检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial intelligence 2025年

作者： Yuan, Jidong Zhang, Lingyin Jia, Weiqiang Guo, Jia Liu, Haiyang Wang, Jinfeng Ministry of Education Key Laboratory of Big Data & Artificial Intelligence in Transportation China Beijing Jiaotong University School of Computer Science and Technology Beijing100044 China

For multivariate time series classification, current research predominantly focuses on contrastive learning to acquire suitable representations. Despite their successes in enhancing accuracy and reducing label dependency, existing methods primarily concentrate on time-domain features, potentially neglecting the frequency-domain information inherent in time series. Additionally, the challenging problem of addressing the impact of false negative samples in contrastive learning remains unresolved. To tackle this, we propose a cross-modal architecture based on ranking time-frequency contrastive learning. This novel approach considers time-frequency consistency of time series, introducing an innovative time-frequency-based ranking loss to regulate the proximity between positive/negative samples and the anchor point, thereby mitigating issues related to false negatives. Extensive experiments validate the effectiveness of our proposed method in advancing multivariate time series classification © 2020 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

FormerTime: Hierarchical Multi-Scale Representations for Multivariate Time Series Classification

arXiv

引用

arXiv 2023年

作者： Cheng, Mingyue Liu, Qi Liu, Zhiding Li, Zhi Luo, Yucong Chen, Enhong Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Hefei China Shenzhen International Graduate School Tsinghua University Shenzhen China

Deep learning-based algorithms, e.g., convolutional networks, have significantly facilitated multivariate time series classification (MTSC) task. Nevertheless, they suffer from the limitation in modeling long-range dependence due to the nature of convolution operations. Recent advancements have shown the potential of transformers to capture long-range dependence. However, it would incur severe issues, such as fixed scale representations, temporal-invariant and quadratic time complexity, with transformers directly applicable to the MTSC task because of the distinct properties of time series data. To tackle these issues, we propose FormerTime, an hierarchical representation model for improving the classification capacity for the MTSC task. In the proposed FormerTime, we employ a hierarchical network architecture to perform multi-scale feature maps. Besides, a novel transformer encoder is further designed, in which an efficient temporal reduction attention layer and a well-informed contextual positional encoding generating strategy are developed. To sum up, FormerTime exhibits three aspects of merits: (1) learning hierarchical multi-scale representations from time series data, (2) inheriting the strength of both transformers and convolutional networks, and (3) tacking the efficiency challenges incurred by the self-attention mechanism. Extensive experiments performed on 10 publicly available datasets from UEA archive verify the superiorities of the FormerTime compared to previous competitive baselines. Copyright © 2023, The Authors. All rights reserved.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Whale Optimization Algorithm with Mahalanobis Distance for Optimization Problems 7

An Adaptive Whale Optimization Algorithm with Mahalanobis Di...

引用

7th International Conference on Digital Arts, Media and technology, DAMT 2022 and 5th ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering, NCON 2022

作者： Jitkongchuen, Duangjai Sirikayon, Chaloemphon Thummano, Arit Dhurakij Pundit University Big Data Engineering Program College of Innovative Technology and Engineering Bangkok Thailand King Mongkut's Institute of Technology Ladkrabang Computational Intelligence Laboratory Faculty of Information Technology Bangkok Thailand

ISBN: (纸本)9781665495103

This paper suggests using Mahalanobis distance to regenerate a new whale position to increase the performance of the whale optimization algorithm. Learning from previous evolutionary searches allows the probability parameters to be self-adapted. The suggested approach was compared to the classical whale optimization algorithm (WOA), particle swarm optimization (PSO), and differential evolution algorithm (DE) on 11 well-known benchmark functions. The results of the experiments showed that the proposed algorithm was effective in solving optimization problems. © 2022 IEEE.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

A resilient generative model in few-shot question answering

引用

Knowledge-Based Systems 2025年 323卷

作者： Zou, Anqi Chen, Yanping Huang, Ruizhang Qin, Yongbin Engineering Research Center of Text Computing & Cognitive Intelligence Ministry of Education Guizhou University Guiyang Guizhou550025 China State Key Laboratory of Public Big Data Guizhou University Guiyang Guizhou550025 China College of Computer Science and Technology Guizhou University Guiyang550025 China

In few-shot question answering (QA), only a limited number of training cases are available to tune pre-trained language models (PLMs) for fitting to the task objective. Because a PLM often contains a large number of parameters optimized by a pretraining objective, it is difficult to bridge the gap between the two optimization objectives with a few training cases, which leads to the overfitting problem. Furthermore, in the decoding process of a generative model, sometimes rebuilding an answer to a question is more challenging than directly choosing from an input, because the ability to rebuild requires more informative knowledge and may generate hallucinatory outputs. Motivated by the above discussions, we propose a resilient deep model to support the few-shot question answering tasks. Instead of ambitiously optimizing a full generative model with a few training cases, the resilient model contains a partial learning module and an answer choosing module to reduce the problems caused by a lack of training cases. This has the advantage to enhance the few-shot learning in question answering. Our method was evaluated using several few-shot QA public evaluation datasets. It achieves a state-of-the-art performance, considerably outperforming related works. © 2025 Elsevier B.V.

关键词： Answer choosing Few-shot question answering Overfitting Partial learning The resilient model

来源：评论

学校读者我要写书评

暂无评论

A Joint Learning Sentiment Analysis Method Incorporating Emoji-Augmentation 8

A Joint Learning Sentiment Analysis Method Incorporating Emo...

引用

8th IEEE International Conference on Cloud Computing and intelligence Systems, CCIS 2022

作者： Chen, Jie Luo, Luping Ji, Bojing Zhao, Shu Zhang, Yanping Anhui University The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology China Chizhou University School of Big Data and Artificial Intelligence China

ISBN: (纸本)9781665477352

Social media is the platform for most people to share their opinions, emojis are also widely used to express moods, emotions, and feelings on social media. There have been many researched on emojis and sentiment analysis. However, existing methods mainly face two limitations. First, since deep learning relies on large amounts of labeled data, the training samples of emoji are not enough to achieve the training effect. Second, they consider the sentiment of emojis and texts separately, not fully exploring the impact of emojis on the sentiment polarity of texts. In this paper, we propose a joint learning sentiment analysis method incorporating emoji-augmentation, and the method has two advantages compared with the existing work. First, We optimize the easy data augmentation method so that the newly generated sentences can also preserve the semantic information of emojis, which relieves the problem of insufficient training data with emojis. Second, it fuses emojis and text features to allow the model to better learn the mutual emotional semantics between text and emojis, jointly training emojis and words to obtain the sentence representations containing more semantic information of both emojis and text. Our experimental results show that the proposed method can significantly improve the performance compared with several baselines on two datasets. © 2022 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Reversible data Hiding Using Convolutional Neural Network and Digital Signal Processing Techniques 12

Reversible Data Hiding Using Convolutional Neural Network an...

引用

12th International Conference on Information technology in Medicine and Education, ITME 2022

作者： Qingmei, Peng Shaozi, Li Yaojin, Lin Xiehua, Yu University of Fujian Province Key Laboratory of Big Data and Artificial Intelligence MinNan Science and Technology University Quanzhou China Xiamen University School of Informatics Xiamen China Minnan Normal University School of Computer Science Lab of Data Science and Intelligence Application Zhangzhou China

ISBN: (纸本)9798350310153

Reversible data hiding is a data hiding process in which data is encrypted into an image as a means of authentication, and hidden data is used to hide the original image, and RDH is often used in areas where data authenticity and data preservation are important, such as legal/criminal investigations, medical images. In this study, this paper designed a novel reversible data hiding system that utilizes the Steghide algorithm to encrypt images and hide data, as well as an artificial neural network to recover embedded text and structure. Based on the analysis of the test results, it was concluded that the RDH scheme proposed in this article has the same or higher system accuracy and reliability as the existing RDH scheme. To further refine the system results in future studies, this paper proposes to increase the number of training iterations and the number of images in the training dataset to further improve the accuracy and reliability of the development. © 2022 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Video2Reward: Generating Reward Function from Videos for Legged Robot Behavior Learning 27

Video2Reward: Generating Reward Function from Videos for Leg...

引用

27th European Conference on Artificial intelligence, ECAI 2024

作者： Zeng, Runhao Zhou, Dingjie Liang, Qiwei Liu, Junlin Li, Hui Huang, Changxin Li, Jianqiang Hu, Xiping Sun, Fuchun Artificial Intelligence Research Institute Shenzhen MSU-BIT University China College of Mechatronics and Control Engineering Shenzhen University China College of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Department of Computer Science and Technology Tsinghua University China

ISBN: (纸本)9781643685489

Learning behavior in legged robots presents a significant challenge due to its inherent instability and complex constraints. Recent research has proposed the use of a large language model (LLM) to generate reward functions in reinforcement learning, thereby replacing the need for manually designed rewards by experts. However, this approach, which relies on textual descriptions to define learning objectives, fails to achieve controllable and precise behavior learning with clear directionality. In this paper, we introduce a new video2reward method, which directly generates reward functions from videos depicting the behaviors to be mimicked and learned. Specifically, we first process videos containing the target behaviors, converting the motion information of individuals in the videos into keypoint trajectories represented as coordinates through a video2text transforming module. These trajectories are then fed into an LLM to generate the reward function, which in turn is used to train the policy. To enhance the quality of the reward function, we develop a video-assisted iterative reward refinement scheme that visually assesses the learned behaviors and provides textual feedback to the LLM. This feedback guides the LLM to continually refine the reward function, ultimately facilitating more efficient behavior learning. Experimental results on tasks involving bipedal and quadrupedal robot motion control demonstrate that our method surpasses the performance of state-of-the-art LLM-based reward generation methods by over 37.6% in terms of human normalized score. More importantly, by switching video inputs, we find our method can rapidly learn diverse motion behaviors such as walking and running. © 2024 The Authors.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Legal Risks and Governance Paths for Generative AI--A Case Study of ChatGPT

Legal Risks and Governance Paths for Generative AI--A Case S...

引用

IEEE International Symposium on Information (IT) in Medicine and Education, ITME

作者： Wang Zhenfeng Lin Quanwang Gao Huihui Yu Xiehua Key Laboratory of Big Data and Artificial Intelligence University of Fujian Province MinNan Science and Technology University Fujian: China School of Computer and Information MinNan Science and Technology University Quanzhou China Key Laboratory of Big Data and Artificial Intelligence University of Fujian Quanzhou China

The release of OpenAI's ChatGPT chatbot has sparked widespread concern around the world about the threats and legal issues of generative AI. Although this technological innovation has opened a new chapter in the field of artificial intelligence, it has also caused the public to worry about its possible negative effects. In order to solve the above problems and reasonably regulate the legal risks of generative artificial intelligence, this paper mainly adopts the literature, quantitative and qualitative analysis methods, etc. The first part mainly introduces the development process and current situation of generative artificial intelligence, the second part mainly discusses the impact of generative artificial intelligence on tort law, the third part mainly discusses the legal risks of generative artificial intelligence, and the fourth part mainly discusses the governance path of generative artificial intelligence legal risks. The last part is the conclusion of the research. Among them, the fourth part is the focus of this paper. By taking these issues into account, we can provide legal guarantees for the sustainable development of the generative AI industry and ensure that the widespread application of AI benefits human society[1].

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Ship License Plate Recognition in the Wild: A Large Benchmark and Strong Baseline 39

Towards Ship License Plate Recognition in the Wild: A Large ...

引用

39th Annual AAAI Conference on Artificial intelligence, AAAI 2025

作者： Liu, Baolong Yang, Ruiqing Huang, Roukai Xu, Wenhao Pan, Xin Li, Chuanhuang Wang, Bin Wang, Xun Dong, Jianfeng Zhejiang Gongshang University China Key Laboratory of Public Security Information Application Based on Big-Data Architecture Ministry of Public Security China Zhejiang Key Laboratory of Big Data and Future E-Commerce Technology China Zhejiang University China Zhejiang Key Laboratory of Artificial Intelligence of Things (AIoT) Network and Data Security China

ISBN: (纸本)157735897X

The paper targets the challenging task of Ship License Plate (SLP) recognition. Existing methods for SLP recognition are hampered by the scarcity of large and publicly available datasets, leading to evaluations on small and non-representative datasets. To alleviate it, we have built a large dataset, called SLP34K, which consists of 34,385 images collected by an intelligent traffic surveillance system. The dataset is carefully manually annotated with text labels and attributes, and presents high data diversity by multiple installation locations and long capturing period of the cameras. Additionally, we propose a simple yet effective SLP recognition baseline method. The baseline is equipped with a strong visual encoder that benefits from initial pre-training via self-supervised learning, followed by further refinement through our devised semantic enhancement module. Extensive experiments on SLP34K verify the effectiveness of our proposed baseline. Moreover, while our baseline is designed for SLP recognition, it can also be used for common scene text recognition and achieve state-of-the-art performance on seven mainstream scene text recognition datasets. © 2025, Association for the Advancement of Artificial intelligence (***). All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Augmenting Short Sequence for Robust Session-based Recommendation

Augmenting Short Sequence for Robust Session-based Recommend...

引用

Computers and Artificial intelligence Technologies (CAIT), International Conference on

作者： Xiaoxi Liu Xiangkui Lu Yuanzhouhan Cao Yidong Li School of Computer Science and Technology Beijing Jiaotong University Key Laboratory of Big Data & Artifcial Intelligence in Transportation (Beiing Jiaotong University) Ministry of Education

ISBN: (数字)9798331530891

ISBN: (纸本)9798331530907

In recent years, recommendation systems leveraging deep neural networks have gained prominence as a means to address the information overload challenge exacerbated by the rapid advancement of the Internet. Predominantly, deep recommendation models focus on modeling user attribute features by utilizing the sequence of previously interacted items to predict the next item a user is likely to engage with. However, prior to user registration or login on an application, these recommendation models can only access a limited scope of user interactions, typically restricted to a short sequence of recent sessions. This brevity inherently constrains the accuracy of the recommendation model. To mitigate this limitation, we draw inspiration from the concept of sequence augmentation in contrastive learning, which employs short sequences to derive additional supervised signals based on association rules. Furthermore, we incorporate the notion of non-negative transfer learning to enhance the extraction of supervised signals that better align with the underlying intent of user sessions. Comprehensive experiments conducted on three real-world datasets substantiate the efficacy of our proposed model, demonstrating its superiority over traditional RNN, CNN, GNN, and various Transformer-based approaches.

关键词： Computers Accuracy Transfer learning Contrastive learning Artificial neural networks Predictive models Transformers Internet Association rule learning Recommender systems

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：