检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Hu, Zhongtian Cui, Yiwen Li, Ronghan Zhao, Meng Wang, Lifang School of Computer Science and Engineering Northwestern Polytechnical University China School of Computer Science and Technology Xidian University China School of Artificial Intelligence and Big Data Henan University of Technology China

Dialogue response generation has made significant progress, but most research has focused on dyadic dialogue. In contrast, multi-party dialogues involve more participants, each potentially discussing different topics, making the task more complex. Current methods often rely on graph neural networks to model dialogue context, which helps capture the structural dynamics of multi-party conversations. However, these methods are heavily dependent on intricate graph structures and dataset annotations, and they often overlook the distinct speaking styles of participants. To address these challenges, we propose CMR, a Contrastive learning-based Multi-party dialogue Response generation model. CMR uses self-supervised contrastive learning to better distinguish "who says what." Additionally, by comparing speakers within the same conversation, the model captures differences in speaking styles and thematic transitions. To the best of our knowledge, this is the first approach to apply contrastive learning in multi-party dialogue generation. Experimental results show that CMR significantly outperforms state-of-the-art models in multiparty dialogue response tasks. © 2025, CC BY.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

A New Model Based on Differential Evolutionary Algorithm and Markov Clustering for Identifying Protein Complexes 42

A New Model Based on Differential Evolutionary Algorithm and...

引用

42nd Chinese Control Conference, CCC 2023

作者： Feng, Zengyu Tuo, Shouheng Chen, Tianrui School of Computer Science and Technology Xi'an University of Posts and Telecommunications Shaanxi Xi'an710121 China Xi'an Key Laboratory of Big Data and Intelligent Computing Shaanxi Xi'an710121 China

ISBN: (纸本)9789887581543

As the material basis for all life activities, proteins play a crucial role in performing life activities. Most real-life proteins perform various functions in the form of protein complexes, so it is essential for understanding of life activities to accurately identify protein complexes. Most of the existing approaches learn protein interactions directly from protein topology, ignoring the biological characteristics of the actual proteins. Nevertheless, actual protein complexes are usually composed of protein cores and protein attachments. In this study, a new MP-DE algorithm is designed from the core-attachment structure to generate protein complex cores using Markov clustering, while searching for attached proteins in the second-order neighborhood of core protein complexes based on differential evolution(DE) algorithm. The experimental results show that the proposed method has high detection accuracy and efficiency on the current mainstream protein-protein interaction(PPI) database. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Proteins

来源：评论

学校读者我要写书评

暂无评论

Multivariate Prediction of Retail Sales by Multi-task Time Series Learning

Multivariate Prediction of Retail Sales by Multi-task Time S...

引用

2021 International Conference on computer Graphics, Artificial Intelligence, and data Processing, ICCAID 2021

作者： Lin, Miaopei Yu, Jianxing Yin, Jian Sun Yat-sen University School of Computer Science and Engineering Guangdong Key Laboratory of Big Data Analysis and Processing China

ISBN: (数字)9781510652170

ISBN: (纸本)9781510652163

Predicting retail sales is a hot research topic that can help firms achieve on-demand procurement. That can reduce the extra costs caused by an inventory shortage or surpluses. Traditional methods usually regard the sales of a certain product as the independent time series and then solve the task by a curve fitting model. However, the sales volume is not a single value, but the one aggregated from many types of products. There are correlations between different types of product sales. The increase in one type of product sales may lead to changes in sales in another type. Without capturing the correlation between different product sales, it is difficult to obtain satisfactory performance. To solve this problem, we propose a new multi-task method based on multivariate time series learning. Considering there are multiple product types and each type has different trend characteristics, we first cluster the time series of all product types and then model each as a multivariate prediction task. We then design a new dilated convolution network to fusion the features of related products and the trend characteristic of each task. Moreover, we develop a trend structural entropy network to grasp the fluctuation features of the task. A new self-enhancement mechanism is proposed to finely capture the correlations among tasks. Through multi-task learning, the model can effectively improve prediction accuracy by using the complementary information of closely related time series. Experimental results on two real data sets show the effectiveness of our approach. © 2022 SPIE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

BCLNet: Bilateral Consensus Learning for Two-View Correspondence Pruning

arXiv

引用

arXiv 2024年

作者： Miao, Xiangyang Xiao, Guobao Wang, Shiping Yu, Jun School of Electronics and Information Engineering Tongji University China College of Computer and Data Science Fuzhou University China School of Computer Science and Technology Hangzhou Dianzi University China

Correspondence pruning aims to establish reliable correspondences between two related images and recover relative camera motion. Existing approaches often employ a progressive strategy to handle the local and global contexts, with a prominent emphasis on transitioning from local to global, resulting in the neglect of interactions between different contexts. To tackle this issue, we propose a parallel context learning strategy that involves acquiring bilateral consensus for the two-view correspondence pruning task. In our approach, we design a distinctive self-attention block to capture global context and parallel process it with the established local context learning module, which enables us to simultaneously capture both local and global consensuses. By combining these local and global consensuses, we derive the required bilateral consensus. We also design a recalibration block, reducing the influence of erroneous consensus information and enhancing the robustness of the model. The culmination of our efforts is the Bilateral Consensus Learning Network (BCLNet), which efficiently estimates camera pose and identifies inliers (true correspondences). Extensive experiments results demonstrate that our network not only surpasses state-of-the-art methods on benchmark datasets but also showcases robust generalization abilities across various feature extraction techniques. Noteworthily, BCLNet obtains 3.98% mAP5◦ gains over the second best method on unknown outdoor dataset, and obviously accelerates model training speed. The source code will be available at: https://***/guobaoxiao/BCLNet. Copyright © 2024, The Authors. All rights reserved.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Stable Learning via Triplex Learning

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第10期5卷 5267-5276页

作者： Yang, Shuai Jiang, Tingting Dang, Qianlong Gu, Lichuan Wu, Xindong Anhui Agricultural University School of Information and Artificial Intelligence Hefei230036 China Anhui Provincial Engineering Research Center for Agricultural Information Perception and Intelligent Computing Hefei230036 China Northwest A & F University College of Science Yangling712100 China Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data The Ministry of Education of China Hefei230601 China Hefei University of Technology School of Computer Science and Information Engineering Hefei230601 China

Stable learning aims to learn a model that generalizes well to arbitrary unseen target domain by leveraging a single source domain. Recent advances in stable learning have focused on balancing the distribution of confounders for each feature to eliminate spurious correlations. However, previous studies treat all features equally without considering the difficulties of confounder balancing associated with different features, and regard irrelevant features as confounders, deteriorating generalization performance. To tackle these issues, this article proposes a novel triplex learning (TriL) based stable learning algorithm, which performs sample reweighting, causal feature selection, and representation learning to remove spurious correlations. Specifically, first, TriL adaptively assigns weights to the confounder balancing term of each feature in accordance with the difficulties of confounder balancing, and aligns the confounder distribution of each feature by learning a group of sample weights. Second, TriL integrates the sample weights into a weighted cross-entropy model to compute causal effects of features for excluding irrelevant features from the confounder set. Finally, TriL relearns a set of sample weights and uses them to guide a new supervised dual-autoencoder containing two classifiers to learn feature representations. TriL forces the results of two classifiers to remain consistent for removing spurious correlations by using a cross-classifier consistency regularization. Extensive experiments on synthetic and two real-world datasets show the superiority of TriL compared with seven methods. © 2024 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

MA2-FPN for Tiny Object Detection from Remote Sensing Images 15

MA2-FPN for Tiny Object Detection from Remote Sensing Images

引用

15th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2022

作者： Li, Saiwei Tong, Qiang Liu, Xuhong Cui, Zhanqi Liu, Xiulei College of Computer Beijing Information Science and Technology University Beijing China Beijing Information Science and Technology University Beijing Advanced Innovation Center for Materials Genome Engineering Laboratory of Data Science and Information Studies Beijing China

ISBN: (数字)9781665488877

ISBN: (纸本)9781665488877

Tiny object detection has been a challenging topic in computer vision recent years. Moreover, in remote sensing field, smaller and clustered tiny objects make its detection more difficult compared to ground-based images. This makes general detectors fail to achieve good performance when facing tiny objects in remote sensing images. In this paper, we propose a Mask Augmented Attention Feature Pyramid Network(MA2-FPN) to detect tiny objects in remote sensing images, which consists of two modules, Attention Enhancement Module(AEM) and Mask Supervision Module(MSM). Specifically, AEM aggregates tiny target context and spatial feature information by large kernel separable convolutional attention mechanism, and MSM supervises AEM through a segmentation attention loss to aggregate attention information more accurately while suppressing the influence of irrelevant background. Experiments based on the AI-TOD benchmark show that our MA2-FPN achieves state-of-the-art(SOTA) level. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Contrastive Learning based Item Representation with Asymmetric Augmentation for Sequential Recommendation 23

Contrastive Learning based Item Representation with Asymmetr...

引用

2nd International Conference on Algorithms, data Mining, and Information Technology, ADMIT 2023

作者： Zeng, Kexiang Shi, Xiaoyu Xie, Hong Shang, Mingsheng Department of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing China Chongqing Key Laboratory of Big Data and IntelligentComputing Chongqing Institute of Green and Intelligent Technology Chongqing China

ISBN: (纸本)9798400707629

Contrastive learning has been widely applied in sequential recommendation to improve the recommendation performance. Existing contrastive learning methods focus on adjusting the views number of positive and negative samples to enhance the item representation via data-level augmentation(e.g., MMInfoRec). However, they generally ignore the sampled items still follow a long-tail distribution, i.e., a few popular items have a high-frequency occurrence in contrastive learning, while the majority of unpopular items have a low-frequency in contrastive learning. As a result, this imbalance in sample extraction leads to insufficient contrastive learning between popular and unpopular items, resulting in sub-optimal item representation. In this paper, we propose CA4Rec, a Contrastive learning based item representation with Asymmetric augmentation for Sequential Recommendation, that adopts an asymmetric augmented multi-instance contrastive learning strategy to enhance the item representation. Specifically, we first use the popularity-aware method to divide the entire item set into popular and unpopular items, then we generate k augmented views for popular items, and k + n augmented views for unpopular items. Finally, we use our proposed asymmetric multi-instance noise contrastive estimation (AMINCE) to perform contrastive learning calculation. Make sure there is sufficient contrast between popular and unpopular items to mitigate the issue. we implement the improvements on the state-of-the-art model and conduct extensive experiments on three benchmark datasets. The experimental results demonstrate that CA4Rec outperforms the state-of-the-art baselines. © 2023 Owner/Author.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Recent Trends in Text-to-Image GAN

Recent Trends in Text-to-Image GAN

引用

Intelligent Systems for Cybersecurity (ISCS), International Conference on

作者： Varun Kumar Dharmender Kumar Department of Computer Science and Technology Guru Jambheshwar University of Science and Technology Hisar Haryana India Department of Data Science and Artificial Intelligence Guru Jambheshwar University of Science and Technology Hisar Haryana India

ISBN: (数字)9798350375237

ISBN: (纸本)9798350375244

Generating genuine images from textual description is challenging for both computer vision and linguistic representation in text-to-image synthesis. Generative adversarial networks (GAN) are an emerging generative model that has been producing great results by generating high-quality images with diverse images. The present review provides an overview of GAN with its background like architecture, game theory key ideas, loss functions, performance metrics and challenges. Recent and relevant text-to-image GAN models are discussed, including Gradual Refinement GAN (GR-GAN), Generative Adversarial CLIPS (GALIP), GigaGAN and StyleGAN-T with their architecture, dataset used highlighting limitations, strengths, year, and applications and comparing their performance metrics like Inception Score (IS) and Fréchet Inception Distance (FID) with identifying future directions, such as drawing boundaries for open research challenges. The present review functions as an extensive knowledge base and is highly valuable for researchers and practitioners who are interested in learning more about text-to-image using GANs.

关键词： Measurement Reviews Knowledge based systems Text to image computer architecture Linguistics Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Reveal training performance mystery between Tensor Flow and PyTorch in the single GPU environment

引用

science China(Information sciences) 2022年第1期65卷 147-163页

作者： Hulin DAI Xuan PENG Xuanhua SHI Ligang HE Qian XIONG Hai JIN National Engineering Research Center for Big Data Technology and System Service Computing Technology and System LabSchool of Computer Science and Technology Huazhong University of Science and Technology Department of Computer Science University of Warwick

Deep learning has gained tremendous success in various fields while training deep neural networks(DNNs) is very compute-intensive, which results in numerous deep learning frameworks that aim to offer better usability and higher performance to deep learning practitioners. Tensor Flow and Py Torch are the two most popular frameworks. Tensor Flow is more promising within the industry context, while Py Torch is more appealing in academia. However, these two frameworks differ much owing to the opposite design philosophy:static vs dynamic computation graph. Tensor Flow is regarded as being more performance-friendly as it has more opportunities to perform optimizations with the full view of the computation graph. However, there are also claims that Py Torch is faster than Tensor Flow sometimes, which confuses the end-users on the choice between them. In this paper, we carry out the analytical and experimental analysis to unravel the mystery of comparison in training speed on single-GPU between Tensor Flow and Py Torch. To ensure that our investigation is as comprehensive as possible, we carefully select seven popular neural networks, which cover computer vision, speech recognition, and natural language processing(NLP). The contributions of this work are two-fold. First, we conduct the detailed benchmarking experiments on Tensor Flow and Py Torch and analyze the reasons for their performance difference. This work provides the guidance for the end-users to choose between these two frameworks. Second, we identify some key factors that affect the performance,which can direct the end-users to write their models more efficiently.

关键词： deep learning performance comparison TensorFlow PyTorch

来源：评论

学校读者我要写书评

暂无评论

p-Mean Regret for Stochastic Bandits

arXiv

引用

arXiv 2024年

作者： Krishna, Anand John, Philips George Barik, Adarsh Tan, Vincent Y.F. Department of Electrical and Computer Engineering NUS Singapore CNRS-CREATE Department of Computer Science NUS Singapore Institute of Data Science NUS Singapore Department of Mathematics NUS Singapore

In this work, we extend the concept of the p-mean welfare objective from social choice theory (Moulin 2004) to study p-mean regret in stochastic multi-armed bandit problems. The p-mean regret, defined as the difference between the optimal mean among the arms and the p-mean of the expected rewards, offers a flexible framework for evaluating bandit algorithms, enabling algorithm designers to balance fairness and efficiency by adjusting the parameter p. Our framework encompasses both average cumulative regret and Nash regret as special cases. We introduce a simple, unified UCB-based algorithm (EXPLORE-THEN-UCB)that achieves novel p-mean regret bounds. Our algorithm consists of two phases: a carefully calibrated uniform exploration phase to initialize sample means, followed by the UCB1 algorithm of Auer, Cesa-Bianchi, and Fischer (2002). Under mild assumptions, we prove that our algorithm achieves a p-mean regret bound of Õ (rT 2k|1p|! for all p ≤ −1, where k represents the number of arms and T the time horizon. When −1 (rkT1.125) . For the range 0 (qTk) , which matches the previously established lower bound up to logarithmic factors (Auer et al. 1995). This result stems from the fact that the p-mean regret of any algorithm is at least its average cumulative regret for p ≤ 1. In the case of Nash regret (the limit as p approaches zero), our unified approach differs from prior work (Barman et al. 2023), which requires a new Nash Confidence Bound algorithm. Notably, we achieve the same regret bound up to constant factors using our more general method. Copyright © 2024, The Authors. All rights reserved.

关键词： Stochastic 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：