检索结果-内蒙古大学图书馆

Vision-Based Sign Language Translation via a Skeleton-Aware Neural Network

Journal of computer science & technology 2025年第2期40卷 378-396页

作者： Shi-Wei Gan Ya-Feng Yin Zhi-Wei Jiang Lei Xie Sang-Lu Lu State Key Laboratory for Novel Software Technology Nanjing UniversityNanjing 210023China

Sign languages are mainly expressed by human actions,such as arm,hand,and finger *** a skeleton which reflects human pose information can provide an important cue for distinguishing signs(i.e.,human actions),and can be used for sign language translation(SLT),which aims to translate sign language to spoken ***,the recent neural networks typically focus on extracting local-area or full-frame features,while ignoring informative skeleton ***,this paper proposes a novel skeleton-aware neural network,SANet,for vision-based ***,to introduce skeleton modality,we design a self-contained branch for skeleton *** efficiently guide the feature extraction from videos with skeletons,we concatenate the skeleton channel and RGB channels of each frame for feature *** distinguish the importance of clips(i.e.,segmented short videos),we construct a skeleton-based graph convolutional network,GCN,for feature scaling,i.e.,giving an importance weight for each ***,to generate spoken language from features,we provide an end-to-end method and a two-stage method for ***,based on SANet,we provide an SLT solution on the smartphone for benefiting communication between hearing-impaired people and normal *** experiments on three public datasets and case studies in real scenarios demonstrate the effectiveness of our method,which outperforms existing methods.

关键词： human action recognition sign language translation skeleton neural network

来源：评论

学校读者我要写书评

暂无评论

Adv-Triplet Loss for Sparse Attack on Facial Expression Recognition 20th

Adv-Triplet Loss for Sparse Attack on Facial Expression Re...

引用

20th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2023

作者： Li, Weitao Li, Shijun Shang, Lin State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China Department of Computer Science and Technology Nanjing University Nanjing210023 China

ISBN: (纸本)9789819970247

The susceptibility of current Deep Neural Networks (DNNs) to adversarial examples has been a significant concern in deep learning methods. In particular, sparse adversarial examples represent a specific category of adversarial examples that can deceive the target model by perturbing only a few pixels in images. While existing sparse adversarial attack methods have shown achievements, the current results of sparsity and efficiency are inadequate and require significant improvements. This paper introduces an adv-triplet loss and proposes a search attack method to attack the Face Expression Recognition (FER) system with minimal pixel perturbations. Specifically, we propose an adv-triplet loss function and utilize its gradient information to generate pixels for adversarial examples. Extensive experiments conducted on the CK+ and Oulu-CASIA datasets demonstrate the superiority of our proposed method over several state-of-the-art sparse attack methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Meaningful Update and Repair of Markov Decision Processes for Self-Adaptive Systems

引用

Journal of computer science & technology 2022年第1期37卷 106-127页

作者： Wen-Hua Yang Min-Xue Pan Yu Zhou Zhi-Qiu Huang College of Computer Science and Technology Nanjing University of Aeronautics and AstronauticsNanjing 211106China State Key Laboratory for Novel Software Technology Nanjing UniversityNanjing 210093China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing UniversityNanjing 210023China

Self-adaptive systems are able to adjust their behaviour in response to environmental condition changes and are widely deployed as *** as a promising way to handle the ever-growing complexity of software systems,they have seen an increasing level of interest and are covering a variety of applications,e.g.,autonomous car systems and adaptive network *** approaches for the construction of self-adaptive systems have been developed,and probabilistic models,such as Markov decision processes(MDPs),are one of the ***,the majority of them do not deal with the problems of the underlying MDP being obsolete under new environments or unsatisfactory to the given *** results in the generated policies from such MDP failing to guide the self-adaptive system to run correctly and meet *** this article,we propose a systematic approach to updating an obsolete MDP by exploring new states and transitions and removing obsolete ones,and repairing an unsatisfactory MDP by adjusting its structure in a more meaningful way rather than arbitrarily changing the transition probabilities to values not in line with *** results show that the MDPs updated and repaired by our approach are more competent in guiding the self-adaptive systems’correct running compared with the original ones.

关键词： self-adaptive system Markov decision process model repair

来源：评论

学校读者我要写书评

暂无评论

When debugging encounters artificial intelligence: state of the art and open challenges

引用

science China(Information sciences) 2024年第4期67卷 42-84页

作者： Yi SONG Xiaoyuan XIE Baowen XU School of Computer Science Wuhan University State Key Laboratory of Novel Software Technology Nanjing University

Both software debugging and artificial intelligence techniques are hot topics in the current field of software engineering. Debugging techniques, which comprise fault localization and program repair, are an important part of the software development lifecycle for ensuring the quality of software systems. As the scale and complexity of software systems grow, developers intend to improve the effectiveness and efficiency of software debugging via artificial intelligence(artificial intelligence for software debugging, AI4SD). On the other hand, many artificial intelligence models are being integrated into safety-critical areas such as autonomous driving, image recognition, and audio processing, where software debugging is highly necessary and urgent(software debugging for artificial intelligence, SD4AI). An AI-enhanced debugging technique could assist in debugging AI systems more effectively, and a more robust and reliable AI approach could further guarantee and support debugging techniques. Therefore, it is important to take AI4SD and SD4AI into consideration comprehensively. In this paper, we want to show readers the path, the trend, and the potential that these two directions interact with each other. We select and review a total of 165 papers in AI4SD and SD4AI for answering three research questions, and further analyze opportunities and challenges as well as suggest future directions of this cross-cutting area.

关键词： software debugging fault localization program repair artificial intelligence machine learning

来源：评论

学校读者我要写书评

暂无评论

A Blockchain-Assisted Federated Learning Method for Recommendation Systems 22

A Blockchain-Assisted Federated Learning Method for Recommen...

引用

22nd IEEE International Symposium on Parallel and Distributed Processing with Applications, ISPA 2024

作者： Zhang, Hang Tian, Hao Chen, Cheng Tian, Chen Dou, Wanchun Nanjing University State Key Laboratory for Novel Software Technology Nanjing China

ISBN: (纸本)9798331509712

Due to the privacy advantages of federated learning (FL), federated recommendation systems (FedRSs) are gaining popularity for improving recommendation performance through training on local data. However, FedRSs frequently face the significant challenge of high communication costs between the server and clients. Most FedRSs utilize a client-server communication architecture, leading to heavy communication loads and single points of failure due to dependence on a central server. Clients may also encounter problems due to limited communication resources. In view of this challenge, in this paper, we propose a blockchain-assisted federated learning method at edge for communication-efficient recommendation systems, named BFedRec. Specifically, BFedRec reduces reliance on the central server by utilizing blockchain systems on edge servers to aggregate and distribute the recommendation model. To mitigate the high communication costs between clients and blockchain in each iteration, a communication-efficient training algorithm is used that trains the recommendation model directly on low-rank compressed parameters. Finally, we conduct extensive experiments on real-world datasets to verify the communication efficiency of BFedRec compared to existing methods. The experimental results show that BFedRec effectively improves communication efficiency without compromising recommendation performance. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

TS3Net: Triple Decomposition with Spectrum Gradient for Long-Term Time Series Analysis 40

TS3Net: Triple Decomposition with Spectrum Gradient for Long...

引用

40th IEEE International Conference on Data Engineering, ICDE 2024

作者： Ma, Xiangkai Hong, Xiaobin Lu, Sanglu Li, Wenzhong State Key Laboratory for Novel Software Technology Nanjing University Nanjing China

ISBN: (纸本)9798350317152

Time series analysis has a wide range of applications in the fields of weather forecasting, traffic management, fault detection, intelligent operation, etc. In the real world, time series typically consist of dynamic fluctuations and mixtures of periodicities, which bring challenges on modeling and analyzing their patterns. To overcome the complexities, a common approach is to decompose long-term time series into sub-components for easier analysis. Unlike conventional time series decomposition that decouples a series into the trend and seasonal parts, we proposed a novel triple decomposition method to decouple a long-term series into three components: trend-part, regular-part, and fluctuant-part. Notably, the third part is a particular component that represents the dynamic spectral fluctuation in time series with the formulation of spectrum gradient. Based on triple decomposition, we propose a novel task-general deep learning model called TS3Net for long-term series analysis. It introduces a temporal-frequency block (TF-Block) with a multi-branch structure to expand the time series into a 2D temporal-frequency distribution. Subsequently, deep representation can be learned by a vision architecture that captures the dynamic variations from the complex multi-periodic series. The decomposed components are processed by TS3Net individually, and their results are integrated to form the final result for time series analysis. We conduct extensive experiment based on six open datasets to evaluate the proposed method in comparison with 10 baselines. Numerical results show that TS3Net significantly outperforms the state-of-the-art methods on both time series forecasting and imputation tasks. The source codes of TS3Net are publicly available on https://***/Xiang-Kai/TS3Net. © 2024 IEEE.

关键词： Time series analysis

来源：评论

学校读者我要写书评

暂无评论

DYNAMIC REPLAY TRAINING FOR CLASS-INCREMENTAL LEARNING 49

DYNAMIC REPLAY TRAINING FOR CLASS-INCREMENTAL LEARNING

引用

49th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yang, Yan Ren, Dongdong Peng, Chenglei Huo, Jing Li, Wenbin Gao, Yang State Key Laboratory for Novel Software Technology Nanjing University China The School of Electronic Science and Engineering Nanjing University China

ISBN: (纸本)9798350344868;9798350344851

Replay-based methods for Class-Incremental Learning (CIL) typically employ new classes and a limited subset of old classes stored in memory to facilitate the model training. However, these methods often lead to class imbalance and catastrophic forgetting, where the model forgets previously learned tasks. While some studies have attempted to address such a class imbalance issue, they do not fully consider the dynamic nature of forgetting in the model. In this paper, we propose a novel method called Dynamic Replay Training (DRT) to address the dynamic forgetting of previously learned tasks by the model. DRT replays memory data with dynamically changing frequencies, offering a novel perspective to tackle catastrophic forgetting and class imbalance. The proposed method is evaluated on CIFAR-100 and ImageNet-100 in various settings, showing significant improvements of 8.28% and 4.53% in terms of classification accuracy compared to the baseline method on the two datasets, respectively.

关键词： Class Imbalance Catastrophic Forgetting Class-Incremental Learning Replay-based CIL

来源：评论

学校读者我要写书评

暂无评论

DeepTD: Diversity-Guided Deep Neural Network Test Generation 9th

DeepTD: Diversity-Guided Deep Neural Network Test Generation

引用

9th International Symposium on Dependable software Engineering: Theories, Tools and Applications, SETTA 2023

作者： Zhu, Jin Tao, Chuanqi Guo, Hongjing Ju, Yue College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Ministry Key Laboratory for Safety-Critical Software Development and Verification Nanjing China State Key Laboratory for Novel Software Technology Nanjing China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing China

ISBN: (纸本)9789819986637

Coverage-guided Fuzz Testing (CGF) techniques have been applied to deep neural network (DNN) testing in recent years, generating a significant number of test samples to uncover inherent defects in DNN models. However, the effectiveness of CGF techniques that utilize structured coverage metrics as coverage criteria is currently being questioned. A few unstructured coverage metrics, such as surprise adequacy, only take into account the diversity of the test samples against the training set, while ignoring the diversity of the test samples themselves. In addition to this, the existing surprise adequacy metrics have some limitations in their applications. Therefore, this paper proposes DeepTD, a diversity-guided deep neural networks test generation method. Firstly, DeepTD selects high-loss test samples from each class on average, ensuring these test seeds possess a strong ability to reveal model errors. Then, DeepTD transforms these test seeds to enhance the diversity of the generated samples. Finally, Cluster-based Surprise Adequacy is designed to guide the generation of test samples. To evaluate the effectiveness of DeepTD, six DNN models are selected as subjects, covering two well-known image datasets. Experimental results demonstrate that the Cluster-based Surprise Adequacy outperforms the two existing metrics not only in computational efficiency but also in discovering more model defects. What’s more, the test samples generated by DeepTD are on average 6.04% and 3.24% more effective for model retraining in MNIST and CIFAR10 compared to baseline methods, respectively. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Coverage-guided fuzz testing Deep neural network Test generation Test samples diversity

来源：评论

学校读者我要写书评

暂无评论

Self-stabilizing (Δ+ 1 ) -Coloring in Sublinear (in Δ ) Rounds via Locally-Iterative Algorithms 29th

Self-stabilizing (Δ+ 1 ) -Coloring in Sublinear (in Δ ) R...

引用

29th International Computing and Combinatorics Conference, COCOON 2023

作者： Fu, Xinyu Yin, Yitong Zheng, Chaodong State Key Laboratory for Novel Software Technology Nanjing University Nanjing China

ISBN: (纸本)9783031491894

Fault-tolerance is a central theme in distributed computing. Self-stabilization is a key property that guarantees a distributed system starting from an arbitrary state eventually converges to a desired behavior. Such strong level of fault-tolerance is often desirable due to the error-prone nature of distributed systems. Developing fast and robust coloring algorithms has been a central topic in the study of distributed graph algorithms. In this paper, we give a (Δ+ 1 ) -coloring algorithm with O(Δ3 / 4log Δ) + log ∗n stabilization time, only using messages of size O(log n), on input graphs of n vertices and maximum degree Δ. This is the first self-stabilizing (Δ+ 1 ) -coloring algorithm with sublinear-in- Δ stabilization time. The key building block of our algorithm is a new locally-iterative (Δ+ 1 ) -coloring algorithm with O(Δ3 / 4log Δ) + log ∗n runtime. To the best of our knowledge, this is the first locally-iterative (Δ+ 1 ) -coloring algorithm with sublinear-in- Δ runtime. This answers an open question raised in [Barenboim, Elkin, and Goldberg, JACM ’21]. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

Bug localization based on syntactical and semantic information of source code

引用

Journal of Systems Engineering and Electronics 2023年第1期34卷 236-246页

作者： YAN Xuefeng CHENG Shasha GUO Liqin College of Computer Science Technology Nanjing University of Aeronautics and AstronauticsNanjing 211106China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing 211106China State Key Laboratory of Intelligent Manufacturing System Technology Beijing Institute of Electronic System EngineeringBeijing 100854China

The existing software bug localization models treat the source file as natural language, which leads to the loss of syntactical and structure information of the source file. A bug localization model based on syntactical and semantic information of source code is proposed. Firstly, abstract syntax tree(AST) is divided based on node category to obtain statement sequence. The statement tree is encoded into vectors to capture lexical and syntactical knowledge at the statement ***, the source code is transformed into vector representation by the sequence naturalness of the statement. Therefore,the problem of gradient vanishing and explosion caused by a large AST size is obviated when using AST to the represent source code. Finally, the correlation between bug reports and source files are comprehensively analyzed from three aspects of syntax, semantics and text to locate the buggy code. Experiments show that compared with other standard models, the proposed model improves the performance of bug localization, and it has good advantages in mean reciprocal rank(MRR), mean average precision(MAP) and Top N Rank.

关键词： bug report abstract syntax tree code representation software bug localization

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：