检索结果-内蒙古大学图书馆

2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022

作者： Wang, Jiarui Zhang, Richong Chen, Junfan Kim, Jaein Mao, Yongyi SKLSDE Beihang University Beijing China Zhongguancun Laboratory Beijing China School of Electrical Engineering and Computer Science University of Ottawa Canada

Text style transfer is an important task in natural language processing with broad applications. Existing models following the masking and filling scheme suffer two challenges: the word masking procedure may mistakenly remove unexpected words and the selected words in the word filling procedure may lack diversity and semantic consistency. To tackle both challenges, in this study, we propose a style transfer model, with an adversarial masking approach and a styled filling technique (AMSF). Specifically, AMSF first trains a mask predictor by adversarial training without manual configuration. Then two additional losses, i.e. an entropy maximization loss and a consistency regularization loss, are introduced in training the word filling module to guarantee the diversity and semantic consistency of the transferred texts. Experimental results and analysis on two benchmark text style transfer data sets demonstrate the effectiveness of the proposed approaches. © 2022 Association for Computational Linguistics.

关键词： Filling

来源：评论

学校读者我要写书评

暂无评论

APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentation

APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semanti...

引用

Conference on computer vision and Pattern Recognition (CVPR)

作者： Weizhao He Yang Zhang Wei Zhuo Linlin Shen Jiaqi Yang Songhe Deng Liang Sun Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen Institute of Artificial Intelligence and Robotics for Society School of Computer Science University of Nottingham China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Few-shot semantic segmentation (FSS) endeavors to segment unseen classes with only a few labeled samples. Current FSS methods are commonly built on the assumption that their training and application scenarios share similar domains, and their performances degrade significantly while applied to a distinct domain. To this end, we propose to leverage the cutting-edge foundation model, the segment Anything Model (SAM), for generalization enhancement. The SAM however performs unsatisfactorily on domains that are distinct from its training data, which primarily comprise natural scene images, and it does not support automatic segmentation of specific semantics due to its interactive prompting mechanism. In our work, we introduce APSeg, a novel auto-prompt network for cross-domain few-shot semantic segmentation (CD-FSS), which is designed to be auto-prompted for guiding cross-domain segmentation. Specifically, we propose a Dual Prototype Anchor Transformation (DPAT) module that fuses pseudo query prototypes extracted based on cycle-consistency with support prototypes, allowing features to be transformed into a more stable domain-agnostic space. Additionally, a Meta Prompt (MPG) module is introduced to automatically generate prompt embeddings, eliminating the need for manual visual prompts. We build an efficient model which can be applied directly to target domains without fine-tuning. Extensive experiments on four cross-domain datasets show that our model outperforms the state-of-the-art CD-FSS method by 5.24% and 3.10% in average accuracy on 1-shot and 5-shot settings, respectively.

关键词： Training Metalearning Visualization Semantic segmentation Semantics Prototypes Training data

来源：评论

学校读者我要写书评

暂无评论

An Isomerism Learning Model to Solve Time-Varying Problems Through Intelligent Collaboration

引用

IEEE/CAA Journal of Automatica Sinica 2023年第8期10卷 1772-1774页

作者： Zhihao Hao Guancheng Wang Bob Zhang Leyuan Fang Haisheng Li the Department of Computer and Information Science University of MacaoMacao 999078China the School of Data Science the Chinese University of Hong KongShenzhen 518172 Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen 518000 China Industrial Control Systems Cyber Emergency Response Team Beijing 100040China IEEE the College of Electrical and Information Engineering Hunan UniversityChangsha 410082 the Peng Cheng Laboratory Shenzhen 518000China the Beijing Key Laboratory of Big Data Technology for Food Safety Beijing Technology and Business UniversityBeijing 100048 the School of Computer Science and Engineering Beijing Technology and Business UniversityBeijing 100048China

Dear Editor,This letter deals with a solution for time-varying problems using an intelligent computational(IC)algorithm driven by a novel decentralized machine learning approach called isomerism *** order to meet the challenges of the model’s privacy and security brought by traditional centralized learning models,a private permissioned blockchain is utilized to decentralize the model in order to achieve an effective coordination,thereby ensuring the credibility of the overall model without exposing the specific parameters and solution process.

关键词： ism thereby letter

来源：评论

学校读者我要写书评

暂无评论

A Perspective on Rhythmic Gymnastics Performance Analysis Powered by Intelligent Fabric

引用

Advanced Fiber Materials 2023年第1期5卷 1-11页

作者： Dan Zhu Zhenyu Zhang Min Chen Pan Li Yuanzhuo Xiang Jingyu Ouyang Zhiheng Huang Xiaojuan Liu Fuhong Wang Maiping Yang Hongtao Zeng Ping Hong Lei Wei Chong Hou Guangming Tao School of Martial Arts and Performance Capital University of Physical Education and SportsBeijing 100191China Wuhan National Laboratory for Optoelectronics and School of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China State Key Laboratory of Material Processing and Die&Mould Technology School of Materials Science and EngineeringHuazhong University of Science and TechnologyWuhan 430074China School of Sports Medicine and Mealth Chengdu Sport UniversityChengdu 610000China School of Physical Education Chaohu UniversityHefei 238000China School of Physical Education Huazhong University of Science and TechnologyWuhan 430074China Beijing Sport University Beijing 100091China School of Electronic and Electrical Engineering and School of Materials Science and Engineering Nanyang University of TechnologySingapore 639798Singapore School of Optics and Electronic Information Huazhong University of Science and TechnologyWuhan 430074China

Performance analysis is an important tool for gymnasts and coaches to assess the techniques,strengths,and weaknesses of rhythmic gymnasts during *** have an accurate insight about the motion and postures can help the optimization of their performance and offer personalized ***,there are three primary limitations of traditional perfor-mance analysis systems applied in rhythmic gymnastics:(1)Inability to quantify anthropometric data in an imperceptible way,(2)labor-intensive nature of data labeling and analysis,and(3)lack of monitoring of all-round and multi-dimensional perspectives of the ***,an advanced performance analysis system for rhythmic gymnastics is proposed in this paper,powered by intelligent *** system uses intelligent fabric to detect the physiological and anthropometric data of the *** a variety of data are collected,the analysis component is implemented by artificial intelligence techniques resulting in behavior recognition,decision-making,and other functions assisting performance improvement.A feasible solution to implementing the analysis component is the use of the hyperdimensional computing *** addition,four typical applications are presented to improve training *** by intelligent fabric,the proposed advanced performance analysis system exhibits the potential to promote innovative technologies for improving training and competi-tive performance,prolonging athletic careers,as well as reducing sports injuries.

关键词： Rhythmic gymnastics Intelligent fabric Augmented reality Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Parameter-free Automatically Prompting: A Latent Pseudo Label Mapping Model for Prompt-based Learning

Parameter-free Automatically Prompting: A Latent Pseudo Labe...

引用

2022 Findings of the Association for Computational Linguistics: EMNLP 2022

作者： Qi, Jirui Zhang, Richong Chen, Junfan Kim, Jaein Mao, Yongyi SKLSDE Beihang University Beijing China Zhongguancun Laboratory Beijing China School of Electrical Engineering and Computer Science University of Ottawa Canada

Prompt-based learning has achieved excellent performance in few-shot learning by mapping the outputs of the pre-trained language model to the labels with the help of a label mapping component. Existing manual label mapping (MLM) methods achieve good results but heavily rely on expensive human knowledge. Automatic label mapping (ALM) methods that learn the mapping functions with extra parameters have shown their potentiality. However, no effective ALM model comparable to MLM methods is developed yet due to the limited data. In this paper, we propose a Latent Pseudo Label Mapping (LPLM) method that optimizes the label mapping without human knowledge and extra parameters. LPLM is built upon a probabilistic latent model and is iteratively self-improved with the EM-style algorithm. The empirical results demonstrate that our LPLM method is superior to the mainstream ALM methods and significantly outperforms the SOTA method in few-shot classification tasks. Moreover, LPLM also shows impressively better performance than the vanilla MLM method which requires extra task-specific prior knowledge. © 2022 Association for Computational Linguistics.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Deep Multi-Instance Learning with Adaptive Recurrent Pooling for Medical Image Classification

Deep Multi-Instance Learning with Adaptive Recurrent Pooling...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Ding, Yi Zhao, Lu Yuan, Liming Wen, Xianbin School of Computer Science and Engineering Tianjin University of Technology Tianjin300384 China School of Computer and Information Engineering Tianjin Chengjian University Tianjin300384 China Key Laboratory of Computer Vision and System Ministry of Education Tianjin300384 China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin300384 China

ISBN: (纸本)9781665468190

Recently, deep multi-instance neural networks have been successfully applied for medical image classification, where only image-level labels rather than fine-grained patch-level labels are available for use. One key issue for these multi-instance neural networks is how to aggregate all patch (instance) features into an entire image (bag) representation, referred to as multi-instance pooling, e.g., max, mean, and attention based pooling. Nevertheless, these multi-instance pooling operations do not take the structural information within an image into account. This is obviously inappropriate for medical image classification since there often exist certain dependencies among regional patches/lesions. We propose an adaptive recurrent pooling based deep multi-instance neural network in this paper. In this network, we first extract multi-view global structural features from every bag using the self-attention mechanism, and then aggregate these multi-view features into a whole bag representation based on the adaptive recurrent pooling operation in order to further capture the contextual information within the bag. Moreover, we introduce the cross-normalization operation used in the Unit Force Operated vision Transformer into the self-attention module to reduce its computational complexity. We have experimentally evaluated the performance of the proposed network on three medical image datasets, namely UCSB breast, Messidor, and Colon cancer. The results demonstrate the advantage of our network over current state-of-the-art deep multi-instance networks in terms of classification accuracy and interpretability. © 2022 IEEE.

关键词： Aggregates

来源：评论

学校读者我要写书评

暂无评论

Free-form acoustic topological waveguides enabled by topological lattice defects

引用

Physical Review B 2024年第18期109卷 L180101-L180101页

作者： Yin Wang Yong Ge Yu-Jing Lu Shuai Gu Yi-Jun Guan Qiao-Rui Si Shou-Qi Yuan Qiang Wang Hong-Xiang Sun Haoran Xue Research Center of Fluid Machinery Engineering and Technology School of Physics and Electrical Engineering School of Computer Science and Communication Engineering School of Physics Collaborative Innovation Center of Advanced Microstructures State Key Laboratory of Acoustics Department of Physics The

The emerging field of topological acoustics provides exciting possibilities for controlling sound propagation with extraordinary robustness. Conventional topological acoustic waveguides built from topological edge states, which arise solely from the nontrivial topology in the momentum space, usually have restricted shapes due to their crystalline structures. Here, we show that, using an acoustic topological system with both nontrivial topologies in the real and momentum spaces, free-form acoustic topological waveguides can be constructed. These topological waveguides support disclination-localized states, caused by the interplay between topological lattice defects and the valley-Hall topology. As demonstrated in our simulations and experiments, such disclination waveguides can take arbitrary shapes and form open arcs within the lattice, which are not possible for previous crystalline acoustic topological waveguides. Furthermore, by increasing the number of topological lattice defects, we can realize more than one topological waveguide in one lattice. They join at the topological lattice defect and form a topological waveguide network, enabling more complicated functionalities such as beam splitting. Our results point to a promising direction for free-form acoustic topological devices with the advantages of embedded forms, easy cascading, and high robustness.

关键词： Acoustics Defects Topological phase transition Topological phases of matter

来源：评论

学校读者我要写书评

暂无评论

Generalization-Enhanced Few-Shot Object Detection in Remote Sensing

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年第6期35卷 5445-5460页

作者： Lin, Hui Li, Nan Yao, Pengjuan Dong, Kexin Guo, Yuhan Hong, Danfeng Zhang, Ying Wen, Congcong China Academy of Electronics and Information Technology Beijing100846 China China Meteorological Administration National Satellite Meteorological Center Innovation Center for FengYun Meteorological Satellite Beijing100081 China Tsinghua University State Key Laboratory of Hydroscience and Engineering Department of Hydraulic Engineering Beijing100084 China Chinese Academy of Sciences Aerospace Information Research Institute Beijing100094 China University of Chinese Academy of Sciences School of Electronic Electrical and Communication Engineering Beijing100049 China University of Science and Technology Beijing School of Automation and Electrical Engineering Beijing100083 China New York University Abu Dhabi Department of Electrical and Computer Engineering Abu Dhabi United Arab Emirates University of Science and Technology of China Anhui China

Object detection is a fundamental task in computer vision that involves accurately locating and classifying objects within images or video frames. In remote sensing, this task is particularly challenging due to the high resolution, multi-scale features, and diverse ground object characteristics inherent in satellite and UAV imagery. These challenges necessitate more advanced approaches for effective object detection in such environments. While deep learning methods have achieved remarkable success in remote sensing object detection, they typically rely on large amounts of labeled data. Acquiring sufficient labeled data, particularly for novel or rare objects, is both challenging and time-consuming in remote sensing scenarios, limiting the generalization capabilities of existing models. To address these challenges, few-shot learning (FSL) has emerged as a promising approach, aiming to enable models to learn new classes from limited labeled examples. Building on this concept, few-shot object detection (FSOD) specifically targets object detection challenges in data-limited conditions. However, the generalization capability of FSOD models, particularly in remote sensing, is often constrained by the complex and diverse characteristics of the objects present in such environments. In this paper, we propose the Generalization-Enhanced Few-Shot Object Detection (GE-FSOD) model to improve the generalization capability in remote sensing FSOD tasks. Our model introduces three key innovations: the Cross-Level Fusion Pyramid Attention Network (CFPAN) for enhanced multi-scale feature representation, the Multi-Stage Refinement Region Proposal Network (MRRPN) for more accurate region proposals, and the Generalized Classification Loss (GCL) for improved classification performance in few-shot scenarios. GE-FSOD demonstrates superior robustness and accuracy in remote sensing FSOD tasks through these enhancements. Extensive experiments on the DIOR and NWPU VHR-10 datasets show that our

关键词： Labeled data

来源：评论

学校读者我要写书评

暂无评论

Deep Learning and Network Analysis:Classifying and Visualizing Geologic Hazard Reports

引用

Journal of Earth science 2024年第4期35卷 1289-1303页

作者： Wenjia Li Liang Wu Xinde Xu Zhong Xie Qinjun Qiu Hao Liu Zhen Huang Jianguo Chen School of Geography and Information Engineering China University of GeosciencesWuhan430078China Key Laboratory of Geological Survey and Evaluation of Ministry of Education China University of GeosciencesWuhan430078China School of Computer Science China University of GeosciencesWuhan430078China Key Laboratory of Urban Land Resources Monitoring and Simulation Ministry of Natural ResourcesShenzhen518034China Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering China Three Gorges UniversityYichang443002China Wuhan Geomatics Institute Wuhan430074China Faculty of Earth Resources China University of GeosciencesWuhan430074China

If progress is to be made toward improving geohazard management and emergency decision-making,then lessons need to be learned from past geohazard information.A geologic hazard report provides a useful and reliable source of information about the occurrence of an event,along with detailed information about the condition or factors of the *** such reports,however,can be a challenging process because these texts are often presented in unstructured long text formats,and contain rich specialized and detailed *** text classification is commonly used to mine disaster text data in open domains(e.g.,news and microblogs).But it has limitations to performing contextual long-distance dependencies and is insensitive to discourse *** deficiencies are most obviously exposed in long text ***,this paper uses the bidirectional encoder representations from Transformers(BERT),to model long ***,utilizing a softmax layer to automatically extract text features and classify geohazards without manual *** latent Dirichlet allocation(LDA)model is used to examine the interdependencies that exist between causal variables to visualize *** proposed method is useful in enabling the machine-assisted interpretation of text-based ***,it can help users visualize causes,processes,and other geohazards and assist decision-makers in emergency responses.

关键词： geologic hazard network analysis latent dirichlet allocation text classification deep learning

来源：评论

学校读者我要写书评

暂无评论

Harnessing Light Field Angular Cues and Spatial Geometries for Semantic Segmentation

Harnessing Light Field Angular Cues and Spatial Geometries f...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Chen Jia Fan Shi Xu Cheng School of Computer Science and Engineering The Engineering Research Center of Learning-Based Intelligent System (Ministry of Education) The Key Laboratory of Computer Vision and System (Ministry of Education) Tianjin University of Technology Tianjin China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

4D light field imaging captures rich spatial-angular information, providing essential geometric cues for semantic segmentation tasks. In this paper, we introduce a novel backbone network called the Light Field Extraction Interaction Network (LFEI-Net). LFEI-Net excels in extracting global structures and multi-scale spatial-angular features, capturing feature dependencies through channel modeling and diverse feature interactions. Unlike traditional methods that depend on pyramid and dilated feature extraction, LFEI-Net pioneers an efficient method by integrating large-scale horizontal depth-wise convolution (HDWC) and vertical depth-wise convolution (VDWC) with interactive operations for comprehensive spatial multi-scale feature extraction. Furthermore, we present the Multi-Angular Modeling (MAM) module, which effectively captures scene angle variations from multiple perspectives and precisely delineates object boundaries, thereby improving model adaptability. Our experimental evaluations on two datasets demonstrate that LFEI-Net significantly outperforms state-ofthe-art (SOTA) 2D and 4D light field semantic segmentation methods, achieving mean Intersection over Union (mIoU) of 83.72% and 86.88%, respectively.

关键词： Geometry Adaptation models Convolution Semantic segmentation Imaging Feature extraction Light fields Acoustics Speech processing

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：