检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Hua, Cong Xu, Qianqian Bao, Shilong Yang, Zhiyong Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores a novel multi-modal alternating learning paradigm pursuing a reconciliation between the exploitation of uni-modal features and the exploration of cross-modal interactions. This is motivated by the fact that current paradigms of multi-modal learning tend to explore multi-modal features simultaneously. The resulting gradient prohibits further exploitation of the features in the weak modality, leading to modality competition, where the dominant modality overpowers the learning process. To address this issue, we study the modality-alternating learning paradigm to achieve reconcilement. Specifically, we propose a new method called ReconBoost to update a fixed modality each time. Herein, the learning objective is dynamically adjusted with a reconcilement regularization against competition with the historical models. By choosing a KL-based reconcilement, we show that the proposed method resembles Friedman's Gradient-Boosting (GB) algorithm, where the updated learner can correct errors made by others and help enhance the overall performance. The major difference with the classic GB is that we only preserve the newest model for each modality to avoid overfitting caused by ensembling strong learners. Furthermore, we propose a memory consolidation scheme and a global rectification scheme to make this strategy more effective. Experiments over six multi-modal benchmarks speak to the efficacy of the method. We release the code at https://***/huacong/ReconBoost. Copyright 2024 by the author(s)

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Real-time Dense 3D Semantic Mapping Using RGB-D Camera

Real-time Dense 3D Semantic Mapping Using RGB-D Camera

引用

第42届中国控制会议

作者： Guanci Yang Xiaoyuan Wang Dongying Zhu Yang Li School of Mechanical Engineering Guizhou University State Key Laboratory of Public Big Data Guizhou University

Focusing on the poor real-time performance of 3D semantic mapping using RGB-D cameras in indoor environments,this paper investigates the Real-time Dense 3D Semantic Mapping(RD3DSM) using RGB-D camera. Firstly, a lightweight semantic point cloud acquisition algorithm based on keyframe is designed, which is used to segment scene images and obtain the semantic point cloud real-timely. Secondly, to address the loss of inter-frame tracking in the semantic mapping process,ORB-SLAM3 system is employed as the underlying architecture of the visual 3D semantic mapping system to provide stable camera pose. Thirdly, an information fusion mechanism of the visual 3D semantic mapping system is designed, and the OctoMap 3D scene reconstruction module is adopted to implement dense 3D map representation with semantic information, and then a visual 3D semantic mapping algorithm based on ORB-SLAM3 is proposed. Finally, the designed RD3DSM system is integrated into a robot platform. The tests were conducted on the TUM dataset and natural indoor scenes. The results show the effectiveness and real-time performance of the RD3DSM system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A molecular probe carrying anti-tropomyosin 4 for early diagnosis of cerebral ischemia/reperfusion injury

引用

Neural Regeneration Research 2023年第6期18卷 1321-1324页

作者： Teng-Fei Yu Kun Wang Lu Yin Wen-Zhe Li Chuan-Ping Li Wei Zhang Jie Tian Wen He Department of Ultrasound Beijing Tiantan HospitalCapital Medical UniversityBeijingChina CAS Key Laboratory of Molecular Imaging Institute of AutomationChinese Academy of SciencesBeijingChina State Key Laboratory of Natural and Biomimetic Drugs School of Pharmaceutical SciencesPeking UniversityBeijingChina Anhui Province Key Laboratory of Functional Coordinated Complexes for Materials Chemistry and Application School of Chemical and Environmental EngineeringAnhui Polytechnic UniversityWuhuAnhui ProvinceChina Beijing Advanced Innovation Center for Big Data-Based Precision Medicine School of Engineering MedicineBeihang UniversityBeijingChina

In vivo imaging of cerebral ischemia/reperfusion injury remains an important *** injected porous Ag/Au@SiO_(2) bimetallic hollow nanoshells carrying anti-tropomyosin 4 as a molecular probe into mice with cerebral ischemia/reperfusion injury and observed microvascular changes in the brain using photoacoustic imaging with *** each measured time point,the total photoacoustic signal was significantly higher on the affected side than on the healthy *** hours after reperfusion,cerebral perfusion on the affected side increased,cerebrovascular injury worsened,and anti-tropomyosin 4 expression ***-four hours after reperfusion and later,perfusion on the affected side declined slowly and stabilized after 1 week;brain injury was also *** and immunohistochemical examinations confirmed the brain injury tissue *** nanoshell molecular probe carrying anti-tropomyosin 4 has potential for use in early diagnosis of cerebral ischemia/reperfusion injury and evaluating its progression.

关键词： cerebral ischemia/reperfusion injury diagnosis dynamic monitoring ischemic stroke middle cerebral artery occlusion molecular probe nanoshells photoacoustic imaging tropomyosin 4 ultrasound

来源：评论

学校读者我要写书评

暂无评论

Joint-Motion Mutual Learning for Pose Estimation in Video 24

Joint-Motion Mutual Learning for Pose Estimation in Video

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Wu, Sifan Chen, Haipeng Yin, Yifang Hu, Sihao Feng, Runyang Jiao, Yingying Yang, Ziqi Liu, Zhenguang College of Computer Science and Technology Jilin University Changchun China A STAR Singapore Singapore Georgia Institute of Technology AtlantaGA United States School of Artificial Intelligence Jilin University Changchun China The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China Institute of Blockchain and Data Security Hangzhou China

ISBN: (纸本)9798400706868

Human pose estimation in videos has long been a compelling yet challenging task within the realm of computer vision. Nevertheless, this task remains difficult because of the complex video scenes, such as video defocus and self-occlusion. Recent methods strive to integrate multi-frame visual features generated by a backbone network for pose estimation. However, they often ignore the useful joint information encoded in the initial heatmap, which is a by-product of the backbone generation. Comparatively, methods that attempt to refine the initial heatmap fail to consider any spatio-temporal motion features. As a result, the performance of existing methods for pose estimation falls short due to the lack of ability to leverage both local joint (heatmap) information and global motion (feature) dynamics. To address this problem, we propose a novel joint-motion mutual learning framework for pose estimation, which effectively concentrates on both local joint dependency and global pixel-level motion dynamics. Specifically, we introduce a context-aware joint learner that adaptively leverages initial heatmaps and motion flow to retrieve robust local joint feature. Given that local joint feature and global motion flow are complementary, we further propose a progressive joint-motion mutual learning that synergistically exchanges information and interactively learns between joint feature and motion flow to improve the capability of the model. More importantly, to capture more diverse joint and motion cues, we theoretically analyze and propose an information orthogonality objective to avoid learning redundant information from multi-cues. Empirical experiments show our method outperforms prior arts on three challenging benchmarks. © 2024 ACM.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

Dynamic Tracking with Fuzzy Rules for Evolutionary Dynamic Constrained Optimization

Dynamic Tracking with Fuzzy Rules for Evolutionary Dynamic C...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Bu, Chenyang Liu, Yuxin Zhang, Lizhong Zhu, Tao Luo, Wenjian School of Computer Science and Information Engineering Hefei University of Technology Ministry of Education Key Laboratory of Knowledge Engineering with Big Data Anhui Hefei230027 China School of Computer Science and Information Engineering University of South China Hunan Hengyang421200 China School of Computer Science and Technology Harbin Institute of Technology Guangdong Shenzhen518000 China

ISBN: (纸本)9798350337020

Nature-inspired population-based stochastic search algorithms (SSA) have demonstrated effectiveness in solving many real-world dynamic optimization problems (DOPs), such as dynamic optimal power flow (DOPF) problems. The basic idea of solving DOPs using SSAs is to 'track the moving optima', rather than solving the changed problems from scratch. Its hidden assumption is that the problems are slightly changed in general, and it is expected that the search process can be accelerated by learning from past search experiences. However, the hidden assumption that the current search process can always benefit from previous search experiences might not be true for certain cases. For example, if the current problem is not similar to any of its previous problems, the historical solutions might not be helpful for the current search. To reduce such negative transfer, the following issues are worthy of study: how to choose which historical problems to learn from, and how to determine the degree of learning from historical problems. To solve the above problems, we propose a dynamic processing framework based on fuzzy rules from the perspective of incorporating human knowledge for optima tracking. The experimental results on the DOPF problems show that the SSA with the proposed optima tracking strategy outperforms other comparative algorithms. We open up the code and data of our algorithm44https://***/DMiC-Lab-HFUT/SMDE-Transfer. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Meta-path Enhanced knowledge Graph Convolutional Network for Recommender Systems 12

Meta-path Enhanced Knowledge Graph Convolutional Network for...

引用

12th IEEE International Conference on big knowledge, ICBK 2021

作者： Wang, Ru Wu, Meng Ji, Shengwei Hefei University of Technology Key Laboratory of Knowledge Engineering With Big Data Ministry of Education School of Computer Science and Information Engineering Hefei China

ISBN: (纸本)9781665438582

knowledge Graph (KG) is a directed heterogeneous information network that contains a large number of entities and relations, which is widely used as effective side information in rec-ommender systems. Moreover, in recommender systems, the Graph Convolutional Network (GCN) model is introduced to mine the relatedness between entities in a KG because of its efficiency in extracting spatial features on topological graphs. The knowledge Graph Convolutional Network (KGCN) model up-dates the embedding of a currently positioned entity by aggregating the information of adjacent entities selected randomly. Never-theless, it has two limititations: 1) the information of neighbors se-lected randomly cannot accurately represent the current entity in the KG;2) the model is hard to converge as graph features (i.e. The spatial relation features and semantic information features of en-tities in the KG) grow. To solve these limitations, in this paper, a meta-path (i.e., a sequence of artificially constructed relationships) is introduced into the selection of neighbors in the KGCN model to enhance the representation of each entity. Furthermore, two construction methods of the meta-path - constructing a meta-path based on the same relation (KGCN-SP) and the characteris-tics of KG (KGCN-MP) -are proposed. The experiments based on three real-world datasets demonstrate that the neighbor selection based on the meta-path is able to collect more accurate infor-mation from a KG and improve the recommendation performance effectively. © 2021 IEEE.

关键词： knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Event-driven Robotic Tactile data Learning Using Temporal Spike Sequence Backpropagation Method

Event-driven Robotic Tactile Data Learning Using Temporal Sp...

引用

2022 Chinese Automation Congress, CAC 2022

作者： Hou, Qing Liu, Tingqing Yang, Jing Ji, Xiaoyang Li, Qinglang Li, Jian Yin, Baofan Guizhou University School of Computer Science and Technology Guiyang China Guizhou University School of Computer Science and Technology Guizhou University State Key Laboratory of Public Big Data Guiyang China Guizhou University State Key Laboratory of Public Big Data Guizhou University School of Mechanical Engineering Guiyang China Guizhou University School of Mechanical Engineering Guiyang China

ISBN: (纸本)9781665465335

Tactile perception is indispensable for intelligent robots to interact intelligently like humans. Therefore, the effective use of deep learning methods to acquire tactile features has become an important focus of tactile perception research. Satisfactory time-driven characteristics and the ability to process spatiotemporal information efficiently of spiking neural networks are advantageous for event-based data. We apply a temporal spike sequence learning backpropagation method that can handle continuous spikes to improve the spike neural network for tactile object recognition based on event-driven data. We prove the effectiveness of the temporal spike sequence error backpropagation method in practical applications to address the problem of losing temporal information of data using approximate derivatives. In practical application, we have proved the validity of the back propagation method of temporal spike sequence error in solving the problem of losing temporal information of data using approximate derivatives © 2022 IEEE.

关键词： Backpropagation

来源：评论

学校读者我要写书评

暂无评论

Remote Sensing Image Semantic Segmentation Based on Fusion of Transformer and Lightweight Deeplabv3+

Remote Sensing Image Semantic Segmentation Based on Fusion o...

引用

International Conference on Guidance, Navigation and Control, ICGNC 2022

作者： Cao, Yuanyang Chen, Jian Xue, Zhentao Zhang, Zichao Hu, Gui College of Engineering China Agricultural University Beijing China Key Laboratory of Spatial-Temporal Big Data Analysis and Application of Natural Resources in Megacities MNR Shanghai China Key Laboratory of Urban Land Resources Monitoring and Simulation Ministry of Natural Resources Shenzhen China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijng China

ISBN: (纸本)9789811966125

Aiming at the problems that the classification of remote sensing image datasets is not balanced so that the accuracy of semantic segmentation is not high and the segmentation effect of scarce samples is poor. Transformer encoder with multihead self-attention mechanism is integrated into Deeplabv3+ network, and the attention mechanism is used to enhance the ability to capture global information, so as to improve the precision requirement of scarce categories in remote sensing semantic segmentation task. The algorithm firstly uniformly crops high-resolution remote sensing images into low-resolution image information for batch training and reducing information loss. Secondly, MobileNetV2, a lightweight backbone feature extraction network, is used to replace Xception network of Deeplabv3+. Finally, Transformer encoder based on multihead self-attention mechanism is connected in series with atrous spatial pyramid pooling (ASPP) of Deeplabv3+ encoder region to increase its segmentation precision by enhancing feature learning of scarce category samples in deep feature information. The experimental result shows that the proposed model called TransDeeplabv3+ gets 67.67% mIoU and 81.86% mPA on GID remote sensing dataset. Compared with Deeplabv3+ model, mIoU and mPA are improved by 9.46% and 8.52% respectively. TransDeeplabv3+ can effectively increase the precision because of the ability of increasing attention to the scarce species samples and solve the problem of the decrease of segmentation accuracy due to unbalanced data categories. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Statistical Text Simplification

引用

IEEE Transactions on knowledge and data engineering 2021年第4期33卷 1802-1806页

作者： Qiang, Jipeng Wu, Xindong Department of Computer Science Yangzhou University Yangzhou Jiangsu225127 China Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Ministry of Education Hefei Anhui10084 China

Most recent approaches for Text Simplification (TS) have drawn on insights from machine translation to learn simplification rewrites from the monolingual parallel corpus of complex and simple sentences, yet their effectiveness strongly relies on large amounts of parallel sentences. However, there has been a serious problem haunting TS for decades, that is, the availability of parallel TS corpora is scarce or not fit for the learning task. In this paper, we will focus on one especially useful and challenging problem of unsupervised TS without a single parallel sentence. To the best of our knowledge, we present the first unsupervised text simplification system based on phrase-based machine translation system, which leverages a careful initialization of phrase tables and language models. On the widely used WikiLarge and WikiSmall benchmarks, our system respectively obtains 39.08 and 25.12 SARI points, even outperforms some supervised baselines. © 1989-2012 IEEE.

关键词： Machine translation

来源：评论

学校读者我要写书评

暂无评论

Extracting Named Entity Using Entity Labeling in Geological Text Using Deep Learning Approach

引用

Journal of Earth Science 2023年第5期34卷 1406-1417页

作者： Qinjun Qiu Miao Tian Zhong Xie Yongjian Tan Kai Ma Qingfang Wang Shengyong Pan Liufeng Tao State Key Laboratory of Geo-Information Engineering and Key Laboratory of Surveying and Mapping Science and Geospatial Information Technology of MNR Chinese Academy of Surveying and MappingBeijing 100036China Key Laboratory of Spatial-Temporal Big Data Analysis and Application of Natural Resources in Megacities MNRShanghai 20063China Key Laboratory of Geological Survey and Evaluation of Ministry of Education China University of GeosciencesWuhan 430074China Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering China Three Gorges UniversityYichang 443002China College of Computer and Information Technology China Three Gorges UniversityYichang 443002China Chengdu Geological Environment Monitoring Station Chengdu 610036China Wuhan Zondy Cyber Science&Technology Co. Ltd.Wuhan 430074China

Artificial intelligence(AI) is the key to mining and enhancing the value of big data, and knowledge graph is one of the important cornerstones of artificial intelligence, which is the core foundation for the integration of statistical and physical representations. Named entity recognition is a fundamental research task for building knowledge graphs, which needs to be supported by a high-quality corpus, and currently there is a lack of high-quality named entity recognition corpus in the field of geology, especially in Chinese. In this paper, based on the conceptual structure of geological ontology and the analysis of the characteristics of geological texts, a classification system of geological named entity types is designed with the guidance and participation of geological experts, a corresponding annotation specification is formulated, an annotation tool is developed, and the first named entity recognition corpus for the geological domain is annotated based on real geological reports. The total number of words annotated was 698 512 and the number of entities was 23 345. The paper also explores the feasibility of a model pre-annotation strategy and presents a statistical analysis of the distribution of technical and term categories across genres and the consistency of corpus annotation. Based on this corpus, a Lite Bidirectional Encoder Representations from Transformers(ALBERT)-Bi-directional Long Short-Term Memory(BiLSTM)-Conditional Random Fields(CRF) and ALBERT-BiLSTM models are selected for experiments, and the results show that the F1-scores of the recognition performance of the two models reach 0.75 and 0.65 respectively, providing a corpus basis and technical support for information extraction in the field of geology.

关键词： ontology geological reports named entity recognition geological corpus construction semi-automated annotation platforms deep learning

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：