检索结果-内蒙古大学图书馆

Proceedings of the 41st International Conference on Machine Learning

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

关键词：

来源：评论

学校读者我要写书评

暂无评论

StylizedGS: Controllab.e Stylization for 3D Gaussian Splatting

arXiv

引用

arXiv 2024年

作者： Zhang, Dingxi Chen, Zhuoxun Yuan, Yu-Jie Zhang, Fang-Lue He, Zhenliang Shan, Shiguang Gao, Lin The University of Chinese Academy of Sciences Beijing China The Beijing Key Laboratory of Mobile Computing and Pervasive Device Institute of Computing Technology Chinese Academy of Sciences Beijing China Victoria University of Wellington New Zealand The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

With the rapid development of XR, 3D generation and editing are becoming more and more important, among which, stylization is an important tool of 3D appearance editing. It can achieve consistent 3D artistic stylization given a single reference style image and thus is a user-friendly editing way. However, recent NeRF-based 3D stylization methods face efficiency issues that affect the actual user experience and the implicit nature limits its ability to transfer the geometric pattern styles. Additionally, the ability for artists to exert flexible control over stylized scenes is considered highly desirable, fostering an environment conducive to creative exploration. In this paper, we introduce StylizedGS, a 3D neural style transfer framework with adaptable control over perceptual factors based on 3D Gaussian Splatting (3DGS) representation. The 3DGS brings the benefits of high efficiency. We propose a GS filter to eliminate floaters in the reconstruction which affects the stylization effects before stylization. Then the nearest neighbor-based style loss is introduced to achieve stylization by fine-tuning the geometry and color parameters of 3DGS, while a depth preservation loss with other regularizations is proposed to prevent the tampering of geometry content. Moreover, facilitated by specially designed losses, StylizedGS enables users to control color, stylized scale and regions during the stylization to possess customized capabilities. Our method can attain high-quality stylization results characterized by faithful brushstrokes and geometric consistency with flexible controls. Extensive experiments across various scenes and styles demonstrate the effectiveness and efficiency of our method concerning both stylization quality and inference FPS. Copyright © 2024, The Authors. All rights reserved.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Understanding News Creation Intents: Frame, Dataset, and Method

arXiv

引用

arXiv 2023年

作者： Wang, Zhengjia Wang, Danding Sheng, Qiang Cao, Juan Su, Silong Sun, Yifan Hu, Beizhe Ma, Siyuan Key Lab of Intelligent Information Processing Chinese Academy of Sciences Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China University of Macau China

As the disruptive changes in the media economy and the proliferation of alternative news media outlets, news intent has progressively deviated from ethical standards that serve the public interest. News intent refers to the purpose or intention behind the creation of a news article. While the significance of research on news intent has been widely acknowledged, the absence of a systematic news intent understanding framework hinders further exploration of news intent and its downstream applications. To bridge this gap, we propose News INTent (NINT) frame, the first component-aware formalism for understanding the news creation intent based on research in philosophy, psychology, and cognitive science. Within this frame, we define the news intent identification task and provide a benchmark dataset with fine-grained lab.ls along with an efficient benchmark method. Experiments demonstrate that NINT is beneficial in both the intent identification task and downstream tasks that demand a profound understanding of news. This work marks a foundational step towards a more systematic exploration of news creation intents. Copyright © 2023, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automatic Survey Generation Based Onposition Closeness of key Words

SSRN

引用

SSRN 2022年

作者： Sun, Xiaoping Zhuge, Hai Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China Chinese Academy of Sciences China

Survey enables researchers to know a research area quickly. Automatic survey generation is a challenge to text summarization research because a survey consists of many sections, each of which is composed by the sentences selected from the papers most relevant to its titles. The key is to rank papers, determine top-k papers and select sentences from the top-k papers according to section title. This paper proposes a measure called key word position closeness to rank papers by measuring how closely two neighboring key words of a section title are distributed within a paper. The basic rationale is that the positions of the neighboring key words of a section title should be closer in more relevant papers to be surveyed. To select the top-k papers for each section, an unsupervised method is proposed to predict the top-k value based on the shape of the curve of the sorted ranking scores. Based on the duality property of the closeness, sentence ranking scores of a selected paper with respect to the key words of section title can be directly obtained when the paper ranking score is computed using the closeness, both the importance and coherence of selected sentences can be reflected without extra sentence ranking calculation. Experiments and manual evaluation show that the proposed methods achieve significant improvements compared with term frequency-based approaches to generating scientific survey. © 2022, The Authors. All rights reserved.

关键词： Text processing

来源：评论

学校读者我要写书评

暂无评论

Improving Molecular Graph Generation with Flow Matching and Optimal Transport

arXiv

引用

arXiv 2024年

作者： Hou, Xiaoyang Zhu, Tian Ren, Milong Bu, Dongbo Gao, Xin Zhang, Chunming Sun, Shiwei Key Laboratory of Intelligent Information Processing Institute of Computing Technology School of Computer Science and Technology University of Chinese Academy of Sciences China Central China Research Institute for Artificial Intelligence Technologies China Western Institute of Computing Technology Phil Rivers Technology King Abdullah University of Science and Technology Saudi Arabia

Generating molecular graphs is crucial in drug design and discovery but remains challenging due to the complex interdependencies between nodes and edges. While diffusion models have demonstrated their potentiality in molecular graph design, they often suffer from unstable training and inefficient sampling. To enhance generation performance and training stability, we propose GGFlow, a discrete flow matching generative model incorporating optimal transport for molecular graphs and it incorporates an edge-augmented graph transformer to enable the direct communications among chemical bounds. Additionally, GGFlow introduces a novel goal-guided generation framework to control the generative trajectory of our model, aiming to design novel molecular structures with the desired properties. GGFlow demonstrates superior performance on both unconditional and conditional molecule generation tasks, outperforming existing baselines and underscoring its effectiveness and potential for wider application. © 2024, CC BY.

关键词： Molecular docking

来源：评论

学校读者我要写书评

暂无评论

Light-wave manipulation of subwavelength metallic gratings by electrically controlling the surface charge distribution based on surface-plasmon excitation

引用

Physical Review Applied 2024年第3期21卷 034062-034062页

作者： Chai Hu Taige Liu Kewei Liu Zhe Wang Mao Ye Jiashuo Shi Xinyu Zhang National Key Lab of Multispectral Information Intelligent Processing Technology Huazhong University of Science and Technology Wuhan 430074 China School of Automation & Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China Innovation Institute Huazhong University of Science and Technology Wuhan 430074 China

This paper proposes a light-wave polarization response model based on a kind of subwavelength metallic grating (SMG) by controlling the rearrangement of surface free electrons and net positive charges. The action of charging interdigital SMGs to form a capacitor-shaped architecture can be used to modulate the surface charge distribution, leading to a decrease in the transmission of the incident light waves with initial polarization orientations parallel to the long axis of the grating (parallel waves or P waves) and an increase in the transmission of the incident light waves with initial polarization orientations perpendicular to the long axis of the grating (vertical waves or S waves), thus contributing to the modulation of the polarization state of the SMGs. By using serrated-shaped sidewalls for each nanostrip in the SMGs, the surface net charges can be more efficiently pumped onto the nearest apex in a linear nanotip array to clearly enhance or suppress the penetration of P waves or S waves in a wide wavelength range of approximately 200 to 2500 nm. The developed graphene-covered SMG metasurface further demonstrates a typical feature: the transmittivity of the P wave is maximally increased by 10.24% and that of the S waves is maximally decreased by 21.84% when a low dc voltage is applied because of the controlled conductive action of the graphene film formed by sequentially stacking 30 layers of single-crystal graphene over the surface of the serrated SMGs. The above behavioral attributes provide an alternative way of realizing the adjustability and controllab.lity of the polarization response characteristics of the incident light wave and performing the fast and fine acquisition of polarization information in polarization imaging.

关键词： Electric dipole-dipole interactions Fano resonance Plasmonics Polarization of light Surface plasmons Interfaces Metamaterials Nanowires

来源：评论

学校读者我要写书评

暂无评论

A Cross-direction Task Decoupling Network for Small Logo Detection

A Cross-direction Task Decoupling Network for Small Logo Det...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Sujuan Hou Xingzhuo Li Weiqing Min Jiacheng Li Jing Wang Yuanjie Zheng Shuqiang Jiang School of Information Science and Engineering Shandong Normal University Jinan China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

Logo detection plays an integral role in many applications. However, handling small logos is still difficult since they occupy too few pixels in the image, which burdens the extraction of discriminative features. The aggregation of small logos also brings a great challenge to the classification and localization of logos. To solve these problems, we creatively propose Cross-direction Task Decoupling Network (CTDNet) for small logo detection. We first introduce Cross-direction Feature Pyramid (CFP) to realize cross-direction feature fusion by adopting horizontal transmission and vertical transmission. In addition, Multi-frequency Task Decoupling Head (MTDH) decouples the classification and localization tasks into two branches. A multi-frequency attention convolution branch is designed to achieve more accurate regression by combining discrete cosine transform and convolution creatively. Comprehensive experiments on four logo datasets demonstrate the effectiveness and efficiency of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Cross-direction Task Decoupling Network for Small Logo Detection

arXiv

引用

arXiv 2023年

作者： Hou, Sujuan Li, Xingzhuo Min, Weiqing Li, Jiacheng Wang, Jing Zheng, Yuanjie Jiang, Shuqiang School of Information Science and Engineering Shandong Normal University Jinan China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Redundant Data Detection and Deletion to Meet Privacy Protection Requirements in Blockchain-Based Edge computing Environment

引用

China Communications 2024年第3期21卷 149-159页

作者： Zhang Lejun Peng Minghui Su Shen Wang Weizheng Jin Zilong Su Yansen Chen Huiling Guo Ran Sergey Gataullin Cyberspace Institute Advanced Technology Guangzhou UniversityGuangzhou 510006China College of Information Engineering Yangzhou UniversityYangzhou 225127China School Math&Computer Science Quanzhou Normal UniversityQuanzhou 362000China Computer Science Department City University of Hong KongHong Kong 999077China School of Computer and Software Nanjing University of Information Science and TechnologyNanjing 21004China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and TechnologyAnhui UniversityHefei 230601China Department of Computer Science and Artificial Intelligence Wenzhou UniversityWenzhou 325035China Guangzhou University Library Guangzhou UniversityGuangzhou 510006China Central Economic and Mathematics Institute Russian Academy of Sciences MIREA-Russian Technological University Moscow RegionRussia

With the rapid development of information technology,IoT devices play a huge role in physiological health data *** exponential growth of medical data requires us to reasonably allocate storage space for cloud servers and edge *** storage capacity of edge nodes close to users is *** should store hotspot data in edge nodes as much as possible,so as to ensure response timeliness and access hit rate;However,the current scheme cannot guarantee that every sub-message in a complete data stored by the edge node meets the requirements of hot data;How to complete the detection and deletion of redundant data in edge nodes under the premise of protecting user privacy and data dynamic integrity has become a challenging *** paper proposes a redundant data detection method that meets the privacy protection *** scanning the cipher text,it is determined whether each sub-message of the data in the edge node meets the requirements of the hot *** has the same effect as zero-knowledge proof,and it will not reveal the privacy of *** addition,for redundant sub-data that does not meet the requirements of hot data,our paper proposes a redundant data deletion scheme that meets the dynamic integrity of the *** use Content Extraction Signature(CES)to generate the remaining hot data signature after the redundant data is *** feasibility of the scheme is proved through safety analysis and efficiency analysis.

关键词： blockchain data integrity edge computing privacy protection redundant data

来源：评论

学校读者我要写书评

暂无评论

Real time Monitoring Method of Welding Defects Based on LSTM Sequence Model 3

Real time Monitoring Method of Welding Defects Based on LSTM...

引用

3rd IEEE International Conference on information technology, Big Data and Artificial Intelligence, ICIBA 2023

作者： Zhou, Xundao Chen, Mingmin Shang, Weipeng Shen, Hongping Xu, Huawei Fifth Institute of Electronics Ministry of Industry and Information Technology China Key Lab. of Min. of Technol. Indust. and Info. Technol. of Intelligent Prod. Qual. Eval. and Reliability Assur. China

ISBN: (纸本)9781665490788

During laser welding, abnormal conditions can result in workpiece defects and product failure. Therefore, a real-time monitoring system is required to detect laser welding processes and ensure product quality. In this study, we developed a real-time laser welding data acquisition system to collect plasma density, laser intensity, and molten pool temperature data during the welding process. Additionally, we established a neural network based on a combination of LSTM and CNN models to rapidly detect laser welding defects. The experimental results demonstrate that this method can effectively identify welding defects with an average accuracy rate of 96%. Furthermore, the LSTM layer can significantly improve the prediction performance of the CNN feature extraction model, particularly for forecasting and non-local features such as sequence offsets and delays. © 2023 IEEE.

关键词： Data acquisition

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：