge Engineering (MOE) and School of Information Renmin University of China Department of Computer Science and Technology Tsinghua University BNRist Computer Science Department North Carolina State University Department of Computer Science ETH Zürich

ISBN: (数字)9781728129037

ISBN: (纸本)9781728129044

Recent studies have shown the promise of direct data processing on hierarchically-compressed text documents. By removing the need for decompressing data, the direct data processing technique brings large savings in both time and space. However, its benefits have been limited to data traversal operations; for random accesses, direct data processing is several times slower than the state-of-the-art baselines. This paper presents a set of techniques that successfully eliminate the limitation, and for the first time, establishes the feasibility of effectively handling both data traversal operations and random data accesses on hierarchically-compressed data. The work yields a new library, which achieves 3.1× speedup over the state-of-the-art on random data accesses to compressed data, while preserving the capability of supporting traversal operations efficiently and providing large (3.9×) space savings.

关键词： Indexing data processing data structures Technological innovation Dictionaries Law data mining

来源：评论

学校读者我要写书评

暂无评论

Real-time Semantic Segmentation via Spatial-detail Guided Context Propagation

arXiv

引用

arXiv 2020年

作者： Hao, Shijie Zhou, Yuan Guo, Yanrong Hong, Richang Cheng, Jun Wang, Meng Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Ministry of Education School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Chinese University of Hong Kong Hong Kong

Nowadays, vision-based computing tasks play an important role in various real-world applications. However, many vision computing tasks, e.g. semantic segmentation, are usually computationally expensive, posing a challenge to the computing systems that are resource-constrained but require fast response speed. Therefore, it is valuable to develop accurate and real-time vision processing models that only require limited computational resources. To this end, we propose the Spatial-detail Guided Context Propagation Network (SGCPNet) for achieving real-time semantic segmentation. In SGCPNet, we propose the strategy of spatial-detail guided context propagation. It uses the spatial details of shallow layers to guide the propagation of the low-resolution global contexts, in which the lost spatial information can be effectively reconstructed. In this way, the need for maintaining high-resolution features along the network is freed, therefore largely improving the model efficiency. On the other hand, due to the effective reconstruction of spatial details, the segmentation accuracy can be still preserved. In the experiments, we validate the effectiveness and efficiency of the proposed SGCPNet model. On the Citysacpes dataset, for example, our SGCPNet achieves 69.5% mIoU segmentation accuracy, while its speed reaches 178.5 FPS on 768×1536 images on a GeForce GTX 1080 Ti GPU card. In addition, SGCPNet is very lightweight and only contains 0.61 M parameters. The code will be released at https://***/zhouyuan888888/SGCPNet. Copyright © 2020, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Improving Object Detection of Remotely Sensed Multispectral Imagery Via Pan-sharpening 2020

Improving Object Detection of Remotely Sensed Multispectral ...

引用

Proceedings of the 2020 9th International Conference on Computing and Pattern Recognition

作者： Feng Chen Shenlong Lou Yuejun Song College of Computer and Information Engineering Xiamen University of Technology Big Data Institute of Digital Natural Disaster Monitoring in Fujian Xiamen University of Technology Xiamen China and Fujian Key Laboratory of Sensing and Computing for Smart Cities School of Informatics Xiamen University Xiamen China UNISOC Pudong New Area Shanghai China Jiangxi Key Laboratory of Soil Erosion and Prevention Jiangxi Institute of Soil and Water Conservation Nanchang Jiangxi Province China

ISBN: (纸本)9781450387835

Pan-sharpening is used to fuse multispectral images with low spatial resolution and a panchromatic (Pan) image with high spatial resolution to generate synthesized images featured with high spatial and multispectral properties. The pan-sharpened images are assumed valuable for further application. However, there have been a few investigations on the effectiveness of the pan-sharpened products in practice (i.e. object detection), compared with the fact many algorithms for pan-sharpening have been developed. In this paper, improvements contributed by pan-sharpening process for the object detection in multispectral imagery were investigated. Original multispectral images along with the corresponding Pan images acquired by Gaojing-1 (SuperView-1, as the first sub-meter high-resolution commercial remote sensing satellite independently developed in China) satellite were used. Seven algorithms widely used in pan-sharpening were applied separately and compared, while the object detection experiments were done by implementing Faster RCNN. The preliminary findings show: (1) the pan-sharpened images present obviously positive contribution to object detection with Faster RCNN, compared to the original multispectral images; (2) detection results of the pan-sharpened images vary with the algorithms used in pan-sharpening process. Furthermore, this investigation suggests none of the pan-sharpening algorithms showed absolute advantages in image fusion to achieve better object detection consequently.

关键词： SuperView-1 multispectral imagery spatial resolution Faster RCNN Pan-sharpening

来源：评论

学校读者我要写书评

暂无评论

Learning Group-Disentangled Representation for Interpretable Thoracic Pathologic Prediction

Learning Group-Disentangled Representation for Interpretable...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Hao Li Yirui Wu Hexuan Hu Hu Lu Yong Lai Shaohua Wan Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University College of Computer and Information Hohai University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University School of Computer Science and Communication Engineering Jiangsu University Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

Deep learning methods have shown significant performance in medical image analysis tasks. However, they generally act like ”black box” without explanations in both feature extraction and decision processes, leading to lack of clinical insights and high risk assessments. To aid deep learning in envisioning diseases with visual clues, we propose Representation Group-Disentangling Network (RGD-Net), which can completely disentangle feature space of input X-ray images into several independent feature groups, each corresponding to a specific disease. Taking several semantically related and labeled X-ray images as input, RGD-Net firstly extracts completely group-disentangled representations of diseases through Group-Disentangle Module, which applies group-swap and linking operations to construct latent space by enforcing semantic consistency of attributes. To prevent learning degenerate representations defined as shortcut problem, we further introduce adversarial constricts on mapping from features to diseases, thus avoiding model collapse with former free-form disentanglement. Experiments on chestxray-14 and ChestXpert datasets demonstrate that RGD-Net are effective in predicting diseases with remarkable advantages, which leverage potential factors contributing to different diseases, thus enhancing interpretability in working patterns of deep learning methods.

关键词： Deep learning Training Visualization Image analysis Semantics Feature extraction Risk management

来源：评论

学校读者我要写书评

暂无评论

Object Level Depth Reconstruction for Category Level 6D Object Pose Estimation From Monocular RGB Image

arXiv

引用

arXiv 2022年

作者： Fan, Zhaoxin Song, Zhenbo Xu, Jian Wang, Zhicheng Wu, Kejian Liu, Hongyan He, Jun Key Laboratory of Data Engineering and Knowledge Engineering of MOE School of Information Renmin University of China Beijing100872 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Department of Management Science and Engineering Tsinghua University Beijing100084 China Nreal China

Recently, RGBD-based category-level 6D object pose estimation has achieved promising improvement in performance, however, the requirement of depth information prohibits broader applications. In order to relieve this problem, this paper proposes a novel approach named Object Level Depth reconstruction Network (OLD-Net) taking only RGB images as input for category-level 6D object pose estimation. We propose to directly predict object-level depth from a monocular RGB image by deforming the category-level shape prior into object-level depth and the canonical NOCS representation. Two novel modules named Normalized Global Position Hints (NGPH) and Shape-aware Decoupled Depth Reconstruction (SDDR) module are introduced to learn high fidelity object-level depth and delicate shape representations. At last, the 6D object pose is solved by aligning the predicted canonical representation with the back-projected object-level depth. Extensive experiments on the challenging CAMERA25 and REAL275 datasets indicate that our model, though simple, achieves state-of-the-art performance. Copyright © 2022, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

amAssist: In-IDE ambient search of online programming resources

amAssist: In-IDE ambient search of online programming resour...

引用

IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)

作者： Hongwei Li Xuejiao Zhao Zhenchang Xing Lingfeng Bao Xin Peng Dongjing Gao Wenyun Zhao Shanghai Key Laboratory of Data Science Fudan University Shanghai China School of Computer Information Engineering Jiangxi Normal University Nanchang China School of Computer Engineering Nanyang Technological University Singapore College of Computer Science Zhejiang University Hangzhou China

ISBN: (纸本)9781479984701

Developers work in the IDE, but search online resources in the web browser. The separation of the working and search context often cause the ignorance of the working context during online search. Several tools have been proposed to integrate the web browser into the IDE so that developers can search and use online resources directly in the IDE. These tools enable only the shallow integration of the web browser and the IDE. Some tools allow the developer to augment search queries with program entities in the current snapshot of the code. In this paper, we present an in-IDE ambient search agent to bridge the separation of the developer's working context and search context. Our approach considers the developers' working context in the IDE as a time-series stream of programming event observed from the developer's interaction with the IDE over time. It supports the deeper integration of the working context in the entire search process from query formulation, custom search, to search results refinement and representation. We have implemented our ambient search agent and integrate it into the Eclipse IDE. We conducted a user study to evaluate our approach and the tool support. Our evaluation shows that our ambient search agent can better aid developers in searching and using online programming resources while working in the IDE.

关键词： Context Web pages Programming Browsers Search engines Google Libraries

来源：评论

学校读者我要写书评

暂无评论

A better constant approximation for minimum 3-connected m-dominating set problem in unit disk graph using Tutte decomposition

A better constant approximation for minimum 3-connected m-do...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE Computer and Communications Societies

作者： Wei Wang Bei Liu Donghyun Kim Deying Li Jingyi Wang Yaolin Jiang School of Mathematics and Statistics Xi'an Jiaotong University Xi'an China Department of Mathematics and Physics North Carolina Central University Durham USA Key Laboratory of Data Engineering and Knowledge Engineering (Renmin University) Renmin University of China Beijing P.R. China

Over years, virtual backbone has attracted lots of attentions as a promising approach to deal with the broadcasting storm problem in wireless networks. One popular way to construct a quality virtual backbone is to solve the minimum connected dominating set problem. However, a virtual backbone computed in this way is not resilient against topology change since the induced graph by the connected dominating set is one-vertex-connected. As a result, the minimum k-connected m-dominating set problem is introduced to construct a fault-tolerant virtual backbone. Currently, the best known approximation algorithm for the problem in unit disk graph assumes k ≤ 3 and m ≥ 1 and its performance ratio is 280 when k = m = 3. In this paper, we use a classical result from graph theory, Tutte decomposition, to design a new approximation algorithm for the problem in unit disk graph for k ≤ 3 and m ≥ 3. In particular, the algorithm features with much simpler structure and much smaller performance ratio, e.g. nearly 66 when k = m = 3. We also conduct simulation to evaluate the performance of our algorithm.

关键词： Particle separators Approximation algorithms Algorithm design and analysis Approximation methods Wireless networks Conferences Computers

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：