检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Yehuan Wang Jiefeng Long Jian Hu Lin Shang Department of Computer Science and Technology State Key Laboratory for Novel Software Technology Nanjing University Nanjing China School of Mechanical Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Image captioning aims to generate fluent and accurate descriptions for images. To evaluate the quality of captions, various metrics have been proposed. However, current metrics only assess captions at sequence-level, which overwhelms the distinctions between each token. Thus, existing objectives tend to treat each token equally, assigning them with identical weights in loss functions. Intuitively, key words in a caption carry the primary information and contribute more than other words to sequence-level metrics. They should be distinguished and weighted more during training. In this work, we propose to explicitly measure each word and guide the model to focus more on key words in captions. Firstly, we devise token-level CIDEr (CIDEr-T) as a new metric to quantify the importance of each word, by decomposing the sequence-level CIDEr into token-level granularity. CIDEr-T maintains consistency with CIDEr and shows the distinctions between tokens. Thus, we engage CIDEr-T scores of each token as their unique weights in the raw loss functions, which can bridge the gap between training and evaluation.

关键词： Measurement Training Accuracy Neural networks

来源：评论

学校读者我要写书评

暂无评论

Amplified locality-sensitive hashing-based recommender systems with privacy protection

Amplified locality-sensitive hashing-based recommender syste...

引用

作者： Chi, Xiaoxiao Yan, Chao Wang, Hao Rafique, Wajid Qi, Lianyong School of Information Science and Engineering Qufu Normal University Rizhao China Department of Computer Science Norwegian University of Science and Technology Gjøvik Norway State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Computer Science and Technology Nanjing University Nanjing China

With the advent of Internet of Things (IoT) age, the variety and volume of web services have been increasing at a fast speed. This often leads to users' selections for web services more complicated. Under the circumstance, a variety of methods such as collaborative filtering are adopted to deal with this challenging situation. While traditional collaborative filtering method has some shortcomings, one of which is that only centralized user-service data are considered while distributed quality data from multiple platform are ignored. Generally, service recommendation across different platforms often involves data communication among multiple platforms, during which user privacy may be disclosed and much computational time is required. Considering these challenges, a unique amplified locality-sensitive hashing (LSH)-based service recommendation method, that is, SRAmplified-LSH, is proposed in the article. SRAmplified-LSH can guarantee a good balance between accuracy and efficiency of recommendation and user privacy information. Finally, extensive experiments deployed on WS-DREAM dataset validate the feasibility of our proposed method. © 2020 John Wiley & Sons, Ltd.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Response

引用

Gastrointestinal endoscopy 2024年第3期99卷 476-477页

作者： Xiang Zhang Dehua Tang Jin-Dong Zhou Wu-Jun Li Lei Wang Department of Gastroenterology Nanjing Drum Tower Hospital Affiliated Drum Tower Hospital Medical School of Nanjing University Nanjing China. National Institute of Healthcare Data Science at Nanjing University Nanjing China National Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University Nanjing China. National Key Laboratory for Novel Software Technology Department of Computer Science and Technology Center for Medical Big Data Nanjing Drum Tower Hospital Affiliated Drum Tower Hospital Medical School of Nanjing University Nanjing China.

来源：评论

学校读者我要写书评

暂无评论

Energy-guided diffusion sampling for offline-to-online reinforcement learning 24

Energy-guided diffusion sampling for offline-to-online reinf...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Xu-Hui Liu Tian-Shuo Liu Shengyi Jiang Ruifeng Chen Zhilong Zhang Xinwei Chen Yang Yu National Key Laboratory for Novel Software Technology & School of Artificial Intelligence Nanjing University China National Key Laboratory for Novel Software Technology & School of Artificial Intelligence Nanjing University China and Polixir Technologies Department of Computer Science The University of Hong Kong Hong Kong China Polixir Technologies

Combining offline and online reinforcement learning (RL) techniques is indeed crucial for achieving efficient and safe learning where data acquisition is expensive. Existing methods replay offline data directly in the online phase, resulting in a significant challenge of data distribution shift and subsequently causing inefficiency in online fine-tuning. To address this issue, we introduce an innovative approach, Energy-guided DIffusion Sampling (EDIS), which utilizes a diffusion model to extract prior knowledge from the offline dataset and employs energy functions to distill this knowledge for enhanced data generation in the online phase. The theoretical analysis demonstrates that EDIS exhibits reduced suboptimality compared to solely utilizing online data or directly reusing offline data. EDIS is a plug-in approach and can be combined with existing methods in offline-to-online RL setting. By implementing EDIS to off-the-shelf methods Cal-QL and IQL, we observe a notable 20% average improvement in empirical performance on MuJoCo, AntMaze, and Adroit environments. Code is available at https://***/liuxhym/EDIS

关键词：

来源：评论

学校读者我要写书评

暂无评论

Validity-Preserving Delta Debugging via Generator Trace Reduction

arXiv

引用

arXiv 2024年

作者： Ren, Luyao Zhang, Xing Hua, Ziyue Jiang, Yanyan He, Xiao Xiong, Yingfei Xie, Tao Key Laboratory of High Confidence Software Technologies Ministry of Education School of Computer Science Peking University Beijing China State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University China School of Computer and Communication Engineering University of Science and Technology Beijing China

Reducing test inputs that trigger bugs is crucial for efficient debugging. Delta debugging is the most popular approach for this purpose. When test inputs need to conform to certain specifications, existing delta debugging practice encounters a validity problem: it blindly applies reduction rules, producing a large number of invalid test inputs that do not satisfy the required specifications. This overall diminishing effectiveness and efficiency becomes even more pronounced when the specifications extend beyond syntactical structures. Our key insight is that we should leverage input generators, which are aware of these specifications, to generate valid reduced inputs, rather than straightforwardly performing reduction on test inputs. In this paper, we propose a generator-based delta debugging method, namely GReduce, which derives validity-preserving reducers. Specifically, given a generator and its execution, demonstrating how the bug-inducing test input is generated, GReduce searches for other executions on the generator that yield reduced, valid test inputs. The evaluation results on five benchmarks (i.e., graphs, DL models, JavaScript programs, SymPy, and algebraic data types) show that GReduce substantially outperforms state-of-the-art syntax-based reducers including Perses and T-PDD, and also outperforms QuickCheck, SmartCheck, as well as the state-of-the-art choice-sequence-based reducer Hypothesis, demonstrating the effectiveness, efficiency, and versatility of GReduce. Copyright © 2024, The Authors. All rights reserved.

关键词： software testing

来源：评论

学校读者我要写书评

暂无评论

E²GO: Free Your Hands for Smartphone Interaction

引用

International Journal of Human-computer Interaction 2025年

作者： Yan, Shaoming Ju, Yuanliang Quan, Rong Tu, Huawei Liang, Dong MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Collaborative Innovation Center of Novel Software Technology and Industrialization College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Department of Computer Science and Information Technology La Trobe University Melbourne Australia

Current eye-gaze interaction technologies for smartphones are considered inflexible, inaccurate, and power-hungry. These methods typically rely on hand involvement and accomplish partial interactions. In this paper, we propose a novel eye-gaze smartphone interaction method named Event-driven Eye-Gaze Operation ((Formula presented.)), which can realize comprehensive interaction using only eyes and gazes to cover various interaction types. Before the interaction, an anti-jitter gaze estimation method was exploited to stabilize human eye fixation and predict accurate and stable human gaze positions on smartphone screens to further explore refined time-dependent eye-gaze interactions. We also integrated an event-triggering mechanism in (Formula presented.) to significantly decrease its power consumption to deploy on smartphones. We have implemented the prototype of (Formula presented.) on different brands of smartphones and conducted a comprehensive user study to validate its efficacy, demonstrating (Formula presented.) ‘s superior smartphone control capabilities across various scenarios. Demo videos. © 2025 Taylor & Francis Group, LLC.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

A robust TDoA-based localization and tracking method designed for intelligent recommender systems

引用

Information sciences 2025年 717卷

作者： Mei, Hong-Yuan Zhou, Zhi Shen, Fu-Rao Zhao, Jian State Key Laboratory for Novel Software Technology Nanjing China Department of Computer Science and Technology Nanjing University China School of Artificial Intelligence Nanjing University China School of Electronic Science and Engineering Nanjing University China

In today's fast-paced society, the demand for intelligent Recommender Systems(RS) is increasing day by day. Users may hope that RSs can take their real-time situation into consideration to help them make timely decisions. To fulfill this goal, RSs need to accurately understand users' information, especially their real-time location. Therefore, localization of the users is very helpful in building an intelligent RS. Meanwhile, great efforts have been made to deal with localization based on time-difference-of-arrival (TDoA) measurements in the past decades. It is widely used in applications such as radar, sonar, sensor networks, and mobile communications. However, such a task is still challenging in complex real-world scenarios where large-scale noise and none-light-of-sight (NLoS) occur. To address this challenge, we propose a noise-tolerant method consisting of two stages: the Robust Multilateration Solver (RMS) and the Restricted Particle Filter (RPF). In the first stage, anomaly detection is adopted to eliminate outliers, and NLoS effects are mitigated by a data augmentation strategy. Then a rough estimate of the current position is obtained by combining two modified multilateration algorithms. In the second stage, the rough estimate is passed through an enhanced particle filter in order to reduce its bias caused by heavy Gaussian noise and smooth the motion trajectory. Meanwhile, localization rationality is guaranteed by confining the position to a predefined area. Sufficient testing in real indoor environments and simulation results demonstrate the effectiveness of our method and reveal its fitness for various industrial fields. © 2025

关键词： Indoor localization Recommender systems Source tracking TDoA

来源：评论

学校读者我要写书评

暂无评论

Deeply Reinforcing Android GUI Testing with Deep Reinforcement Learning

Deeply Reinforcing Android GUI Testing with Deep Reinforceme...

引用

International Conference on software Engineering (ICSE)

作者： Yuanhong Lan Yifei Lu Zhong Li Minxue Pan Wenhua Yang Tian Zhang Xuandong Li State Key Lab for Novel Software Technology Nanjing University Nanjing China College of Computer Science and Technology Nanjing University of Aero-nautics and Astronautics Nanjing China

ISBN: (数字)9798400702174

ISBN: (纸本)9798350382143

As the scale and complexity of Android applications continue to grow in response to increasing market and user demands, quality assurance challenges become more significant. While previous studies have demonstrated the superiority of Reinforcement Learning (RL) in Android GUI testing, its effectiveness remains limited, particularly in large, complex apps. This limitation arises from the ineffectiveness of Tabular RL in learning the knowledge within the large state-action space of the App Under Test (AUT) and from the suboptimal utilization of the acquired knowledge when em-ploying more advanced RL techniques. To address such limitations, this paper presents DQT, a novel automated Android GUI testing approach based on deep reinforcement learning. DQT preserves widgets' structural and semantic information with graph embedding techniques, building a robust foundation for identifying similar states or actions and distinguishing different ones. Moreover, a specially designed Deep Q-Network (DQN) effectively guides curiosity-driven exploration by learning testing knowledge from runtime interactions with the AUT and sharing it across states or actions. Experiments conducted on 30 diverse open-source apps demonstrate that DQT outperforms existing state-of-the-art testing approaches in both code coverage and fault detection, particularly for large, complex apps. The faults detected by DQT have been reproduced and reported to developers; so far, 21 of the reported issues have been explicitly confirmed, and 14 have been fixed.

关键词： Runtime Quality assurance Codes Fault detection Semantics Buildings Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A General Complementary API Recommendation Framework based on Learning Model

A General Complementary API Recommendation Framework based o...

引用

IEEE International Conference on Web Services (ICWS)

作者： Qiqi Chen Guosheng Kang Yamei Nie Jianxun Liu Buqing Cao HNUST Hunan Provincial Key Lab. for Services Computing and Novel Software Technology Xiangtan China School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China

ISBN: (数字)9798350368550

ISBN: (纸本)9798350368567

With the advancement of service computing technology, the Internet has witnessed an exponential proliferation of Web APIs. However, the selection of suitable APIs from this vast pool for Mashup creation poses a great challenge for users. Various Web API recommendation methods have been proposed to address this issue, aiming to simplify the complex selection process. Despite these efforts, limited studies have been conducted on complementary function recommendation. In this context, a general complementary Web API recommendation framework based on a learning model, named CoWAR, is designed to recommend complementary Web APIs tailored for Mashup creation, based on the user’s selected Web APIs. Specifically, we propose a data labeling algorithm to generate the labeled dataset based on Mashup-API interactions derived from historical Mashups and Web APIs. Additionally, we employ BERT model to generate representation vectors of Web APIs based on the functionality description documents. Subsequently, we utilize SANFM (Self-Attentional Neural Factorization Machines) to train the complementary Web API recommendation model with the labeled sample dataset based on representation vectors of Web APIs. To the best of our knowledge, this is the first work addressing the complementary function recommendation problem with a learning model. By conducting a set of experiments over a real-world dataset, the effectiveness of the proposed approach is validated. The experimental results demonstrate that the learning model outperforms the traditional machine learning-based models and several deep learning-based models.

关键词： Training Measurement Mashups Service computing Vectors Data models labeling Context modeling

来源：评论

学校读者我要写书评

暂无评论

JMF-SS: Joint Matrix Factorization for Web API Recommendation with Mashup-Mashup Similarities and API-API Similarities

JMF-SS: Joint Matrix Factorization for Web API Recommendatio...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Lihong Zhang Jing He Yamei Nie Xiaokang Zhou Qiqi Chen Guosheng Kang School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China Hunan Provincial Key Lab. for Services Computing and Novel Software Technology HNUST Xiangtan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

With the development of service computing technology, the number of publicly available Web APIs online has increased dramatically. Developers tend to use Web APIs to implement their software development requirements. However, due to the large number of Web APIs, how to select the appropriate Web API from the huge resource library for Mashup development has become a challenge. To solve this problem, some researchers have proposed Web API recommendation methods based on collaborative filtering or matrix factorization. However, the Web API recommendation performance is still limited due to the reliance on Mashup- API interaction and the ignorance of Mashup and Web API description documents. Moreover, the Mashup-API interaction matrix is extremely sparse, resulting in low accuracy in matrix factorization and collaborative filtering. To further improve the recommendation performance, we propose a novel joint matrix factorization method for the Mashup-API interaction matrix by incorporating the Mashup-Mashup similarity matrix and the API-API similarity matrix. A set of experiments are conducted on a real-world dataset, and the experimental results show that the proposed method outperforms the baselines.

关键词： Measurement Accuracy Federated learning Mashups Collaborative filtering Service computing Libraries

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：