检索结果-内蒙古大学图书馆

Consistent image processing based on co-saliency

CAAI Transactions on Intelligence Technology 2021年第3期6卷 324-337页

作者： Xiangnan Ren Jinjiang Li Zhen Hua Xinbo Jiang School of Computer Science and Technology Shandong Technology and Business UniversityYantaiChina Co-innovation Center of Shandong Colleges and Universities Future Intelligent ComputingShandong Technology and Business UniversityYantaiChina School of Information and Electronic Engineering Shandong Technology and Business UniversityYantaiChina Shandong Provincial Key Laboratory of Software Engineering Shandong UniversityJinanChina

In a group of images,the recurrent foreground objects are considered as the key objects in the group of *** co-saliency detection,these are described as common saliency *** aim is to be able to naturally guide the user's gaze to these common salient *** guiding the user's gaze,users can easily find these common saliency objects without interference from other ***,a method is proposed for reducing user visual attention based on co-saliency *** the co-saliency detection algorithm and matting algorithm for image preprocessing,the exact position of non-common saliency objects(called Region of Interest here,***)in the image group can be *** the attention retargeting algorithm,the internal features of the image to adjust the saliency of the ROI areas are *** the HSI colour space,the three components H,S,and I are adjusted ***,the hue distribution is constructed by the Dirac kernel function,and then the most similar hue distribution to the sur-rounding environment is selected as the best hue distribution of ROI *** S and I components can be set as the contrast difference between ROI areas and surrounding background areas according to the user's *** results show that this method effectively reduces the ROI areas'attraction to the user's visual ***,comparing this method with other methods,the saliency adjustment effect achieved is much better,and the processed image is more natural.

关键词： image algorithm distribution

来源：评论

学校读者我要写书评

暂无评论

Robust Generalization Against Photon-Limited Corruptions via Worst-Case Sharpness Minimization

Robust Generalization Against Photon-Limited Corruptions via...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Zhuo Huang Miaoxi Zhu Xiaobo Xia Li Shen Jun Yu Chen Gong Bo Han Bo Du Tongliang Liu Sydney AI Centre The University of Sydney National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University JD Explore Academy Department of Automation University of Science and Technology of China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Department of Computer Science Hong Kong Baptist University

Robust generalization aims to tackle the most challenging data distributions which are rare in the training set and contain severe noises, i.e., photon-limited corruptions. Common solutions such as distributionally robust optimization (DRO) focus on the worst-case empirical risk to ensure low training error on the uncommon noisy distributions. However, due to the over-parameterized model being optimized on scarce worst-case data, DRO fails to produce a smooth loss landscape, thus struggling on generalizing well to the test set. Therefore, instead of focusing on the worst-case risk minimization, we propose SharpDRO by penalizing the sharpness of the worst-case distribution, which measures the loss changes around the neighbor of learning parameters. Through worst-case sharpness minimization, the proposed method successfully produces a flat loss curve on the corrupted distributions, thus achieving robust generalization. Moreover, by considering whether the distribution annotation is available, we apply SharpDRO to two problem settings and design a worst-case selection process for robust generalization. Theoretically, we show that SharpDRO has a great convergence guarantee. Experimentally, we simulate photon-limited corruptions using CIFAR10/100 and ImageNet30 datasets and show that SharpDRO exhibits a strong generalization ability against severe corruptions and exceeds well-known baseline methods with large performance gains.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Superconducting Quantum Chip Architecture Design Method for Quantum Programs

A Superconducting Quantum Chip Architecture Design Method fo...

引用

computer Technology and Information science (ISCTIS), International Symposium on

作者： Chen Liang Zhenyu Li Mengfan Zhang Lin Han School of Cyber Science and Engineering Zhengzhou Universityne Zhengzhou China School of Computer and Artificial Intelligence Zhengzhou University Zhengzhou China National Supercomputing Center in Zhengzhou Zhengzhou University Zhengzhou China

In the field of superconducting quantum computing, chip architecture design is an important research direction. Currently, most chips are designed for general-purpose architectures, and the fixed connection structure is difficult to ensure the flexibility of mapping, adding extra gate operations and affecting the execution efficiency of different quantum programs. To this end, this paper proposes a superconducting quantum chip architecture design method for quantum programs. The method aims at reducing the number of gates after mapping, and generates a chip architecture with higher fitness by combining the two-qubit gate information of quantum programs through an improved genetic algorithm. The experimental results show that the chip architecture generated by this method outperforms two 2 * 8 scale square lattice generic architectures in 33 test samples, with an average reduction of 35.3 % and 17.9 % in the total number of gates optimized, respectively, which verifies the effectiveness of this method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Heart Failure: Machine Learning Prediction Within a 5-Year Framework 24

Heart Failure: Machine Learning Prediction Within a 5-Year F...

引用

24th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2024

作者： Tsarapatsani, Konstantina-Helen Tsakanikas, Vasilios D. Sakellarios, Antonis Trampisch, Hans J. Karapintzou, Efterpi Rudolf, Henrik Matsopoulos, George K. Fotiadis, Dimitrios I. Biomedical Research Institute Foundation for Research and Technology-Hellas Ioannina Greece Ruhr University Bochum Department of Medical Informatics Biometry and Epidemiology Bochum Germany University of Ioannina Unit of Medical Technology and Intelligent Information Systems Dept. of Materials Science and Engineering Greece Institute for Biostatistics and Informatics in Medicine and Ageing Research University Medical Center Rostock Germany School of Electrical and Computer Engineering National Technical University of Athens Athens Greece University of Ioannina and Biomedical Research Institute-FORTH Unit of Medical Technology and Intelligent Information Systems Dept. of Materials Science and Engineering Ioannina Greece

ISBN: (纸本)9798331518622

Heart failure (HF) is a complex syndrome that is affected by many factors and causes. It is crucial to early recognize the disease subtypes and the unidentified clinical pathways that give rise to it. Machine learning (ML) is the tool that assist to deal with these challenges and improve the prediction of HF. In this work, the HF risk prediction was implemented by employed ML classifiers, such as Random Forest (RF), Extreme Grading Boosting (XGBoost) and Light Gradient-Boosting Machine (LGBM). We utilized the data from the German epidemiological trial on ankle brachial index - getABI cohort, which includes 6,454 patients. The performance of classifiers was estimated by Accuracy (ACC), Sensitivity, Specificity and the area under the receiver operating characteristic curve (AUC) in mean values for each ML classifier. The results were also interpreted using the Explainable artificial intelligence (XAI) approach, the Shapley Additive exPlanations (SHAP) values. Our work reveals that LGBM classifier predict the HF risk within 5 years follow-up in general population with 68 % accuracy. Moreover, the N-terminal pro-B-type natriuretic peptide (NT-proBNP) was identified as the most important feature for HF risk prediction. © 2024 IEEE.

关键词： Risk perception

来源：评论

学校读者我要写书评

暂无评论

NTIRE 2023 Challenge on Light Field Image Super-Resolution: Dataset, Methods and Results

NTIRE 2023 Challenge on Light Field Image Super-Resolution: ...

引用

2023 IEEE/CVF Conference on computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： Wang, Yingqian Wang, Longguang Liang, Zhengyu Yang, Jungang Timofte, Radu Guo, Yulan Jin, Kai Wei, Zeqiang Yang, Angulia Guo, Sha Gao, Mingzhi Zhou, Xiuzhuang Van Duong, Vinh Huu, Thuc Nguyen Yim, Jonghoon Jeon, Byeungwoo Liu, Yutong Cheng, Zhen Xiao, Zeyu Xu, Ruikang Xiong, Zhiwei Liu, Gaosheng Jin, Manchang Yue, Huanjing Yang, Jingyu Gao, Chen Zhang, Shuo Chang, Song Lin, Youfang Chao, Wentao Wang, Xuechun Wang, Guanghui Duan, Fuqing Xia, Wang Wang, Yan Xia, Peiqi Wang, Shunzhou Lu, Yao Cong, Ruixuan Sheng, Hao Yang, Da Chen, Rongshan Wang, Sizhe Cui, Zhenglong Chen, Yilei Lu, Yongjie Cai, Dongjun An, Ping Salem, Ahmed Ibrahem, Hatem Yagoub, Bilel Kang, Hyun-Soo Zeng, Zekai Wu, Heng National University of Defense Technology China Aviation University of Air Force China University of Würzburg Germany Eth Zürich Switzerland Sun Yat-sen University The Shenzhen Campus of Sun Yat-sen University China Bigo Technology Pte. Ltd. Singapore Smart Medical Innovation Lab Beijing University of Posts and Telecommunications China Global Explorer Ltd. Suzhou China National Engineering Research Center of Visual Technology School of Computer Science Peking University China School of Artificial Intelligence Beijing University of Posts and Telecommunications China Department of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of University of Science and Technology of China China School of Electrical and Information Engineering Tianjin University China Beijing Key Lab of Traffic Data Analysis and Mining School of Computer and Information Technology Beijing Jiaotong University China Beijing Normal University China Toronto Metropolitan University Canada Beijing Institute of Technology China Shenzhen MSU-BIT University China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University China Beihang Hangzhou Innovation Institute Yuhang China Faculty of Applied Sciences Macao Polytechnic University China School of Communication and Information Engineering Shanghai University China School of Information and Communication Engineering Chungbuk National University Korea Republic of Guangdong University of Technology China

ISBN: (纸本)9798350302493

In this report, we summarize the first NTIRE challenge on light field (LF) image super-resolution (SR), which aims at super-resolving LF images under the standard bicubic degradation with a magnification factor of 4. This challenge develops a new LF dataset called NTIRE-2023 for validation and test, and provides a toolbox called BasicLFSR to facilitate model development. Compared with single image SR, the major challenge of LF image SR lies in how to exploit complementary angular information from plenty of views with varying disparities. In total, 148 participants have registered the challenge, and 11 teams have successfully submitted results with PSNR scores higher than the baseline method LF-InterNet [1]. These newly developed methods have set new state-of-the-art in LF image SR, e.g., the winning method achieves around 1 dB PSNR improvement over the existing state-of-the-art method DistgSSR [2]. We report the solutions proposed by the participants, and summarize their common trends and useful tricks. We hope this challenge can stimulate future research and inspire new ideas in LF image SR. © 2023 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

EAViT: External Attention Vision Transformer for Audio Classification

arXiv

引用

arXiv 2024年

作者： Iqbal, Aquib Zim, Abid Hasan Tonmoy, Md Asaduzzaman Zhou, Limengnan Malik, Asad Kuribayashi, Minoru Department of Computer Science University of Massachusetts AmherstMA United States Department of Mechanical Engineering Aligarh Muslim University India Department of Electrical Engineering Aligarh Muslim University India School of Electronic and Information Engineering UESTC China School of Information Technology Monash University Malaysia Malaysia Center for Data-driven Science and Artificial Intelligence Tohoku University Japan

This paper presents the External Attention Vision Transformer (EAViT) model, a novel approach designed to enhance audio classification accuracy. As digital audio resources proliferate, the demand for precise and efficient audio classification systems has intensified, driven by the need for improved recommendation systems, and user personalization in various applications, including music streaming platforms and environmental sound recognition. Accurate audio classification is crucial for organizing vast audio libraries into coherent categories, enabling users to find and interact with their preferred audio content more effectively. In this study, we utilize the GTZAN dataset, which comprises 1,000 music excerpts spanning ten diverse genres. Each 30-second audio clip is segmented into 3-second excerpts to enhance dataset robustness and mitigate overfitting risks, allowing for more granular feature analysis. The EAViT model integrates multi-head external attention (MEA) mechanisms into the Vision Transformer (ViT) framework, effectively capturing long-range dependencies and potential correlations between samples. This external attention (EA) mechanism employs learnable memory units that enhance the network’s capacity to process complex audio features efficiently. The study demonstrates that EAViT achieves a remarkable overall accuracy of 93.99%, surpassing state-of-the-art models. © 2024, CC BY.

关键词： Audio streaming

来源：评论

学校读者我要写书评

暂无评论

Improving Complex Reasoning over Knowledge Graph with Logic-Aware Curriculum Tuning 39

Improving Complex Reasoning over Knowledge Graph with Logic-...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Xia, Tianle Ding, Liang Wan, Guojia Zhan, Yibing Du, Bo Tao, Dacheng School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China The University of Sydney Australia JD Explore Academy College of Computing and Data Science Nanyang Technological University 639798 Singapore

ISBN: (纸本)157735897X

Answering complex queries over incomplete knowledge graphs (KGs) is a challenging task. Most previous works have focused on learning entity/relation embeddings and simulating first-order logic operators with various neural networks. However, they are bottlenecked by the inability to share world knowledge to improve logical reasoning, thus resulting in suboptimal performance. In this paper, we propose a complex reasoning schema over KG upon large language models (LLMs), containing a curriculum-based logical-aware instruction tuning framework, named LACT. Specifically, we augment the arbitrary first-order logical queries via binary tree decomposition, to stimulate the reasoning capability of LLMs. To address the difficulty gap among different types of complex queries, we design a simple and flexible logic-aware curriculum learning framework. Experiments across widely used datasets demonstrate that LACT has substantial improvements (brings an average +5.5% MRR score) over advanced methods, achieving the new state-of-the-art. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

Shape-intensity knowledge distillation for robust medical image segmentation

arXiv

引用

arXiv 2024年

作者： Dong, Wenhui Du, Bo Xu, Yongchao National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan430072 China Institute of Artificial Intelligence School of Computer Science Wuhan University Wuhan430072 China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan430072 China Medical Artificial Intelligence Research Institute of Renmin Hospital Wuhan University Wuhan430072 China

Many medical image segmentation methods have achieved impressive results. Yet, most existing methods do not take into account the shape-intensity prior information. This may lead to implausible segmentation results, in particular for images of unseen datasets. In this paper, we propose a novel approach to incorporate joint shape-intensity prior information into the segmentation network. Specifically, we first train a segmentation network (regarded as the teacher network) on class-wise averaged training images to extract valuable shape-intensity information, which is then transferred to a student segmentation network with the same network architecture as the teacher via knowledge distillation. In this way, the student network regarded as the final segmentation model can effectively integrate the shape-intensity prior information, yielding more accurate segmentation results. Despite its simplicity, experiments on five medical image segmentation tasks of different modalities demonstrate that the proposed Shape-Intensity Knowledge Distillation (SIKD) consistently improves several baseline models (including recent MaxStyle and SAMed) under intra-dataset evaluation, and significantly improves the cross-dataset generalization ability. Code is available at https://***/whdong-whu/SIKD. © 2024, CC BY.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Implicit smoothed particle hydrodynamics model for simulating incompressible fluid-elastic coupling

Implicit smoothed particle hydrodynamics model for simulatin...

引用

作者： Wang, Xiaokun Wang, Tiancheng Wang, Jiamin Xu, Yanrui Ban, Xiaojuan Huang, Houbin Zhu, Zhihong Chang, Jian Zhang, Jian Jun School of Intelligence Science and Technology University of Science and Technology Beijing Beijing China Beijing Key Laboratory of Knowledge Engineering for Materials Science University of Science and Technology Beijing Beijing China National Centre for Computer Animation Bournemouth University Poole United Kingdom Beijing Advanced Innovation Center for Materials Genome Engineering University of Science and Technology Beijing Beijing China Key Laboratory of Perception and Control of Intelligent Bionic Unmanned Systems Ministry of Education University of Science and Technology Beijing Beijing China Chinese PLA General Hospital Beijing China Hainan Hospital of Chinese PLA General Hospital Hainan Sanya China

Fluid simulation has been one of the most critical topics in computer graphics for its capacity to produce visually realistic effects. The intricacy of fluid simulation manifests most with interacting dynamic elements. The coupling for such scenarios has always been challenging to manage due to the numerical instability arising from the coupling boundary between different elements. Therefore, we propose an implicit smoothed particle hydrodynamics fluid-elastic coupling approach to reduce the instability issue for fluid-fluid, fluid-elastic, and elastic-elastic coupling circumstances. By deriving the relationship between the universal pressure field with the incompressible attribute of the fluid, we apply the number density scheme to solve the pressure Poisson equation for both fluid and elastic material to avoid the density error for multi-material coupling and conserve the non-penetration condition for elastic objects interacting with fluid particles. Experiments show that our method can effectively handle the multiphase fluids simulation with elastic objects under various physical properties. © 2023 The Authors. computer Animation and Virtual Worlds published by John Wiley & Sons Ltd.

关键词： Poisson equation

来源：评论

学校读者我要写书评

暂无评论

Decision Tree Based Early Termination Algorithm for Affine Prediction in AVS3

Decision Tree Based Early Termination Algorithm for Affine P...

引用

IEEE Workshop on Multimedia Signal Processing

作者： Jiacheng Wu Songlin Sun Jiaqi Zhang Xu Han School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China National Engineering Research Center of Visual Technology School of Computer Science Peking University Beijing China School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China

The third generation of Audio Video Standard(AVS3) has adopted affine prediction(including affine merge mode and affine inter mode), which can characterize non-translational motions such as rotation, zooming, and shearing. Though affine prediction leads to BD-Rate saving, it also results in substantial computational complexity. In this paper, we propose a fast algorithm to address this problem. Some useful features are introduced and used to train five decision tree classifiers to skip unnecessary calculations in affine prediction. Experimental results show that compared to HPM 14.0, the proposed algorithm reduces 19% affine merge time, 18% affine inter time, and 6% encoding time, with negligible coding performance loss under random access(RA) configurations.

关键词：

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：