检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Hu, Gangqiang Lu, Jianfeng Han, Jianmin Cao, Shuqin Liu, Jing Fu, Hao School of Computer Science and Technology Zhejiang Normal University China School of Computer Science and Technology Wuhan University of Science and Technology China Key Laboratory of Social Computing and Cognitive Intelligence Dalian University of Technology Ministry of Education China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology China

ISBN: (纸本)157735897X

Due to the sensitivity of data, Federated Learning (FL) is employed to enable distributed machine learning while safeguarding data privacy and accommodating the requirements of various devices. However, in the context of semi-decentralized FL, clients’ communication and training states are dynamic. This variability arises from local training fluctuations, heterogeneous data distributions, and intermittent client participation. Most existing studies primarily focus on stable client states, neglecting the dynamic challenges inherent in real-world scenarios. To tackle this issue, we propose a TRust-Aware clIent scheduLing mechanism called TRAIL, which assesses client states and contributions, enhancing model training efficiency through selective client participation. We focus on a semi-decentralized FL framework where edge servers and clients train a shared global model using unreliable intra-cluster model aggregation and inter-cluster model consensus. First, we propose an adaptive hidden semi-Markov model to estimate clients’ communication states and contributions. Next, we address a client-server association optimization problem to minimize global training loss. Using convergence analysis, we propose a greedy client scheduling algorithm. Finally, our experiments conducted on real-world datasets demonstrate that TRAIL outperforms state-of-the-art baselines, achieving an improvement of 8.7% in test accuracy and a reduction of 15.3% in training loss. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Divide-Solve-Combine: An Interpretable and Accurate Prompting Framework for Zero-shot Multi-Intent Detection 39

Divide-Solve-Combine: An Interpretable and Accurate Promptin...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Qin, Libo Chen, Qiguang Zhou, Jingxuan Wang, Jin Fei, Hao Che, Wanxiang Li, Min School of Computer Science and Engineering Central South University China Key Laboratory of Data Intelligence and Advanced Computing in Provincial Universities Soochow University China Research Center for Social Computing and Information Retrieval Harbin Institute of Technology China Yunnan University China National University of Singapore Singapore

ISBN: (纸本)157735897X

Zero-shot multi-intent detection is capable of capturing multiple intents within a single utterance without any training data, which gains increasing attention. Building on the success of large language models (LLM), dominant approaches in the literature explore prompting techniques to enable zero-shot multi-intent detection. While significant advancements have been witnessed, the existing prompting approaches still face two major issues: lacking explicit reasoning and lacking interpretability. Therefore, in this paper, we introduce a Divide-Solve-Combine Prompting (DSCP) to address the above issues. Specifically, DSCP explicitly decomposes multi-intent detection into three components including (1) single-intent division prompting is utilized to decompose an input query into distinct sub-sentences, each containing a single intent;(2) intent-by-intent solution prompting is applied to solve each sub-sentence recurrently;and (3) multi-intent combination prompting is employed for combining each sub-sentence result to obtain the final multi-intent result. By decomposition, DSCP allows the model to track the explicit reasoning process and improve the interpretability. In addition, we propose an interactive divide-solve-combine prompting (Inter-DSCP) to naturally capture the interaction capabilities of large language models. Experimental results on two standard multi-intent benchmarks (i.e., MIXATIS and MIXSNIPS) reveal that both DSCP and Inter-DSCP obtain substantial improvements over baselines, achieving superior performance and higher interpretability. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive multiple-view label propagation for semi-supervised classification 1

引用

1st International Conference on Neural Computing for Advanced Applications, NCAA 2020

作者： Jia, Lei Zhang, Huan Zhang, Zhao School of Computer Science and Technology Soochow University Suzhou215006 China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou215006 China School of Computer and Information Science Hefei University of Technology Hefei China

ISBN: (数字)9789811576706

ISBN: (纸本)9789811576690

We propose a novel Adaptive Multiple-view Label Propagation (MLP) framework for semi-supervised classification. MLP performs classification on multiple views rather than on the single view, and can exploit the complementarity of multiple views in the label prediction process. Moreover, MLP integrates the multi-view label propagation and the adaptive multiple graph weight learning into a unified model, where a linear transformation is used to enforce different weights form different view spaces. Thus, an optimal graph weight matrix can be constructed from each view. Due to the adaptive manner for defining the weight matrices from multiple views, MLP can avoid the complex and tricky process to select the neighborhood size or kernel parameter. Extensive results on real data show that MLP can deliver the enhanced performances, by comparing with other related techniques. © Springer Nature Singapore Pte Ltd. 2020.

关键词： Linear transformations

来源：评论

学校读者我要写书评

暂无评论

NEAT-Net: An Unsupervised Cross-View Prior Inpainting Network for CBCT Metal Artifact Reduction

NEAT-Net: An Unsupervised Cross-View Prior Inpainting Networ...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Yang Yang Zhan Tong Xinyun Zhong Yijie Shi Yan Xi Wenxue Yu Zhan Wu Yang Chen Laboratory of Image Science and Technology the School of Computer Science and Engineering Southeast University Nanjing China First-Imaging Tech Shanghai China Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing the Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Nanjing China

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Intraoperative Cone-Beam Computed Tomography (CBCT) facilitates intraoperative navigation for Minimally Invasive Spine Surgery (MISS). However, high-attenuation metal implants used in MISS often cause metal artifacts in the reconstructed CBCT images. Current algorithms do not consider the cross-view information in the projection-domain for metal artifact reduction (MAR). Inaccurate projection-domain inpainting results in CBCT MAR lead to tissue blurring and secondary artifacts, significantly compromising the accuracy of CBCT-guided MISS and increasing surgical risks. To address the above challenge, in this paper, we propose a novel unsupervised cross-view prior inpainting network for CBCT Metal Artifact Reduction named NEAT-Net. Firstly, a cross-view prior multi-scale inpainting module is constructed to learn the inter-view complementary information. Secondly, a hybrid feature attention module is proposed to adaptively fuse cross-view features. In addition, an unsupervised training approach is proposed to directly learn from metal-affected data. Extensive experiments are conducted to verify the effectiveness of our algorithm on a real clinical dataset.

关键词： Training Minimally invasive surgery Accuracy Navigation Fuses Computed tomography Metals Implants Engineering in medicine and biology Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Ascl: Accelerating Semi-Supervised Learning Via Contrastive Learning

SSRN

引用

SSRN 2024年

作者： Liu, Haixiong Li, Zuoyong Wu, Jiawei Zeng, Kun Hu, Rong Zeng, Wei Fujian Provincial Key Laboratory of Big Data Mining and Applications School of Computer Science and Mathematics Fujian University of Technology Fuzhou350118 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Data Science Minjiang University Fuzhou350121 China School of Intelligent Systems Engineering Shenzhen Campus of Sun Yat-sen University Guangdong Shenzhen518107 China The Key Laboratory of Cognitive Computing and Intelligent Information Processing of Fujian Education Institutions Wuyi University Wuyishan354300 China School of Physics and Mechanical and Electrical Engineering Longyan University Longyan364012 China

SSL(Semi-supervised learning) is widely used in machine learning, which leverages labeled and unlabeled data to improve model performance. SSL aims to optimize class mutual information, but noisy pseudo-labels introduce false class information due to the scarcity of labels. Therefore, these algorithms often need significant training time to refine pseudo-labels for performance improvement iteratively. To tackle this challenge, we propose a novel plug-and-play method named ASCL(Accelerating Semi-Supervised Learning via Contrastive Learning). This method combines contrastive learning with uncertainty-based selection for performance improvement and accelerates the convergence of SSL algorithms. Contrastive learning initially emphasizes the mutual information between samples as a means to decrease dependence on pseudo-labels. Subsequently, it gradually turns to maximizing the mutual information between classes, aligning with the objective of semi-supervised learning. Uncertainty-based selection provides a robust mechanism for acquiring pseudo-labels. The combination of the contrastive learning module and the uncertainty-based selection module forms a virtuous cycle to improve the performance of the proposed model. Extensive experiments demonstrate that ASCL outperforms state-of-the-art methods in terms of both convergence efficiency and performance. In the experimental scenario where only one label is assigned per class in the CIFAR-10 dataset, the application of ASCL to Pseudo-label, UDA (Unsupervised Data Augmentation for Consistency Training), and Fixmatch benefits substantial improvements in classification accuracy. Specifically, the results demonstrate notable improvements in respect of 16.32%, 6.9%, and 24.43% when compared to the original outcomes. Moreover, the required training time is reduced by almost 50%. © 2024, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Spatial-Spectral Transformer for Local and Global Hyperspectral Image Classification

Spatial-Spectral Transformer for Local and Global Hyperspect...

引用

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： MengXin Cao Guixin Zhao Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

Deep learning techniques have become increasingly prevalent in hyperspectral image (HSI) classification. However, convolutional neural network (CNN)-based approaches often struggle with inefficient utilization of spectral sequence data and inadequate processing of fine-grained spectral details. In contrast, transformer models are inherently designed to capture sequence dependencies across spectral bands. Yet, most existing approaches tend to focus on either local or global feature extraction separately, which limits their ability to fully exploit the spectral information. To overcome these limitations, we propose the Local and Global Fusion Spectral Transformer (LGFST), an innovative architecture that combines Swin Transformer blocks, standard Transformer blocks, and a novel Local-Global Fusion (LGF) module. This architecture is designed to simultaneously capture both local and global features, thereby improving the extraction of detailed spectral information. The Swin Transformer block, integrated with patch merging and hierarchical attention mechanisms, expands the receptive field and enhances local feature representation through both intra- and cross-window interactions. Meanwhile, the Transformer block performs self-attention across all tokens to extract global features. The fusion of local and global features from these two blocks effectively improves the texture and discriminative power of spectral data, leading to enhanced classification performance, especially in scenarios with dense class distributions. Finally, the LGF module facilitates interaction between local and global feature sets, ensuring a seamless integration of information from both blocks. Extensive experiments on three benchmark HSI datasets demonstrate that LGFST outperforms conventional transformer models and sets new benchmarks in performance compared to state-of-the-art methods.

关键词： Merging Benchmark testing Transformers Feature extraction Distortion Sensors Data mining Standards Hyperspectral imaging Image classification

来源：评论

学校读者我要写书评

暂无评论

PMC-CNN: Trajectory Prediction Method Fusing Pedestrian Motion Features

PMC-CNN: Trajectory Prediction Method Fusing Pedestrian Moti...

引用

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

作者： Xiling Cao Yan Li Hong Liu School of Information Science and Engineering Shandong Normal University Shandong Provincial Key Laboratory for Distributed Computer Software Novel Technology Jinan China Inspur (Shandong) Computer Technology Co Ltd. Jinan China

ISBN: (数字)9798350356670

ISBN: (纸本)9798350356687

Predicting how pedestrians will move is a valuable and challenging task. It can be applied to various domains, such as crowd evacuation and autonomous driving. However, in practice, scene information and pedestrian interaction make it difficult to accurately predict pedestrian trajectories. Therefore, more effective processing of information affecting pedestrian trajectories is particularly important. Extraction of pedestrian motion features is insufficient in current research in this area. To address this problem, a neural network trajectory prediction method, PMC-CNN, is proposed. This method incorporates pedestrian motion features and stores the heterogeneous information required for prediction within a knowledge graph. Furthermore, it combines this information with the proposed IN-EX pedestrian motion model, resulting in an improvement in prediction accuracy. In addition, this research applies the prediction framework to a crowd evacuation scenario to improve the efficiency of crowd evacuation. This verifies the effectiveness and practicality of our proposed model.

关键词： Pedestrians Accuracy Urban planning Neural networks Safety management Knowledge graphs Predictive models Feature extraction Real-time systems Trajectory

来源：评论

学校读者我要写书评

暂无评论

DAMPER: A Dual-Stage Medical Report Generation Framework with Coarse-Grained MeSH Alignment and Fine-Grained Hypergraph Matching

arXiv

引用

arXiv 2024年

作者： Huang, Xiaofei Chen, Wenting Liu, Jie Lu, Qisheng Luo, Xiaoling Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Electrical Engineering City University of Hong Kong Kowloon Hong Kong National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

Medical report generation is crucial for clinical diagnosis and patient management, summarizing diagnoses and recommendations based on medical imaging. However, existing work often overlook the clinical pipeline involved in report writing, where physicians typically conduct an initial quick review followed by a detailed examination. Moreover, current alignment methods may lead to misaligned relationships. To address these issues, we propose DAMPER, a dual-stage framework for medical report generation that mimics the clinical pipeline of report writing in two stages. In the first stage, a MeSH-Guided Coarse-Grained Alignment (MCG) stage that aligns chest X-ray (CXR) image features with medical subject headings (MeSH) features to generate a rough keyphrase representation of the overall impression. In the second stage, a Hypergraph-Enhanced Fine-Grained Alignment (HFG) stage that constructs hypergraphs for image patches and report annotations, modeling high-order relationships within each modality and performing hypergraph matching to capture semantic correlations between image regions and textual phrases. Finally,the coarse-grained visual features, generated MeSH representations, and visual hypergraph features are fed into a report decoder to produce the final medical report. Extensive experiments on public datasets demonstrate the effectiveness of DAMPER in generating comprehensive and accurate medical reports, outperforming state-of-the-art methods across various evaluation metrics. Copyright © 2024, The Authors. All rights reserved.

关键词： Coarse-grained modeling

来源：评论

学校读者我要写书评

暂无评论

Fake It till You Make It: Curricular Dynamic Forgery Augmentations towards General Deepfake Detection

arXiv

引用

arXiv 2024年

作者： Lin, Yuzhen Song, Wentang Li, Bin Li, Yuezun Ni, Jiangqun Chen, Han Li, Qiushi Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security SZU-AFS Joint Innovation Center for AI Technology Shenzhen University Shenzhen China College of Computer Science and Technology Ocean University of China Qingdao China School of Cyber Science and Technology Sun Yat-Sen University Department of New Networks Peng Cheng Laboratory Shenzhen China

Previous studies in deepfake detection have shown promising results when testing face forgeries from the same dataset as the training. However, the problem remains challenging when one tries to generalize the detector to forgeries from unseen datasets and created by unseen methods. In this work, we present a novel general deepfake detection method, called Curricular Dynamic Forgery Augmentation (CDFA), which jointly trains a deepfake detector with a forgery augmentation policy network. Unlike the previous works, we propose to progressively apply forgery augmentations following a monotonic curriculum during the training. We further propose a dynamic forgery searching strategy to select one suitable forgery augmentation operation for each image varying between training stages, producing a forgery augmentation policy optimized for better generalization. In addition, we propose a novel forgery augmentation named self-shifted blending image to simply imitate the temporal inconsistency of deepfake generation. Comprehensive experiments show that CDFA can significantly improve both cross-datasets and cross-manipulations performances of various naive deepfake detectors in a plug-and-play way, and make them attain superior performances over the existing methods in several benchmark datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

A Multi-Stage Goal-Driven Network for Pedestrian Trajectory Prediction

arXiv

引用

arXiv 2024年

作者： Wu, Xiuen Wang, Tao Cai, Yuanzheng Liang, Lingyu Papageorgiou, George Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China College of Computer and Data Science Fuzhou University Fuzhou China School of Electronic and Information Engineering South China University of Technology Guangzhou China SYSTEMA Research Center European University Cyprus Nicosia Cyprus

Pedestrian trajectory prediction plays a pivotal role in ensuring the safety and efficiency of various applications, including autonomous vehicles and traffic management systems. This paper proposes a novel method for pedestrian trajectory prediction, called multi-stage goal-driven network (MGNet). Diverging from prior approaches relying on stepwise recursive prediction and the singular forecasting of a long-term goal, MGNet directs trajectory generation by forecasting intermediate stage goals, thereby reducing prediction errors. The network comprises three main components: a conditional variational autoencoder (CVAE), an attention module, and a multi-stage goal evaluator. Trajectories are encoded using conditional variational autoencoders to acquire knowledge about the approximate distribution of pedestrians' future trajectories, and combined with an attention mechanism to capture the temporal dependency between trajectory sequences. The pivotal module is the multistage goal evaluator, which utilizes the encoded feature vectors to predict intermediate goals, effectively minimizing cumulative errors in the recursive inference process. The effectiveness of MGNet is demonstrated through comprehensive experiments on the JAAD and PIE datasets. Comparative evaluations against state-of-the-art algorithms reveal significant performance improvements achieved by our proposed method. Copyright © 2024, The Authors. All rights reserved.

关键词： Trajectories

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：