检索结果-内蒙古大学图书馆

Promoting Students' Programming Skills in Constructions for Teaching Materials and Curriculums:Experiments for Comprehensive Application of Programming Methods

Promoting Students' Programming Skills in Constructions for ...

引用

作者： Yonghui Wu Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University

The goal for experiments for programming languages is to polish students' programming skills solving problems by programming *** contests are contests solving problems by programming.A programming language experiment based on "solving problems by programming" consists of the related knowledge background for programming languages and methods,programming contest problems and their analysis and *** paper specifies experiments for programming languages based on "solving problems by programming":the comprehensive application of programming *** experiments enlighten students to solve a problem by programming through comprehensively applying programming methods:offline method,binary search,and real precision processing.

关键词： Programming Language Programming Contest Problem Offline Binary Search Real Precision processing

来源：评论

学校读者我要写书评

暂无评论

Multi-contrast High Quality MR Image Super-Resolution with Dual Domain Knowledge Fusion

Multi-contrast High Quality MR Image Super-Resolution with D...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Wang, Runhan Zhao, Ruiwei Fu, Weijia Zhang, Xiaobo Zhang, Yuejie Feng, Rui Fudan University School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Shanghai200433 China Fudan University Academy for Engineering and Technology Shanghai China Children's Hospital of Fudan University National Children's Medical Center Shanghai China

ISBN: (纸本)9781665468190

Multi-contrast high quality high-resolution (HR) Magnetic Resonance (MR) images enrich available information for diagnosis and analysis. Deep convolutional neural network methods have shown promising ability for MR image super-resolution (SR) given low-resolution (LR) MR images. Methods taking HR images as references (Ref) have made progress to enhance the effect of MR images SR. However, existing multi-contrast MR image SR approaches are based on contrasting-expanding backbones, which lose high frequency information of Ref image during downsampling. They also failed to transfer textures of Ref image into target domain. In this paper, we propose Edge Mask Transformer UNet (EMFU) for accelerating MR images SR. We propose Edge Mask Transformer (EMF) to generate global details and texture representation of target domain. Dual domain fusion module in UNet aggregates semantic information of the representation and LR image of target domain. Specifically, we extract and encode edge masks to guide the attention in EMF by re-distributing the embedding tensors, so that the network allocates more attention to image edge area. We also design a dual domain fusion module with self-attention and cross-attention to deeply fuse semantic information of multiple protocols for MRI. Extensive experiments show the effectiveness of our proposed EMFU, which surpasses state-of-the-art methods on benchmarks quantitatively and visually. Codes will be released to the community. © 2022 IEEE.

关键词： Magnetic resonance

来源：评论

学校读者我要写书评

暂无评论

GLaPE: Gold label-agnostic Prompt Evaluation for Large Language Models

GLaPE: Gold Label-agnostic Prompt Evaluation for Large Langu...

引用

2024 Conference on Empirical Methods in Natural Language processing, EMNLP 2024

作者： Zhang, Xuanchang Zhang, Zhuosheng Zhao, Hai College of Zhiyuan Shanghai Jiao Tong University China School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University China Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 China

ISBN: (纸本)9798891761643

Despite the rapid progress of large language models (LLMs), their task performance remains sensitive to prompt design. Recent studies have explored leveraging the LLM itself as an optimizer to identify optimal prompts that maximize task accuracy. However, when evaluating prompts, such approaches heavily rely on elusive manually annotated gold labels to calculate task accuracy for each candidate prompt, which hinders its generality. To overcome the limitation, this work proposes GLaPE, a gold label-agnostic prompt evaluation method to alleviate dependence on gold labels. GLaPE is composed of two critical aspects: self-consistency evaluation of a single prompt and mutual-consistency refinement across multiple prompts. Experimental results on 8 widely-recognized reasoning tasks demonstrate that GLaPE can produce more effective prompts, achieving performance comparable to those derived from manually annotated gold labels. Analysis shows that GLaPE provides reliable evaluations aligned with accuracy, even in the absence of gold labels. Code is publicly available at https://***/thunderous77/GLaPE. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

GenRec: unifying video generation and recognition with diffusion models 24

GenRec: unifying video generation and recognition with diffu...

引用

Proceedings of the 38th International Conference on Neural information processing Systems

作者： Zejia Weng Xitong Yang Zhen Xing Zuxuan Wu Yu-Gang Jiang Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University and Shanghai Collaborative Innovation Center of Intelligent Visual Computing Department of Computer Science University of Maryland

ISBN: (纸本)9798331314385

Video diffusion models are able to generate high-quality videos by learning strong spatial-temporal priors on large-scale datasets. In this paper, we aim to investigate whether such priors derived from a generative process are suitable for video recognition, and eventually joint optimization of generation and recognition. Building upon Stable Video Diffusion, we introduce GenRec, the first unified framework trained with a random-frame conditioning process so as to learn generalized spatial-temporal representations. The resulting framework can naturally supports generation and recognition, and more importantly is robust even when visual inputs contain limited information. Extensive experiments demonstrate the efficacy of GenRec for both recognition and generation. In particular, GenRec achieves competitive recognition performance, offering 75.8% and 87.2% accuracy on SSV2 and K400, respectively. GenRec also performs the best on class-conditioned image-to-video generation, achieving 46.5 and 49.3 FVD scores on SSV2 and EK-100 datasets. Furthermore, GenRec demonstrates extraordinary robustness in scenarios that only limited frames can be observed. Code will be available at https://***/wengzejia1/GenRec.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Recognition of Underwater Acoustic Target Using Sub-pretrained Convolutional Neural Networks 8th

Recognition of Underwater Acoustic Target Using Sub-pretrain...

引用

8th Conference on Sound and Music Technology, CSMT 2020

作者： Pan, Andi Chen, Xi Li, Wei School of Computer Science Fudan University Shanghai201203 China Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai201203 China

ISBN: (纸本)9789811616488

Underwater acoustic target recognition is the task of classifying targets using ship-radiated noise in the marine environment. It is incredibly hard and complex for the complexity of the marine environment. Before the popularization of deep learning, conventional target recognition methods are mainly based on the audio time-frequency domain analysis. Different targets have obvious variation in some frequency bands, which leads to the inability of traditional methods to make full use of spectral information. In order to extremely extract the information in each frequency bands, this paper proposes a novel Sub-pretrained CNNs. For each frequency band in the spectrogram, a CNN classifier is trained on the training set. Finally, the features extracted by each CNN and the position embedding of the frequency band are concatenated as the input of the global classifier. Compare with state of the art method, the paper achieves better performance. As the experimental results show, the identification performance of UATR can be enhanced by the Sub-pre-trained CNNs method. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Channel-wise Attention Mechanism in Convolutional Neural Networks for Music Emotion Recognition 8th

Channel-wise Attention Mechanism in Convolutional Neural Net...

引用

8th Conference on Sound and Music Technology, CSMT 2020

作者： Chen, Xi Wang, Lei Pan, Andi Li, Wei School of Computer Science Fudan University Shanghai201203 China Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai201203 China

ISBN: (纸本)9789811616488

Music Emotion Recognition (MER), a subject of affective computing, aims to identify the emotion of a musical track. With the fast development of deep learning, neural networks, such as Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM), have been applied recently. However, while using convolutional kernels, channels are treated equally, which means treating different aspects (such as tempo and vibrato related features) of a music clip equally. It’s against the rule of human perception. Therefore, Channel-wise Attention Mechanism is introduced into the task of Music Emotion Recognition. The performance could be improved to a certain extent. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Chorus Detection Using Music Structure Analysis 8th

Chorus Detection Using Music Structure Analysis

引用

8th Conference on Sound and Music Technology, CSMT 2020

作者： Cao, Zhengyu Gao, Yongwei Li, Wei School of Computer Science Fudan University Shanghai201203 China Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai201203 China

ISBN: (纸本)9789811616488

This paper describes a novel chorus detection method based on extracting the functional structure of music from its self-similarity matrix. An existing similarity measure was enhanced firstly by using a key-shift invariant distance and by introducing a chroma-like pitch feature that exploits melody extraction results of the music. The repeated sections in the audio were extracted using a graph-based algorithm and clustering-merging method assuming transitivity of similarity then. Finally, a classifier to detect the chorus from the repeated sections was trained. The evaluation results show that our method is comparable with the state-of-the-art algorithms on both multiple and single chorus section detection tasks. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Syntax-guided text generation via graph neural network

引用

science China(information sciences) 2021年第5期64卷 67-76页

作者： Qipeng GUO Xipeng QIU Xiangyang XUE Zheng ZHANG Shanghai Key Laboratory of Intelligent Information Processing School of Computer ScienceFudan University NYU Shanghai and AWS Shanghai AI Lab

Text generation is a fundamental and important task in natural language processing. Most of the existing models generate text in a sequential manner and have difficulty modeling complex dependency structures. In this paper, we treat the text generation task as a graph generation problem exploiting both syntactic and word-ordering relationships. Leveraging the framework of the graph neural network, we propose the word graph model. During the process, the model builds a sentence incrementally and maintains syntactic integrity via a syntax-driven, top-down, breadth-first generation process. Experimental results on both synthetic and real text generation tasks show the efficacy of our approach.

关键词： text generation deep learning graph neural network dependency parsing

来源：评论

学校读者我要写书评

暂无评论

Camouflaged Object Segmentation with Transformer 6th

Camouflaged Object Segmentation with Transformer

引用

6th International Conference on Cognitive Systems and Signal processing, ICCSIP 2021

作者： Wang, Haiwen Wang, Xinzhou Sun, Fuchun Song, Yixu State Key Lab on Intelligent Technology and Systems Department of Computer Science and Technology Tsinghua University Beijing China School of Electronic and Information Engineering Tongji University Shanghai China

ISBN: (纸本)9789811692468

The Vision Transformer (ViT) [6] directly applies a Transformer architecture to image classification and achieves an impressive result compared with convolutional networks. This paper presents a new ViT-base camouflaged object segmentation method, called COS Transformer, which aims to identify and segment objects concealed in a complex environment. The high intrinsic similarities between object and surrounding makes the task challenging than salient object detection. Most recent camouflaged object segmentation methods(e.g., EGNet [29], PraNet [10] and SINet [9]) adopt convolutional network with an encoder-decoder architecture and focused on increasing the receptive field, which is limited by the depth of the network. In camouflaged object segmentation (COS) task, the camouflage is mainly relied on contrast of the whole surrounding instead of the local information. We introduce transformer with global context awareness in this paper, for self-attention allowing COS Transformer to aggregate features globally even in the lowest layers. Specifically, the architecture is composed of a transformer-based encoder and a multi-layers feature aggregation refinement module. After training on the COD10K [9] dataset, COS Transformer attains excellent results compared to state-of-the-art convolutional networks, e.g. 11.7% improvement of E [8] on the COD10K contrasted to SINet. © 2022, Springer Nature Singapore Pte Ltd.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

FedISMH: Federated Learning Via Inference Similarity for Model Heterogeneous

FedISMH: Federated Learning Via Inference Similarity for Mod...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Li, Yongdong Wang, Li-E Sun, Zhigang Li, Xianxian Chang, Hengtong Xu, Jinke Lin, Caiyi Guangxi Normal University School of Computer Science and Engineering Guilin China Guangxi Normal University Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guilin China Guangxi Normal University Guangxi Key Lab of Multi-Source Information Mining and Security Guilin China

ISBN: (纸本)9798350362480

Federated Learning (FL) is a privacy-preserving machine learning paradigm, enabling decentralized devices to collaboratively train models without sharing local data. Traditional FL approaches, however, rely on averaging parameters across clients with homogeneous models, which limits their applicability in scenarios where clients require heterogeneous models. In this paper, we propose FedISMH, a novel approach to address model heterogeneity in FL. Instead of directly applying knowledge distillation, FedISMH clusters clients based on the structural similarities of client models, where clients' structural features can be extracted through either labeled or unlabeled dataset This allows the proposed model to identify clients with similar model architectures while preserving privacy. Additionally, FedISMH introduces a dynamic mechanism to manage noise clients by aligning them with the most structurally similar clusters, ensuring that their inclusion promote the performance of the cluster. Experimental results on MNIST and SVHN demonstrate that FedISMH consistently outperforms state-of-the-art methods in both IID and Non-IID settings, offering improved accuracy, robustness, and flexibility in heterogeneous FL environments. © 2024 IEEE.

关键词： Federated 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：