检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Li, Chenglong Xue, Wanlin Jia, Yaqing Qu, Zhichen Luo, Bin Tang, Jin Sun, Dengdi Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Artificial Intelligence Anhui University Hefei230601 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Key Lab of Intelligent Computing and Signal Processing of Ministry of Education Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China

RGBT tracking receives a surge of interest in the computer vision community, but this research field lacks a large-scale and high-diversity benchmark dataset, which is essential for both the training of deep RGBT trackers and the comprehensive evaluation of RGBT tracking methods. To this end, we present a Large-scale High-diversity benchmark for short-term RGBT tracking (LasHeR) in this work. LasHeR consists of 1224 visible and thermal infrared video pairs with more than 730K frame pairs in total. Each frame pair is spatially aligned and manually annotated with a bounding box, making the dataset well and densely annotated. LasHeR is highly diverse capturing from a broad range of object categories, camera viewpoints, scene complexities and environmental factors across seasons, weathers, day and night. We conduct a comprehensive performance evaluation of 12 RGBT tracking algorithms on the LasHeR dataset and present detailed analysis. In addition, we release the unaligned version of LasHeR to attract the research interest for alignment-free RGBT tracking, which is a more practical task in real-world applications. The datasets and evaluation protocols are available at: https://***/mmic-lcl/Datasets-and-benchmark-code. Copyright © 2021, The Authors. All rights reserved.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Semantic knowledge transfer for semi-supervised medical image segmentation

引用

Engineering Applications of Artificial intelligence 2025年 158卷

作者： Shiwei Zhou Haifeng Zhao Leilei Ma Dengdi Sun Key Laboratory of Intelligent Computing & Signal Processing (ICSP) Ministry of Education Anhui University Hefei 230601 China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Anhui University Hefei 230601 China School of Computer Science and Technology Anhui University Hefei 230601 China School of Artificial Intelligence Anhui University Hefei 230601 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei 230026 China

In semi-supervised medical image segmentation, due to possible differences in information content and distribution between labeled and unlabeled data, dealing with the two separately usually prevents knowledge transfer from labeled to unlabeled data. This prevents the model from effectively sharing learned information between the two types of data. To alleviate this problem, we train labeled and unlabeled data as a whole. Semantic mixing of labeled and unlabeled data is achieved by selecting and exchanging some of the region images of both through a mask to generate complementary input views. In addition, due to the limited labeled data, the unlabeled data has a weak ability to distinguish categories in the feature space. Traditional methods rely on pixel positions to generate positive and negative samples for contrastive learning to solve this problem, but relying on pixel position sampling can easily lead to semantic inconsistency, which affects the effect of feature learning; therefore, to address this problem, we propose an innovative labeled data-guided inter-class contrastive learning strategy, which extracts the category features from labeled and unlabeled data and exploits the accurate category information in the labeled data to guide contrastive learning, while introducing a similarity-based ranking weighting mechanism. Combining the two designs, we propose a new semantic knowledge transfer framework for semi-supervised medical image segmentation. Experiments demonstrate a significant improvement in our model compared to State of the Art (SOTA) on the Automatic Cardiac Diagnosis Challenge (ACDC) dataset and the Left Atrium (LA) dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Differentiable neural architecture learning for efficient neural network design

arXiv

引用

arXiv 2021年

作者： Guo, Qingbei Wu, Xiao-Jun Kittler, Josef Feng, Zhiquan Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi214122 China Shandong Provincial Key Laboratory of Network based Intelligent Computing University of Jinan Jinan250022 China Centre for Vision Speech and Signal Processing University of Surrey GuildfordGU2 7XH United Kingdom

Automated neural network design has received ever-increasing attention with the evolution of deep convolutional neural networks (CNNs), especially involving their deployment on embedded and mobile platforms. One of the biggest problems that neural architecture search (NAS) confronts is that a large number of candidate neural architectures are required to train, using, for instance, reinforcement learning and evolutionary optimisation algorithms, at a vast computation cost. Even recent differentiable neural architecture search (DNAS) samples a small number of candidate neural architectures based on the probability distribution of learned architecture parameters to select the final neural architecture. To address this computational complexity issue, we introduce a novel architecture parameterisation based on scaled sigmoid function, and propose a general Differentiable Neural Architecture Learning (DNAL) method to optimize the neural architecture without the need to evaluate candidate neural networks. Specifically, for stochastic supernets as well as conventional CNNs, we build a new channel-wise module layer with the architecture components controlled by a scaled sigmoid function. We train these neural network models from scratch. The network optimization is decoupled into the weight optimization and the architecture optimization, which avoids the interaction between the two types of parameters and alleviates the vanishing gradient problem. We address the non-convex optimization problem of neural architecture by the continuous scaled sigmoid method with convergence guarantees. Extensive experiments demonstrate our DNAL method delivers superior performance in terms of neural architecture search cost, and adapts to conventional CNNs (e.g., VGG16 and ResNet50), lightweight CNNs (e.g., MobileNetV2) and stochastic supernets (e.g., ProxylessNAS). The optimal networks learned by DNAL surpass those produced by the state-of-the-art methods on the benchmark CIFAR-10 and ImageN

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

An End to End Method of Whisper Enhancement

An End to End Method of Whisper Enhancement

引用

IEEE International Conference on Information Communication and signal processing (ICICSP)

作者： Yan Huang HaiLun Lian Jian Zhou HuaBin Wang Liang Tao MOE Key Laboratory of Intelligent Computing and Signal Processing Anhui University Hefei China

In this paper, we propose a method of enhancing whisper, using whisper without any pretreatment combined with Wavenet. Our method is end-to-end, that is, inputing noised whisper to get clean whisper. The input to our method is the original whisper without any processing, reducing the loss of features caused by other operations. We use speech denoising Wavenet to enhance whisper. Wavenet can not only enhance whisper well, but also tackle the issue of intelligibility. Specifically, use symmetric dilated convolution to obtain noisy speech context, help the model to enhance the speech for better denoising effect. Experimental results show that the enchanced whisper gains better performance both in the aspect of speech quality and intelligibility.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Whispered Speech to Normal Speech Conversion Using Bidirectional LSTMs with Meta-network

Whispered Speech to Normal Speech Conversion Using Bidirecti...

引用

IEEE International Conference on Information Communication and signal processing (ICICSP)

作者： WeiWei Yu HaiLun Lian Jian Zhou HuaBin Wang Liang Tao MOE Key Laboratory of Intelligent Computing and Signal Processing Anhui University Hefei China

In this paper, we are interested in the conversion of whispered to normal speech. The baseline method uses standard bidirectional LSTM (BLSTM) RNN to predict both the spectral features and excitation parameters of the normal speech from whispered speech. Also, it employs STRAIGHT speech synthesizer. The BLSTM based whispered speech to normal speech conversion system is among the best systems in term of the naturalness of generated speech. However, in many cases, the model complexity and inference cost of BLSTM prevents its usage. As opposed to using standard BLSTM with sharing values, we propose a meta-network to generate non-shared weights for LSTM memory block in BLSTM (denote as meta-BLSTM). Besides, we use a low-rank approximation to generate the parameter matrix, which can reduce the model complexity. To our knowledge, this is the first study that uses meta-network to train a whispered to normal speech conversion system. To evaluate the performance of the proposed system, we performed experiments in the TIMIT dataset. Experimental results show that the proposed method achieves state-of-the-art performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hybrid graph-based radiology report generation

引用

Expert Systems with Applications 2025年 289卷

作者： Dengdi Sun Chaofan Mu Xuyang Fan Jin Tang Zegeng Li Jie Zhu Zhuanlian Ding Key Laboratory of Intelligent Computing & Signal Processing (ICSP) Ministry of Education School of Artificial Intelligence Anhui University Hefei 230601 China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei 230601 China First Affiliated Hospital of Anhui University of Chinese Medicine Hefei 230031 China College of Integrated Chinese and Western Medicine Anhui University of Chinese Medicine Hefei 230012 China School of Internet Anhui University Hefei 230039 China

Automatic report generation plays a crucial role in clinical practice by alleviating the heavy workload on doctors and helping to prevent misdiagnoses or missed diagnoses. In the context of radiology report generation, knowledge injection is essential, particularly with the encoder-decoder framework commonly used in image captioning tasks. However, existing studies predominantly rely on expert knowledge, which is both challenging to collect and lacks universality. Additionally, this expert knowledge typically influences single-mode information and overlooks the importance of bridging the visual-to-textual gap. To address these challenges, we propose a hybrid graph-based approach for radiology report generation. Our method integrates two key components: the semantic homogeneous graph (SHG) and the cross-modal heterogeneous graph (CHG). Specifically, the SHG is constructed by mining semantic relationships between keywords across the entire corpus to generate universal knowledge. The CHG, conversely, is built from visual features, textual features, and corresponding knowledge embeddings, enabling knowledge injection during modal interaction. By leveraging graph convolutional networks to enhance graph embeddings, our model improves the quality of generated reports. Experimental results on two widely used benchmark datasets, IU-Xray and MIMIC-CXR, demonstrate the effectiveness of our approach. Notably, our method achieves a BLEU-4 score of 0.185 on the IU-Xray dataset and an F1 score of 0.418 on the MIMIC-CXR dataset, significantly outperforming existing methods.

关键词： Graph convolutional network Hybrid graph Knowledge injection Radiology report generation

来源：评论

学校读者我要写书评

暂无评论

Cross-Modality Coherent Registration of Whole Mouse Brains

Research Square

引用

Research Square 2021年

作者： Peng, Hanchuan Qu, Lei Li, Yuanyuan Xie, Peng Liu, Lijuan Wang, Yimin Wu, Jun Liu, Yu Wang, Tao Li, Longfei Guo, Kaixuan Wan, Wan Ouyang, Lei Xiong, Feng Zheng, Yefeng Xu, Fang Gong, Hui Dong, Hongwei Luo, Qingming Bi, Guo-Qiang Hawrylycz, Michael Zeng, Hongkui Allen Institute for Brain Science United States Key Laboratory of Intelligent Computation & Signal Processing Ministry of Education Anhui University China SEU-ALLEN Joint Center Institute for Brain Intelligence Southeast University Bangladesh Institute for Brain and Intelligence Southeast University Bangladesh Tencent Jarvis Lab China CAS Key Laboratory of Brain Connectome and Manipulation China Britton Chance Center for Biomedical Photonics Wuhan National Laboratory for Optoelectronics MoE Key Laboratory for Biomedical Photonics Huazhong University of Science and Technology China Center for Integrative Connectomics Department of Neurobiology David Geffen School of Medicine UCLA United States Hainan University China Hefei National Laboratory for Physical Sciences at the Microscale School of Life Sciences University of Science and Technology of China China

Recent whole brain mapping projects are collecting large-scale 3D images using powerful and informative modalities, such as STPT, fMOST, VISoR, or MRI. Registration of these multi-dimensional whole-brain images onto a standard atlas is essential for characterizing neuron types and constructing brain wiring diagrams. However, cross-modality image registration is challenging due to intrinsic variations of brain anatomy and artifacts resulted from different sample preparation methods and imaging modalities. We introduced a cross-modality registration method, called mBrainAligner, which uses coherent landmark mapping as well as deep neural networks to align whole mouse brain images to the standard Allen Common Coordinate Framework atlas. We also built a single cell resolution atlas using the fMOST modality, and used our method to generate whole brain map of 3D full single neuron morphology and neuron cell types. © 2021, CC BY.

关键词： Brain mapping

来源：评论

学校读者我要写书评

暂无评论

Let's play music: Audio-driven performance video generation

arXiv

引用

arXiv 2020年

作者： Zhu, Hao Li, Yi Zhu, Feixia Zheng, Aihua He, Ran Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei China CASIA Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Center for Excellence in Brain Science and Intelligence Technology CAS Beijing China

We propose a new task named Audio-driven Performance Video Generation (APVG), which aims to synthesize the video of a person playing a certain instrument guided by a given music audio clip. It is a challenging task to generate the high-dimensional temporal consistent videos from low-dimensional audio modality. In this paper, we propose a multistaged framework to achieve this new task to generate realistic and synchronized performance video from given music. Firstly, we provide both global appearance and local spatial information by generating the coarse videos and keypoints of body and hands from a given music respectively. Then, we propose to transform the generated keypoints to heatmap via a differentiable space transformer, since the heatmap offers more spatial information but is harder to generate directly from audio. Finally, we propose a Structured Temporal UNet (STU) to extract both intra-frame structured information and inter-frame temporal consistency. They are obtained via graph-based structure module, and CNN-GRU based high-level temporal module respectively for final video generation. Comprehensive experiments validate the effectiveness of our proposed framework. Copyright © 2020, The Authors. All rights reserved.

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

Multistage model for robust face alignment using deep neural networks

arXiv

引用

arXiv 2020年

作者： Wang, Huabin Cheng, Rui Zhou, Jian Tao, Liang Kwan, Hon Keung MOE Key Laboratory of Intelligent Computing and Signal Processing School of Computer Science and Technology Anhui University Hefei Anhui230601 China Department of Electrical and Computer Engineering University of Windsor WindsorONN9B 3P4 Canada

An ability to generalize unconstrained conditions such as severe occlusions and large pose variations remains a challenging goal to achieve in face alignment. In this paper, a multistage model based on deep neural networks is proposed which takes advantage of spatial transformer networks, hourglass networks and exemplar-based shape constraints. First, a spatial transformer - generative adversarial network which consists of convolutional layers and residual units is utilized to solve the initialization issues caused by face detectors, such as rotation and scale variations, to obtain improved face bounding boxes for face alignment. Then, stacked hourglass network is employed to obtain preliminary locations of landmarks as well as their corresponding scores. In addition, an exemplar-based shape dictionary is designed to determine landmarks with low scores based on those with high scores. By incorporating face shape constraints, misaligned landmarks caused by occlusions or cluttered backgrounds can be considerably improved. Extensive experiments based on challenging benchmark datasets are performed to demonstrate the superior performance of the proposed method over other state-of-the-art methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Correction to: Enhancing cyber defense strategies with discrete multi-dimensional Z-numbers: a multi-attribute decision-making approach

引用

Complex & Intelligent Systems 2025年第7期11卷 1-1页

作者： Yao, Aiting Huang, Chen Zhang, Weiqi Dong, Chengzu Lu, Meiqu Mao, Junjun Liu, Xiao Li, Xuejun Anhui Provincial International Joint Research Center for Advanced Technology in Medical Imaging School of Computer Science and Technology Anhui University Hefei China AI Techplus Pty Ltd Organization Melbourne Australia School of Information Technology Deakin University Geelong Australia School of Data Science Lingnan University Hongkong China School of Artificial Intelligence Guangxi Minzu University Nanning China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Hefei China

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：