检索结果-内蒙古大学图书馆

arxiv 2023年

作者： Gu, xianming Wang, Lihui Deng, Zeyu Cao, Ying Huang, xingyu Zhu, Yue-Min Engineering Research Center of Text Computing & Cognitive Intelligence Ministry of Education Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550025 China University Lyon INSA Lyon CNRS Inserm IRP Metislab CREATIS UMR5220 U1206 Lyon69621 France

Multi-modal medical image fusion is essential for the precise clinical diagnosis and surgical navigation since it can merge the complementary information in multi-modalities into a single image. The quality of the fused image depends on the extracted single modality features as well as the fusion rules for multi-modal information. Existing deep learning-based fusion methods can fully exploit the semantic features of each modality, they cannot distinguish the effective low and high frequency information of each modality and fuse them adaptively. To address this issue, we propose AdaFuse, in which multimodal image information is fused adaptively through frequency-guided attention mechanism based on Fourier transform. Specifically, we propose the cross-attention fusion (CAF) block, which adaptively fuses features of two modalities in the spatial and frequency domains by exchanging key and query values, and then calculates the cross-attention scores between the spatial and frequency features to further guide the spatial-frequential information fusion. The CAF block enhances the high-frequency features of the different modalities so that the details in the fused images can be retained. Moreover, we design a novel loss function composed of structure loss and content loss to preserve both low and high frequency information. Extensive comparison experiments on several datasets demonstrate that the proposed method outperforms state-of-the-art methods in terms of both visual quality and quantitative metrics. The ablation experiments also validate the effectiveness of the proposed loss and fusion strategy. © 2023, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Q&A driven conversational recommendation integrating multiple interest modeling

引用

Neurocomputing 2025年 647卷

作者： Haiping Zhu Yuqi Sun Shuwei Che Yan Chen School of Computer Science and Technology Xi’an Jiaotong University Xi’an 710049 China Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University Xi’an 710049 China Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an 710049 China

The conversational recommendation aims to provide users with recommendations in an interaction form of “System Ask-User Respond”. Existing studies rarely consider combining users’ multi-interest at the attribute level for preference modeling, and conduct inefficient conversational recommendation strategy learning, which affects the recommendation performance and conversation performance. To this end, we proposed a Q-A driven conversational recommendation method integrating multiple interest modeling. Specifically, we integrate the user’s positive and negative feedback to model a session dynamic graph, then use the signed graph convolutional network for graph representation learning, and we model multiple interest sequences based on the attention mechanism, then obtain the user interest state representation by fusing of sequence representations to solve the problem of insufficient user preference representation. Besides, we proposed a personalized decision space optimization method to narrow the range of action candidates and train the model with a multi-agent reinforcement learning method integrating hierarchical decision debiasing to solve the problem of poor conversational recommendation strategy learning effect. Experimental results on three public datasets, LastFM, Yelp, and Book, show that compared with existing conversational recommendation methods, our method demonstrates consistent performance improvement across all datasets. In addition, the results of ablation experiments verify the effectiveness of each component in our method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A granular-ball generation method based on local density for classification

引用

Information Sciences 2025年 717卷

作者： Liu, Fan Zhang, Qinghua xia, Shuyin xie, Qin Liao, Wei Zhang, Siyang School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and Telecommunication Chongqing400065 China Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing400065 China Tourism Multi-source Data Perception and Decision Technology Key Laboratory of the Ministry of Culture and Tourism Chongqing400065 China

As a new branch of granular computing, granular-ball computing (GBC) has become increasingly popular due to its high efficiency, robustness, and scalability. However, in classification tasks, the existing mainstream methods for generating granular-ball (GB) have two common issues: GBs generated by the existing methods are not accurate enough to describe the distribution of the original data and there are de-overlap operations in the existing GB generation process, which increase the workload of the GB generation process. Therefore, to solve the above two issues, a GB generation method based on local density (LDGBG) is proposed in this paper. First, centers of GBs are selected based on local density to ensure the generated GBs are more consistent with the original data distribution. Second, the method for calculating radii avoids overlaps and incorporates the idea of compact within class and decentralized between classes, which will improve classification performance. Furthermore, a sparsity index is introduced to assess the sparsity of datasets, thereby enabling more effective utilization of original samples in sparse datasets. Finally, comparative experiments are conducted on 27 benchmark datasets and the experimental results show that LDGBG is superior to the existing mainstream models in effectiveness and robustness. © 2025 Elsevier Inc.

关键词： Classification Granular computing Granular-ball computing Granular-ball generation Local density

来源：评论

学校读者我要写书评

暂无评论

USL-Net: Uncertainty Self-Learning Network for Unsupervised Skin Lesion Segmentation

arXiv

引用

arxiv 2023年

作者： Li, xiaofan Peng, Bo Hu, Jie Ma, Changyou Yang, Daipeng xie, Zhuyang School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education Chengdu611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Southwest Jiaotong University Chengdu611756 China Data Recovery Key Laboratory of Sichuan Province Neijiang Normal University Sichuan Neijiang641100 China

Unsupervised skin lesion segmentation offers several benefits, such as conserving expert human resources, reducing discrepancies caused by subjective human labeling, and adapting to novel environments. However, segmenting dermoscopic images without manual labeling guidance is a challenging task due to image artifacts such as hair noise, blister noise, and subtle edge differences. In this paper, we introduce an innovative Uncertainty Self-Learning Network (USL-Net) to eliminate the need for manual labeling guidance for the segmentation. Initially, features are extracted using contrastive learning, followed by the generation of Class Activation Maps (CAMs) as saliency maps. High-saliency regions in the map serve as pseudo-labels for lesion regions while low-saliency regions represent the background. Besides, intermediate regions can be hard to classify, often due to their proximity to lesion edges or interference from hair or blisters. Rather than risking potential pseudo-labeling errors or learning confusion by forcefully classifying these regions, they are taken as uncertainty regions by exempted from pseudo-labeling and allowing the network to self-learning. Further, we employ connectivity detection and centrality detection to refine foreground pseudo-labels and reduce noise-induced errors. The performance is further enhanced by the iterated refinement process. The experimental validation on ISIC-2017, ISIC-2018, and PH2 datasets demonstrates that its performance is comparable to supervised methods, and exceeds that of other existing unsupervised methods. On the typical ISIC-2017 dataset, our method outperforms state-of-the-art unsupervised methods by 1.7% in accuracy, 6.6% in Dice coefficient, 4.0% in Jaccard index, and 10.6% in sensitivity. Copyright © 2023, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Source-free domain adaptation via avatar prototype generation and adaptation

arXiv

引用

arxiv 2021年

作者： Qiu, Zhen Zhang, Yifan Lin, Hongbin Niu, Shuaicheng Liu, Yanxia Du, Qing Tan, Mingkui School of Software Engineering South China University of Technology School of Computing National University of Singapore Singapore Key Laboratory of Big Data and Intelligent Robot Ministry of Education Pazhou Laboratory

We study a practical domain adaptation task, called source-free unsupervised domain adaptation (UDA) problem, in which we cannot access source domain data due to data privacy issues but only a pre-trained source model and unlabeled target data are available. This task, however, is very difficult due to one key challenge: the lack of source data and target domain labels makes model adaptation very challenging. To address this, we propose to mine the hidden knowledge in the source model and exploit it to generate source avatar prototypes (i.e., representative features for each source class) as well as target pseudo labels for domain alignment. To this end, we propose a Contrastive Prototype Generation and Adaptation (CPGA) method. Specifically, CPGA consists of two stages: (1) prototype generation: by exploring the classification boundary information of the source model, we train a prototype generator to generate avatar prototypes via contrastive learning. (2) prototype adaptation: based on the generated source prototypes and target pseudo labels, we develop a new robust contrastive prototype adaptation strategy to align each pseudo-labeled target data to the corresponding source prototypes. Extensive experiments on three UDA benchmark datasets demonstrate the effectiveness and superiority of the proposed method. Copyright © 2021, The Authors. All rights reserved.

关键词： data privacy

来源：评论

学校读者我要写书评

暂无评论

A Deep Self-learning Classification Framework for Incomplete Medical Patents with Multi-label 15th

A Deep Self-learning Classification Framework for Incomplete...

引用

15th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2019, co-located with the 5th International Conference on Harmony Search, Soft computing and Applications, ICHSA 2019

作者： Luo, Mengzhen Shi, xiaoyu Ji, Qianqian Shang, Mingsheng He, xianbo Tao, Weiguo The Computer School of China West Normal University NanchongSichuan637002 China Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing400714 China

ISBN: (纸本)9783030325909

The classification of medical patents play an important role for pharmaceutical company, since medical patens with well labeled can significantly accelerate the process of new drug research. The previous studies using machine learning methods focus on classification the medical patents with single label. However, the classification of medical patents is a multi-label task, and the available data are always incomplete with losing the part information of patents. In this paper, we propose a deep self-learning classification framework that can deal with the incomplete medical patterns with multi-label issue. It consists of a text processor and patent classifier. For the text processor, a professional medical text thesaurus is built via GloVe method, which can learn more specialized vocabulary. For the patent classifier, we adopt a bidirectional long short term memory (Bi-LSTM) model to construct our patent classifier, which can learn the hidden knowledge from medical patents and associate with appropriate labels to medical patents automatically. Furthermore, an advanced focal loss function is design to further improve the classification accuracy. Experiments on the Thomson Reuters dataset demonstrate that our proposed method outperform the other existing methods in terms of precision and recall, when dealing with incomplete medical patents with multi-label issue.. © 2020, Springer Nature Switzerland AG.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Cross-View Fuzziness and Intra-view Uncertainty-Based Weight Reconstruction for Multi-view Feature Selection 11th

Cross-View Fuzziness and Intra-view Uncertainty-Based Weigh...

引用

11th International Joint Conference on Rough Sets, IJCRS 2025

作者： xiang, Biao Chen, Hongmei Mi, Yong Sang, Binbin Horng, Shi-Jinn Li, Tianrui Institute of Artificial Intelligence School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu 611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu 611756 China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education Southwest Jiaotong University Chengdu 611756 China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Southwest Jiaotong University Chengdu 611756 China College of Computer and Information Science Chongqing Normal University Chongqing 401331 China Department of Computer Science and Information Engineering Asia University Taichung 41354 Taiwan

ISBN: (纸本)9783031927430

Weight assignment is a universal and indispensable process in multi-view feature selection. However, most existing methods overlook the fuzziness and uncertainty implied in multi-view data. This may result in improper weight assignment, degrading the quality of selected features. A cross-view fuzziness and intra-view uncertainty-based weight reconstruction method (CFIUWR) is proposed for multi-view feature selection. With the fuzzy rough set theory, fuzzy approximation operators recognize cross-view fuzziness and intra-view uncertainty, which are evaluated by classification-related measurement. Cross-view fuzziness and intra-view uncertainty are incorporated to develop a reconstruction mechanism for view and feature weights. An optimization algorithm is derived, guaranteeing rapid convergence. Comparisons with state-of-the-art methods on several real-world datasets demonstrate the superiority of the CFIUWR. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Feature selection Fuzzy rough set Multi-view Weight reconstruction

来源：评论

学校读者我要写书评

暂无评论

No blind alignment but generation: A different view of continuous sign language recognition based on diffusion

引用

Pattern Recognition 2025年

作者： xi Geng Yunan Li Zhuoqi Ma Zixiang Lu Qiguang Miao School of Computer Science and Technology Xidian University Xi’an 710071 Shaanxi China Xi’an Key Laboratory of Big Data and Intelligent Vision Xidian University Xi’an 710071 Shaanxi China Key Laboratory of Collaborative Intelligence Systems Ministry of Education Xidian University Xi’an 710071 Shaanxi China

Continuous sign language recognition (CSLR) tasks typically rely on cross-modal alignment. However, due to the weakly supervised nature of CSLR, manual alignment often fails to align sign frames with glosses accurately. In this paper, we present a novel perspective for CSLR by treating it as a video-to-text generation task. Utilizing a diffusion model, we bypass the error-prone weakly supervised alignment. By fully exploiting the cross-modal feature correspondence capability of the diffusion model and capitalizing on the semantic consistency between sign videos and textual glosses, the gloss features are obtained directly. Furthermore, we introduce a contrastive learning-based strategy to enhance feature representation during the denoising phase, offering a sophisticated alternative to the simplistic attention mechanisms traditionally employed and guiding the denoising process of the diffusion model. Comprehensive experiments conducted on four public continuous sign language recognition datasets highlight the effectiveness of our generative approach in CSLR, demonstrating that it outperforms state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

One-shot handwriting imitation via self-supervised cross spatial transformer networks

引用

Neurocomputing 2025年 642卷

作者： Zhao, Bocheng Feng, Guanwen Zhang, Wenxing Li, Yunan Miao, Qiguang Liu, xiangzeng Liu, Ruyi School of Computer Science and Technology Xidian University Xi'an710071 China Xi'an Key Laboratory of Big Data and Intelligent Vision Xidian University Xi'an710071 China Key Laboratory of Collaborative Intelligence Systems Ministry of Educational of Computer Science and Technology Xidian University Xi'an710071 China

Generating stylized characters has been a focus of research for a long time. However, current font-led algorithms in the field of handwriting generation often perform suboptimally due to severe geometric distortion among handwriting samples. Additionally, the non-Euclidean characteristic of hidden embedding is identified as another key issue in our research. To address shape distortion, we propose a Self-Supervised Style Learning (SSL) method, aiming to increase the skeleton similarity between the output image and target. Furthermore, to enhance the Euclidean spatial distributions of the generator, this paper introduces a joint spatial transformer by refining the fusion process of content and style information using an attention mechanism. Moreover, the training process of the current GAN is reformed to meet the requirements of SSL. As a result, the proposed method enriches the calligraphy diversity of stylized handwriting generation compared to existing font generation algorithms. Evaluation of the proposed method using a public Chinese handwriting database demonstrates that our approach generates handwriting images with superior quality, stroke correctness, and calligraphy similarity when compared to other prevailing font imitation methods. © 2025

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Forensicability Assessment of Questioned Images in Recapturing Detection

arXiv

引用

arxiv 2022年

作者： Chen, Changsheng Zhao, Lin Cai, Rizhao Yu, Zitong Huang, Jiwu Kot, Alex C. The Guangdong Key Laboratory of Intelligent Information Processing and Shenzhen Key Laboratory of Media Security National Engineering Laboratory for Big Data System Computing Technology College of Electronics and Information Engineering Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society China The Department of Electrical and Electrics Engineering Nanyang Technological University Singapore639798 Singapore

Recapture detection of face and document images is an important forensic task. With deep learning, the performances of face anti-spoofing (FAS) and recaptured document detection have been improved significantly. However, the performances are not yet satisfactory on samples with weak forensic cues. The amount of forensic cues can be quantified to allow a reliable forensic result. In this work, we propose a forensicability assessment network to quantify the forensicability of the questioned samples. The low-forensicability samples are rejected before the actual recapturing detection process to improve the efficiency of recapturing detection systems. We first extract forensicability features related to both image quality assessment and forensic tasks. By exploiting domain knowledge of the forensic application in image quality and forensic features, we define three task-specific forensicability classes and the initialized locations in the feature space. Based on the extracted features and the defined centers, we train the proposed forensic assessment network (FANet) with cross-entropy loss and update the centers with a momentum-based update method. We integrate the trained FANet with practical recapturing detection schemes in face anti-spoofing (FAS) and recaptured document detection tasks. Experimental results show that, for a generic CNN-based FAS scheme, FANet reduces the EERs from 33.75% to 19.23% under ROSE to IDIAP protocol by rejecting samples with the lowest 30% forensicability scores. The performance of FAS schemes is poor in the rejected samples, with EER as high as 56.48%. Similar performances in rejecting low-forensicability samples have been observed for the state-of-the-art approaches in FAS and recaptured document detection tasks. To the best of our knowledge, this is the first work that assesses the forensicability of recaptured document images and improves the system efficiency. Copyright © 2022, The Authors. All rights reserved.

关键词： Image quality

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：