检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Chen, Jiajie Sang, Yu Zhang, Peng-Fei Wang, Jiaan Qu, Jianfeng Li, Zhixu School of Computer Science and Technology Soochow University Suzhou China School of Artificial Intelligence and Computer Science Jiangnan University China School of Electrical Engineering and Computer Science University of Queensland Australia School of Information Renmin University of China Beijing China International College (Suzhou Research Institute) Renmin University of China Suzhou China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China

ISBN: (纸本)157735897X

Next POI recommendation aids users in predicting their destinations of interest and plays an increasingly vital role in location-based social services. Recent works focus on analyzing both long-term and short-term interests in POI recommendation to gain a deeper understanding of user profiles. However, these methods for modeling long-term user's sequences primarily rely on the Transformer model, which functions as a low-pass filter, often leading to the loss of high-frequency information. Additionally, long-term and short-term sequences are typically modeled independently, with short-term sequences often defined solely by the most recent check-ins, overlooking their interactions and dependencies. Therefore, we propose Enhancing Long-and Short-Term Representations for Next POI Recommendations via Frequency and Hierarchical Contrastive Learning (FHCRec). FHCRec captures both high-frequency and low-frequency information in long-term sequences to model richer long-term user's preference representations. Moreover, it harnesses the characteristics of the short-term subsequences embedded within long-term sequences to enhance short-term preference characterization via local and global hierarchical contrastive learning, resulting in more personalized short-term preferences. The enhanced long-term and short-term preferences are integrated to improve model recommendation performance. Extensive experiments on three real-world datasets demonstrate the effectiveness of our method. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). 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

Underwater acoustic intelligent spectrum sensing with multimodal data fusion: An Mul-YOLO approach

引用

Future Generation Computer Systems 2025年 173卷

作者： Li, Yufang Zhang, Liliang Wang, Kai Xu, Lingwei Gulliver, T. Aaron Department of Information Science and Technology Qingdao University of Science and Technology Qingdao266061 China Xiangyang Sub-center of National Engineering Research Center for Water Transport Safety Hubei University of Arts and Science Xiangyang441053 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China Nanning530006 China Department of Electrical and Computer Engineering University of Victoria VictoriaBC V8W 2Y2 Canada

Realizing the Ocean Internet of Things (OIoT) requires diverse and comprehensive real-time marine data. This creates significant demands on spectrum resources for effective underwater communication. Coexisting users in the OIoT can generate massive amounts of data, which results in competition for underwater acoustic spectrum. To address the problem of poor utilization of this spectrum in complex and dynamic ocean environments, this paper proposes an intelligent spectrum sensing scheme based on multimodal data fusion. First, the system obtains time series data for the underwater acoustic signals and a wavelet transform is used to obtain the corresponding image data. The time series and image data constitute multimodal data that provide a more comprehensive time and space perspective and improve the diversity of features. Then, unsupervised learning with a Denoising Autoencoder is used to extract high-quality features from the time series data. Finally, a parallel dual Backbone YOLO network is constructed to compensate for the inability of traditional YOLO to extract multimodal features. One branch captures key temporal features through a network built with deep separable convolutions, while the other branch captures key spatial features using an improved CSPDarknet. This Mul-YOLO network can extract hierarchical structure information from underwater acoustic signals and integrate the diverse multilevel features of the data to achieve accurate spectrum sensing. Compared with Convolutional Neural Network (CNN), ResNet, Swin-Transformer, ConvNext and YOLOv5 algorithms, the average detection probability of the Mul-YOLO algorithm is increased by about 5.9% to 18.9%, and the average false alarm probability is optimized by about 7% to 12.7% in the range of signal-to-noise ratio from −12 dB to 0 dB. The results given show that the proposed algorithm can detect spectrum holes with high accuracy and effectively avoid interference between users. © 2025 Elsevier B.V.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Spirit distillation: A model compression method with multi-domain knowledge transfer

arXiv

引用

arXiv 2021年

作者： Wu, Zhiyuan Jiang, Yu Zhao, Minghao Cui, Chupeng Yang, Zongmin Xue, Xinhui Qi, Hong College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation Knowledge Engineering of Ministry of Education Jilin University Changchun China

Recent applications pose requirements of both cross-domain knowledge transfer and model compression to machine learning models due to insufficient training data and limited computational resources. In this paper, we propose a new knowledge distillation model, named Spirit Distillation (SD), which is a model compression method with multidomain knowledge transfer. The compact student network mimics out a representation equivalent to the front part of the teacher network, through which the general knowledge can be transferred from the source domain (teacher) to the target domain (student). To further improve the robustness of the student, we extend SD to Enhanced Spirit Distillation (ESD) in exploiting a more comprehensive knowledge by introducing the proximity domain which is similar to the target domain for feature extraction. Results demonstrate that our method can boost mIOU and high-precision accuracy by 1.4% and 8.2% respectively with 78.2% segmentation variance, and can gain a precise compact network with only 41.8% FLOPs. Copyright © 2021, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

U-HRMLP: Refining Segmentation Boundaries in Histopathology Images

U-HRMLP: Refining Segmentation Boundaries in Histopathology ...

引用

IEEE International Symposium on Biomedical Imaging

作者： Tao Wang Kai Zhang Weijie Wang Mingrui Ma Ye Zhang He Zhao Guixia Liu College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China School of Information Science and Engineering Shandong Normal University China Department of Information Engineering and Computer Science University of Trento Italy Faculty of Information Engineering and Automation Kunming University of Science and Technology China School of Information Science and Technology Northeast Normal University China

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

Segmenting regions of interest in histopathology images is a critical prerequisite for biomedical applications. CNN-based models have advanced medical image segmentation, yet accurately delineating boundaries is still challenging. This challenge arises from the loss of spatial resolution due to downsampling and the complexity of capturing contextual information when upsampling to the original resolution. To address these issues, we design U-HRMLP, a U-shaped network based on a hybrid combination of HRNet and Multi-Layer Perceptron (MLP). Specifically, we propose a multi-scale feature fusion module to avoid the loss of image resolution in the encoding stage as much as possible. Simultaneously, we propose an MLP-based decoding block to recover image details and resolution progressively, alleviating the issues related to the inadequate segmentation of smaller objects and the blurring of tissue boundaries. Results on the MoNuSeg and GlaS datasets demonstrate that U-HRMLP outperforms conventional or transformer-based methods and achieves state-of- the-art performance.

关键词： Measurement Image segmentation Histopathology Biological system modeling Semantics Refining Transformers

来源：评论

学校读者我要写书评

暂无评论

Bounding-box deep calibration for high performance face detection

arXiv

引用

arXiv 2021年

作者： Luo, Shi Li, Xiongfei Zhang, Xiaoli College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China

Modern convolutional neural networks (CNNs)‐based face detectors have achieved tremendous strides due to large annotated datasets. However, misaligned results with high detection confidence but low localization accuracy restrict the further improvement of detection performance. In this paper, the authors first predict high confidence detection results on the training set itself. Surprisingly, a considerable part of them exist in the same misalignment problem. Then, the authors carefully examine these cases and point out that annotation misalignment is the main reason. Later, a comprehensive discussion is given for the replacement rationality between predicted and annotated bounding‐boxes. Finally, the authors propose a novel Bounding‐Box Deep Calibration (BDC) method to reasonably replace misaligned annotations with model predicted bounding‐boxes and offer calibrated annotations for the training set. Extensive experiments on multiple detectors and two popular benchmark datasets show the effectiveness of BDC on improving models' precision and recall rate, without adding extra inference time and memory consumption. Our simple and effective method provides a general strategy for improving face detection, especially for light‐weight detectors in real‐time situations. © 2021, CC BY.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Multi-focus image fusion based on fully convolutional networks

引用

Frontiers of Information Technology & Electronic engineering 2020年第7期21卷 1019-1033页

作者： Rui GUO Xuan-jing SHEN Xiao-yu DONG Xiao-li ZHANG Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin UniversityChangchun 130012China College of Computer Science and Technology Jilin UniversityChangchun 130012China

We propose a multi-focus image fusion method, in which a fully convolutional network for focus detection(FD-FCN) is constructed. To obtain more precise focus detection maps, we propose to add skip layers in the network to make both detailed and abstract visual information available when using FD-FCN to generate maps. A new training dataset for the proposed network is constructed based on dataset CIFAR-10. The image fusion algorithm using FD-FCN contains three steps: focus maps are obtained using FD-FCN, decision map generation occurs by applying a morphological process on the focus maps, and image fusion occurs using a decision map. We carry out several sets of experiments, and both subjective and objective assessments demonstrate the superiority of the proposed fusion method to state-of-the-art algorithms.

关键词： Multi-focus image fusion Fully convolutional networks Skip layer Performance evaluation

来源：评论

学校读者我要写书评

暂无评论

When Federated Recommendation Meets Cold-Start Problem: Separating Item Attributes and User Interactions

arXiv

引用

arXiv 2023年

作者： Zhang, Chunxu Zhang, Zijian Long, Guodong Yan, Peng Zhou, Tianyi Yang, Bo College of Computer Science and Technology Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Changchun China College of Computer Science and Technology Jilin University City University of Hong Kong China Australian Artificial Intelligence Institute FEIT University of Technology Sydney Sydney Australia Computer Science and UMIACS University of Maryland Maryland United States

Federated recommendation systems usually trains a global model on the server without direct access to users’ private data on their own devices. However, this separation of the recommendation model and users’ private data poses a challenge in providing quality service, particularly when it comes to new items, namely cold-start recommendations in federated settings. This paper introduces a novel method called Item-aligned Federated Aggregation (IFedRec) to address this challenge. It is the first research work in federated recommendation to specifically study the cold-start scenario. The proposed method learns two sets of item representations by leveraging item attributes and interaction records simultaneously. Additionally, an item representation alignment mechanism is designed to align two item representations and learn the meta attribute network at the server within a federated learning framework. Experiments on four benchmark datasets demonstrate IFedRec’s superior performance for cold-start scenarios. Furthermore, we also verify IFedRec owns good robustness when the system faces limited client participation and noise injection, which brings promising practical application potential in privacy-protection enhanced federated recommendation systems. The implementation code is available1 Copyright © 2023, The Authors. All rights reserved.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

PepLand: A large-scale pre-trained peptide representation model for a comprehensive landscape of both canonical and non-canonical amino acids

arXiv

引用

arXiv 2023年

作者： Zhang, Ruochi Wu, Haoran Xiu, Yuting Li, Kewei Chen, Ningning Wang, Yu Wang, Yan Gao, Xin Zhou, Fengfeng Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Jilin Changchun130012 China School of Artificial Intelligence Jilin University Changchun130012 China Syneron Technology Guangzhou510700 China College of Computer Science and Technology Jilin University Jilin Changchun130012 China Thuwal23955 Saudi Arabia Thuwal23955 Saudi Arabia

In recent years, the scientific community has become increasingly interested on peptides with non-canonical amino acids due to their superior stability and resistance to proteolytic degradation. These peptides present promising modifications to biological, pharmacological, and physiochemical attributes in both endogenous and engineered peptides. Notwithstanding their considerable advantages, the scientific community exhibits a conspicuous absence of an effective pre-trained model adept at distilling feature representations from such complex peptide sequences. We herein propose PepLand, a novel pre-training architecture for representation and property analysis of peptides spanning both canonical and non-canonical amino acids. In essence, PepLand leverages a comprehensive multi-view heterogeneous graph neural network tailored to unveil the subtle structural representations of peptides. Empirical validations underscore PepLand's effectiveness across an array of peptide property predictions, encompassing protein-protein interactions, permeability, solubility, and synthesizability. The rigorous evaluation confirms PepLand's unparalleled capability in capturing salient synthetic peptide features, thereby laying a robust foundation for transformative advances in peptide-centric research domains. We have made all the source code utilized in this study publicly accessible via GitHub at https://***/zhangruochi/pepland. © 2023, CC BY-NC-ND.

关键词： Peptides

来源：评论

学校读者我要写书评

暂无评论

Automatic Controversy Detection Based on Heterogeneous Signed Attributed Network and Deep Dual-Layer Self-Supervised Community Analysis

SSRN

引用

SSRN 2023年

作者： Li, Ying Zhang, Xiao Liang, Yu Li, Qianqian Key Laboratory of Symbolic Computation and Knowledge Engineering College of Computer Science and Technology Jilin University Qianjin Street Jilin Changchun130012 China Institutes of Science and Development Chinese Academy of Sciences ZhongGuanCun BeiYiTiao Beijing100190 China School of Public Policy and Management University of Chinese Academy of Sciences ShiJingShan YuQuanLu Beijing100049 China

Controversial analysis entails identifying and scrutinizing contentious events or issues within a specific domain. Detecting controversy, particularly on social media, poses challenges due to the need to consider numerous contents and user interactions. Unlike previous work, rather than studying controversy on limited knowledge of the topic discussion, we introduce multidimensional and heterogeneous information to conduct a comprehensive evaluation. Our method to quantify controversy is based on heterogeneous signed attributed network. This framework constructs a comprehensive heterogeneous signed attributed network to integrate diverse semantic and structural information on social media, encompassing user, retweet, comment, summary, topic, sentiment information, and user attributes. We introduce a deep dual-layer self-supervised algorithm for community detection and controversial analysis within this network. We gauge controversy levels in hot events via community distinctions, betweenness centrality, and user representations. Extensive comparisons of state-of-the-art baseline approaches are performed. We find that existing methods shows instability on different datasets. Whereas our approach integrates the multidimensional features of topics and also takes into account various computational results, our method consistently yields stable results. A user-friendly web server has been developed for accessible analysis of other hot events (http://***/contro/). © 2023, The Authors. All rights reserved.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Document-Level Relation Extraction with Entity Type Constraints

SSRN

引用

SSRN 2024年

作者： Han, Ridong Peng, Tao Zhu, BeiBei Bi, Haijia Han, Jiayu Liu, Lu College of Computer Science and Technology Jilin University Jilin Changchun130012 China College of Software Jilin University Jilin Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin Changchun130012 China College of Computer and Artificial Intelligence Liaoning Normal University Liaoning Dalian116081 China Department of Linguistics University of Washington SeattleWA98195 United States

Long-tail problem and multi-label problem are two commonly encountered challenges in document-level relation extraction task. Current efforts are concerned with enhancing the representations of entity pairs through Transformer or document graphs, which cannot tackle the above challenges well. Relation correlations are a potential solution, which allows head relations to assist in the training of tail ones by transferring correlation knowledge between them, and can measure the semantic distance between relations to assist the classifier in assigning multiple semantically similar relations to multi-label instances. This paper proposes to learn relation correlations from both global and local views using entity type constraints, which means that the subject-object entity types limit the scope of possible relations. Globally, we statistically construct the Type-constrained Graph between entity types and relations, which formulates all possible subject/object types for each relation. Different relations are connected by common entity types, reflecting the desired correlations. Locally, given an entity pair, the classification probability of relations matching its entity types should be greater than those unmatched. Therefore, the Type-constrained Loss is proposed to make the matched relations have greater probabilities. Detailed experiments are conducted on DocRED and DWIE datasets, and our model significantly outperforms baselines under long-tail and multi-label setups. © 2024, The Authors. All rights reserved.

关键词： Extraction

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：