检索结果-内蒙古大学图书馆

2020 3rd International Conference on Computer Information Science and Artificial Intelligence, CISAI 2020

作者： Wu, Tianxin Zhao, Lasheng Zhang, Qiang Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education Dalian University Dalian116622 China

In recent years, Text-To-Speech (TTS) technology has developed rapidly. People have also been paying more attention to how to narrow the gap between synthetic speech and real speech, hoping that synthesized speech can be integrated with real rhythm. A rhythmic feature embedding method for Text-To-Speech was proposed in this thesis based on Tacotron2 model, which has arisen in the field of TTS in recent years. Firstly, rhythmic feature extraction through World vocoder can reduce redundant information in rhythmic features. Then, rhythmic feature fusion based on Variational Auto-Encoder (VAE) network can enhance rhythmic information. Experiments are carried out on the data set LJSpeech-1.0, and then subjective evaluation and objective evaluation are carried out on the synthesized speech respectively. Compared with the comparative literature, the subjective blind hearing test (ABX) score increased by 25%. At that same time, the objective Mel Cepstral Distortion value (MCD) declined to 12.77. © Published under licence by IOP Publishing Ltd.

关键词： Speech synthesis

来源：评论

学校读者我要写书评

暂无评论

A Novel Cross-FOV Gaze-Driven Human-Robot Interaction Framework for Service Robots

A Novel Cross-FOV Gaze-Driven Human-Robot Interaction Framew...

引用

Symposia and Workshops on Ubiquitous, Autonomic and Trusted computing, UIC-ATC

作者： Zheng Zhao Pengfei Yi Jing Dong Rui Liu Mingkai Cheng Dongsheng Zhou Xiaopeng Wei Key Laboratory of Advanced Design and Intelligent Computing (Ministry of Education) School of Software Engineering Dalian University Dalian China Dalian University of Technology Dalian China

Gaze-based methods have been widely applied in human-robot interactions (HRI). However, most methods were often limited to scenarios where the human face and the gazed object should be in the same field of view (FOV), which is difficult to adapt to the complex and changeable typical daily life scene where the service robot is located. To improve the limitation, this paper proposes a framework capable of completing tasks even if the person and the gazed object are not in the same FOV, requiring only a single RGB camera. First, a cross-FOV gaze estimation algorithm is designed to get the gaze point from images containing a human face captured by an RGB camera. Then a multi-view fusion decision model is employed to drive the robot to turn to the gaze point and identify the object according to the gaze point. Finally, a robot can complete tasks using this information. Experiments under conditions of different lighting, different scenes and different users on the NAO robot show the effectiveness of our method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DCET-Net: Dual-Stream Convolution Expanded Transformer for Breast Cancer Histopathological Image Classification

DCET-Net: Dual-Stream Convolution Expanded Transformer for B...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Zou, Ying Chen, Shannan Sun, Qiule Liu, Bin Zhang, Jianxin Dalian University Key Lab of Advanced Design and Intelligent Computing Ministry of Education Dalian China Dalian University of Technology School of Information and Communication Engineering Dalian China Dalian China Dalian Minzu University School of Computer Science and Engineering Dalian China

ISBN: (纸本)9781665401265

Researches on breast cancer histopathological image classification have achieved a great breakthrough using deep backbones of Convolutional Neural Networks (CNNs) in recent years. However, due to the inductive bias of locality, CNNs are unable to effectively extract the global feature information of breast cancer histopathological images, limiting the improvement of the classification results. To overcome this shortcoming, this paper reasonably introduces an extra backbone stream of a pure transformer, which consists of a self-attention mechanism to capture global receptive fields of histopathological images, thereby compensating the locality characteristic of CNNs backbone. Based on two backbone streams of CNN and transformer, a dual-stream network called DCET-Net is proposed, which considers local features and global ones simultaneously, and progressively combines them from these two streams to form the final representations for classification. DCET-Net is extensively evaluated on the representative BreakHis histopathological image dataset, and experimental results demonstrate that it is highly competitive with the state-of-the-art CNN methods in breast cancer histopathological image classification task. © 2021 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Prompt-based Unifying Inference Attack on Graph Neural Networks

arXiv

引用

arXiv 2024年

作者： Wei, Yuecen Fu, Xingcheng Liu, Lingyun Sun, Qingyun Peng, Hao Hu, Chunming School of Software Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University China

Graph neural networks (GNNs) provide important prospective insights in applications such as social behavior analysis and financial risk analysis based on their powerful learning capabilities on graph data. Nevertheless, GNNs’ predictive performance relies on the quality of task-specific node labels, so it is common practice to improve the model’s generalization ability in the downstream execution of decision-making tasks through pre-training. Graph prompting is a prudent choice but risky without taking measures to prevent data leakage. In other words, in high-risk decision scenarios, prompt learning can infer private information by accessing model parameters trained on private data (publishing model parameters in pre-training, i.e., without directly leaking the raw data, is a tacitly accepted trend). However, myriad graph inference attacks necessitate tailored module design and processing to enhance inference capabilities due to variations in supervision signals. In this paper, we propose a novel Prompt-based unifying Inference Attack framework on GNNs, named ProIA. Specifically, ProIA retains the crucial topological information of the graph during pre-training, enhancing the background knowledge of the inference attack model. It then utilizes a unified prompt and introduces additional disentanglement factors in downstream attacks to adapt to task-relevant knowledge. Finally, extensive experiments show that ProIA enhances attack capabilities and demonstrates remarkable adaptability to various inference attacks. Copyright © 2024, The Authors. All rights reserved.

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

Patch Is Not All You Need

arXiv

引用

arXiv 2023年

作者： Li, Changzhen Zhang, Jie Wei, Yang Ji, Zhilong Bai, Jinfeng Shan, Shiguang Key Lab of Intelligent Information Processing Chinese Academy of Sciences Institute of Computing Technology China University of Chinese Academy of Sciences China Hangzhou lnstitute for Advanced Study UCAS School of Intelligent Scienceand Technology China Tomorrow Advancing Life China

Vision Transformers have achieved great success in computer visions, delivering exceptional performance across various tasks. However, their inherent reliance on sequential input enforces the manual partitioning of images into patch sequences, which disrupts the image’s inherent structural and semantic continuity. To handle this, we propose a novel Pattern Transformer (Patternformer) to adaptively convert images to pattern sequences for Transformer input. Specifically, we employ the Convolutional Neural Network to extract various patterns from the input image, with each channel representing a unique pattern that is fed into the succeeding Transformer as a visual token. By enabling the network to optimize these patterns, each pattern concentrates on its local region of interest, thereby preserving its intrinsic structural and semantic information. Only employing the vanilla ResNet and Transformer, we have accomplished state-of-the-art performance on CIFAR-10 and CIFAR-100, and have achieved competitive results on ImageNet. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Triplet-Attention Residual Network for Breast Cancer Histopathology Image Classification 21

Triplet-Attention Residual Network for Breast Cancer Histopa...

引用

Proceedings of the 5th International Conference on Advances in Image Processing

作者： Lu Cao Shan Huang Jianxin Zhang School of Computer Science and Engineering Dalian Minzu University China School of Computer Science and Engineering Dalian Minzu University China and Key Lab of Advanced Design and Intelligent Computing(Ministry of Education) Dalian University China

ISBN: (纸本)9781450385183

Recently, breast cancer histopathology image classification using convolutional neural networks has achieved more and more attentions with the great progress. To capture more discriminant deep features for the classification, this paper proposes a novel triplet-attention residual network, i.e., TAResNet, to distinguish the breast cancer histopathology image. TAResNet employs the representative ResNet18 model to extract deep features of histopathology images, followed by a triplet-attention module to further boost the discriminability of deep features through expanding feature diversity and enhancing inter-dimensional dependency. Extensive experiments carried out on the public BreakHis dataset well evaluate the effectiveness the given TAResNet model. More specifically, TAResNet achieves its optimal classification accuracy of 98.34% and 98.77% at the image level and patient level, respectively.

关键词： Breast cancer Triplet attention Histopathological image classification Convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

AN EMPIRICAL ANALYSIS OF UNCERTAINTY IN LARGE LANGUAGE MODEL EVALUATIONS

arXiv

引用

arXiv 2025年

作者： Xie, Qiujie Li, Qingqiu Yu, Zhuohao Zhang, Yuejie Zhang, Yue Yang, Linyi Zhejiang University China School of Engineering Westlake University China School of Computer Science Shanghai Key Lab of Intelligent Information Processing Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University China Peking University China Westlake Institute for Advanced Study China University College London United Kingdom Huawei Noah’s Ark Lab Hong Kong

As LLM-as-a-Judge emerges as a new paradigm for assessing large language models (LLMs), concerns have been raised regarding the alignment, bias, and stability of LLM evaluators. While substantial work has focused on alignment and bias, little research has concentrated on the stability of LLM evaluators. In this paper, we conduct extensive experiments involving 9 widely used LLM evaluators across 2 different evaluation settings to investigate the uncertainty in model-based LLM evaluations. We pinpoint that LLM evaluators exhibit varying uncertainty based on model families and sizes. With careful comparative analyses, we find that employing special prompting strategies, whether during inference or post-training, can alleviate evaluation uncertainty to some extent. By utilizing uncertainty to enhance LLM’s reliability and detection capability in Out-Of-Distribution (OOD) data, we further fine-tune an uncertainty-aware LLM evaluator named ConfiLM using a human-annotated fine-tuning set and assess ConfiLM’s OOD evaluation ability on a manually designed test set sourced from the 2024 Olympics. Experimental results demonstrate that incorporating uncertainty as additional information during the fine-tuning phase can largely improve the model’s evaluation performance in OOD scenarios. The code and data are released at: https://***/hasakiXie123/LLM-Evaluator-Uncertainty. © 2025, CC BY-NC-SA.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Super-Resolution-Based Channel Completion for Massive MISO Systems

引用

IEEE Signal Processing Letters 2025年 32卷 2254-2258页

作者： Zu, Keke He, Yuhan Chen, Hongyang Zheng, Yu Haardt, Martin Yangtze Delta Region Institute (Quzhou) University of Electronic Science and Technology of China Zhejiang China Shenzhen Key Laboratory of Advanced Machine Learning and Applications Shenzhen University Shenzhen China Research Center for Graph Computing Zhejiang Lab Hangzhou China JD Intelligent Cities Research Beijing China Communications Research Lab Ilmenau University of Technology Ilmenau Germany

With the deployment of large-scale antenna arrays, the already limited time-frequency resources are becoming increasingly scarce. In this study, we propose a novel Laplacian Pyramid Channel Completion Network (LPCCNet) designed for channel completion, thereby reducing the demand for time-frequency resources in massive MIMO systems. Compared with existing network models, the proposed LPCCNet, by employing a progressive upsampling architecture, effectively mitigates aliasing effects, suppresses error propagation, and achieves a substantial reduction in computational complexity. The simulation results show that LPCCNet achieves a superior channel completion quality compared to existing methods, particularly in rapidly time-varying scenarios. © 1994-2012 IEEE.

关键词： Channel estimation Feature extraction Image reconstruction Interpolation Training Superresolution Filters Vectors Convolutional neural networks Time-frequency analysis

来源：评论

学校读者我要写书评

暂无评论

Aspect-Level Sentiment Classification of Chinese Patient Comments Based on Pre-trained Sentiment Embedding

Aspect-Level Sentiment Classification of Chinese Patient Com...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Shan, Yongxue Zhong, Zhaoqian Che, Chao Jin, Bo Wei, Xiaopeng Dalian University Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education Dalian China Dalian University of Technology School of Innovation and Entrepreneurship Dalian China School of Computer Science and Technology Dalian University of Technology Dalian China

ISBN: (纸本)9781665401265

With the development of information technology, online health care service platforms have collected a large amount of patient comment information. Through fine-grained sentiment classification of this information, we can provide references for patients to seek medical treatment and help doctors understand their work. Therefore, we proposed a model that integrated pre-trained emotional information and semantic information at the word and character level for aspect-level sentiment classification. Specifically, we employed adversarial learning for training sentiment word embeddings and the two-layer bidirectional long short-term memory network to extract the sentiment embedding of the entire sentence in a specific aspect. We also combined the pre-trained sentiment feature vector with the structured semantic information by linear weighting and the multi-head self-attention mechanism, enabling the model to pay more attention to the information most relevant to a given aspect category. We performed experiments on the Chinese patient comments data set constructed by our research team and the proposed model outperformed the state-of-the-art methods, which proved the effectiveness of the proposed model for aspect-level sentiment classification of Chinese patient comments. © 2021 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Environment-aware dynamic graph learning for out-of-distribution generalization 23

Environment-aware dynamic graph learning for out-of-distribu...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Haonan Yuan Qingyun Sun Xingcheng Fu Ziwei Zhang Cheng Ji Hao Peng Jianxin Li Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University and School of Computer Science and Engineering Beihang University Key Lab of Education Blockchain and Intelligent Technology Guangxi Normal University Department of Computer Science and Technology Tsinghua University Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University

Dynamic graph neural networks (DGNNs) are increasingly pervasive in exploiting spatio-temporal patterns on dynamic graphs. However, existing works fail to generalize under distribution shifts, which are common in real-world scenarios. As the generation of dynamic graphs is heavily influenced by latent environments, investigating their impacts on the out-of-distribution (OOD) generalization is critical. However, it remains unexplored with the following two major challenges: (1) How to properly model and infer the complex environments on dynamic graphs with distribution shifts? (2) How to discover invariant patterns given inferred spatio-temporal environments? To solve these challenges, we propose a novel Environment-Aware dynamic Graph LEarning (EAGLE) framework for OOD generalization by modeling complex coupled environments and exploiting spatiotemporal invariant patterns. Specifically, we first design the environment-aware EADGNN to model environments by multi-channel environments disentangling. Then, we propose an environment instantiation mechanism for environment diversification with inferred distributions. Finally, we discriminate spatio-temporal invariant patterns for out-of-distribution prediction by the invariant pattern recognition mechanism and perform fine-grained causal interventions node-wisely with a mixture of instantiated environment samples. Experiments on real-world and synthetic dynamic graph datasets demonstrate the superiority of our method against state-of-the-art baselines under distribution shifts. To the best of our knowledge, we are the first to study OOD generalization on dynamic graphs from the environment learning perspective.

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：