检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhou, Zi-Hao Fang, Siyuan Zhou, Zi-Jing Wei, Tong Wan, Yuanyu Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China Xiaomi Inc. China School of Software Technology Zhejiang University Ningbo China

Long-tailed semi-supervised learning poses a significant challenge in training models with limited labeled data exhibiting a long-tailed label distribution. Current state-of-the-art LTSSL approaches heavily rely on high-quality pseudo-labels for large-scale unlabeled data. However, these methods often neglect the impact of representations learned by the neural network and struggle with real-world unlabeled data, which typically follows a different distribution than labeled data. This paper introduces a novel probabilistic framework that unifies various recent proposals in long-tail learning. Our framework derives the class-balanced contrastive loss through Gaussian kernel density estimation. We introduce a continuous contrastive learning method, CCL, extending our framework to unlabeled data using reliable and smoothed pseudo-labels. By progressively estimating the underlying label distribution and optimizing its alignment with model predictions, we tackle the diverse distribution of unlabeled data in real-world scenarios. Extensive experiments across multiple datasets with varying unlabeled data distributions demonstrate that CCL consistently outperforms prior state-of-the-art methods, achieving over 4% improvement on the ImageNet-127 dataset. Our source code is available at https://***/zhouzihao11/CCL. © 2024, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Towards Modality-Agnostic Person Re-identification with Descriptive Query

Towards Modality-Agnostic Person Re-identification with Desc...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Cuiqun Chen Mang Ye Ding Jiang National Engineering Research Center for Multimedia Software Hubei Key Laboratory of Multimedia and Network Communication Engineering Institute of Artificial Intelligence School of Computer Science Wuhan University Wuhan China Hubei Luojia Laboratory Wuhan China

Person re-identification (ReID) with descriptive query (text or sketch) provides an important supplement for general image-image paradigms, which is usually studied in a single cross-modality matching manner, e.g., text-to-image or sketch-to-photo. However, without a camera-captured photo query, it is uncertain whether the text or sketch is available or not in practical scenarios. This motivates us to study a new and challenging modality-agnostic person re-ideruification problem. Towards this goal, we propose a unified person re-identification (UNIReID) architecture that can effectively adapt to cross-modality and multi-modality tasks. Specifically, UNIReID incorporates a simple dual-encoder with task-specific modality learning to mine and fuse visual and textual modality information. To deal with the imbalanced training problem of different tasks in UNIReID, we propose a task-aware dynamic training strategy in terms of task difficulty, adaptively adjusting the training focus. Besides, we construct three multi-modal ReID datasets by collecting the corresponding sketches from photos to support this challenging study. The experimental results on three multi-modal ReID datasets show that our UNIReID greatly improves the retrieval accuracy and generalization ability on different tasks and unseen scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Algorithm Contest of Calibration-free Motor Imagery BCI in the BCI Controlled Robot Contest in World Robot Contest 2021:A survey

引用

Brain Science Advances 2022年第2期8卷 127-141页

作者： Jing Luo Qi Mao Yaojie Wang Zhenghao Shi Xinhong Hei Shaanxi Key Laboratory for Network Computing and Security Technology School of Computer Science and EngineeringXi’an University of TechnologyXi’an 710054ShaanxiChina

Objective:From September 10 to 13,2021,the finals of the BCI Controlled Robot Contest in World Robot Contest 2021 were held in Beijing,*** teams participated in the Algorithm Contest of Calibration-free Motor Imagery *** participants employed both traditional electroencephalograph(EEG)analysis methods and deep learning-based methods in the *** this paper,we reviewed the algorithms utilized by the participants,extracted the trends and highlighted interesting approaches from these methods to inform future contests and research ***:First,we analyzed the algorithms in separate steps,including EEG channel and signal segment setup,prepossessing technology,and classification ***,we emphasized the highlights of each ***,we compared the competition algorithm with the SOTA ***:The algorithm employed in the finals performed better than that of the SOTA *** the final stage of the contest,four of the top five teams used convolutional neural network models,suggesting that with the rapid development of deep learning,convolutional neural network-based models have been the most popular methods in the field of motor imagery BCI.

关键词： brain-computer interface motor imagery con-volutional neural network World Robot Contest

来源：评论

学校读者我要写书评

暂无评论

Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval

Cross-Modal Implicit Relation Reasoning and Aligning for Tex...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Ding Jiang Mang Ye National Engineering Research Center for Multimedia Software Hubei Key Laboratory of Multimedia and Network Communication Engineering Institute of Artificial Intelligence School of Computer Science Wuhan University Wuhan China Hubei Luojia Laboratory Wuhan China

Text-to-image person retrieval aims to identify the target person based on a given textual description query. The primary challenge is to learn the mapping of visual and textual modalities into a common latent space. Prior works have attempted to address this challenge by leveraging separately pre-trained unimodal models to extract visual and textual features. However, these approaches lack the necessary underlying alignment capabilities required to match multimodal data effectively. Besides, these works use prior information to explore explicit part alignments, which may lead to the distortion of intra-modality information. To alleviate these issues, we present IRRA: a cross-modal Implicit Relation Reasoning and Aligning framework that learns relations between local visual-textual tokens and enhances global image-text matching without requiring additional prior supervision. Specifically, we first design an Implicit Relation Reasoning module in a masked language modeling paradigm. This achieves cross-modal interaction by integrating the visual cues into the textual tokens with a cross-modal multimodal interaction encoder. Secondly, to globally align the visual and textual embeddings, Similarity Distribution Matching is proposed to minimize the KL divergence between image-text similarity distributions and the normalized label matching distributions. The proposed method achieves new state-of-the-art results on all three public datasets, with a notable margin of about 3%-9% for Rank-1 accuracy compared to prior methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval

arXiv

引用

arXiv 2023年

作者： Jiang, Ding Ye, Mang National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering School of Computer Science Wuhan University Wuhan China Hubei Luojia Laboratory Wuhan China

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Multi-party privacy-preserving decision tree training with a privileged party

引用

Science China(Information Sciences) 2024年第8期67卷 253-268页

作者： Yiwen TONG Qi FENG Min LUO Debiao HE Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University Shanghai Technology Innovation Centre of Distributed Privacy-Preserving Artificial Intelligence Matrix Elements Technologies Key Laboratory of Computing Power Network and Information Security Ministry of EducationShandong Computer Science Center Qilu University of Technology(Shandong Academy of Sciences)

Currently, a decision tree is the most commonly used data mining algorithm for classification tasks. While a significant number of studies have investigated privacy-preserving decision trees, the methods proposed in these studies often have shortcomings in terms of data privacy breach or efficiency. Additionally,these methods typically only apply to symmetric frameworks, which consist of two or more parties with equal privilege, and are not suitable for asymmetric scenarios where parties have unequal privilege. In this paper,we propose SecureCART, a three-party privacy-preserving decision tree training scheme with a privileged party. We adopt the existing pMPL framework and design novel secure interactive protocols for division,comparison, and asymmetric multiplication. Compared to similar schemes, our division protocol is 93.5–560.4× faster, with the communication overhead reduced by over 90%; further, our multiplication protocol is approximately 1.5× faster, with the communication overhead reduced by around 20%. Our comparison protocol based on function secret sharing maintains good performance when adapted to pMPL. Based on the proposed secure protocols, we implement SecureCART in C++ and analyze its performance using three real-world datasets in both LAN and WAN environments. he experimental results indicate that SecureCART is significantly faster than similar schemes proposed in past studies, and that the loss of accuracy while using SecureCART remains within an acceptable range.

关键词： privacy protection decision trees secure multi-party computation secret sharing privileged party

来源：评论

学校读者我要写书评

暂无评论

Deep Convolutional Dictionary Learning network for Sparse View Ct Reconstruction with a Group Sparse Prior

SSRN

引用

SSRN 2023年

作者： Kang, Yanqin Liu, Jin Wu, Fan Wang, Kun Qiang, Jun Hu, Dianlin Zhang, Yikun College of Computer and Information Anhui Polytechnic University Wuhu China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing China School of Computer Science and Engineering Southeast University Nanjing China

Purpose: Many deep learning-based methods have been applied in sparse view computed tomography (CT) imaging. However, most methods are built intuitively using state-of-the-art black-box convolutional neural networks (CNNs) and lack interpretability. Moreover, CNNs tend to focus on local receptive fields, neglecting nonlocal self-similarity prior information. How to obtain diagnostically useful images from sparsely sampled projections is a challenging, ill-posed ***: To address this issue, we propose a novel interpretable model based on a convolutional dictionary learning network and nonlocal group sparse prior, called DCDL-GS, for sparse view CT image reconstruction. We apply a statistical iterative reconstruction algorithm for a fixed number of iterations with a neural network to improve the image reconstruction quality. Inspired by a group sparsity prior, we adopt a novel group thresholding operation to improve the feature representation and constraint ability and obtain a theoretical interpretation. Additionally, filtered backprojection (FBP) reconstruction, fast sliding window nonlocal self-similarity operations, and a lightweight convolutional dictionary learning network are integrated into our DCDL-GS model, improving model ***: The visual results based on the LDCT-P and UIH datasets show the efficiency of our proposed DCDL-GS model in edge preservation and feature recovery. The quantitative results show improvement over state-of-the-art methods, with improvements of 0.6-0.8 dB for the peak signal-to-noise ratio (PSNR), 0.005-0.01 for the structural similarity index measure (SSIM), and 1-1.3 for the regulated Fréchet inception distance (rFID) based on the test dataset. The quantitative results also show the effectiveness of our proposed deep convolution iterative reconstruction module and nonlocal group sparse ***: We developed a unified optimized mathematical model incorporating projection data and image prior knowled

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

A Data Security Protection Method for Deep Neural network Model Based on Mobility and Sharing 1

引用

18th International Conference on Green, Pervasive, and Cloud Computing, GPC 2023

作者： Zhao, Xinjian Li, Qianmu Wang, Qi Chen, Shi Li, Tengfei Li, Nianzhe State Grid Jiangsu Information and Telecommunication Company Jiangsu Nanjing210024 China School of Computer Science and Engineering Nanjing University of Science and Technology Jiangsu Nanjing210094 China State Grid Smart Grid Research Institute Co. Ltd. Jiangsu Nanjing210003 China State Grid Key Laboratory of Information and Network Security Jiangsu Nanjing210003 China

ISBN: (数字)9789819998937

ISBN: (纸本)9789819998920

With the rapid development of digital economy, numerous business scenarios, such as smart grid, energy network, intelligent transportation, etc., require the design and distribution of deep neural network (DNN) models, which typically use large amounts of data and computing resources for training. As a result, DNN models are now considered important assets, but at great risk of being stolen and distributed illegally. In response to the new risks and challenges brought by frequent data flow and sharing, watermarks have been introduced to protect the ownership of DNN models. Watermarks can be extracted in a relatively simple manner to declare ownership of a model. However, watermarks are vulnerable to attacks. In this work, we propose a novel label-based black-box watermark model protection algorithm. Inspired by new labels, we design a method to embed watermarks by adding new labels in the model, and to prevent watermarks from being forged, we use encryption algorithms to generate key samples. We conduct experiments on the VGG19 model using the CIFAR-10 dataset. Experimental results show that the method is robust to fine-tuning attacks, pruning attacks. Furthermore, our method does not affect the performance of deep neural network models. This method helps to solve scenarios such as "internal data circulation, external data sharing and multi-party data collaboration". © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

From Haziness to Clarity: A Novel Iterative Memory-Retrospective Emergence Model for Omnidirectional Image Saliency Prediction

引用

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society 2025年 34卷 3944-3959页

作者： Dandan Zhu Kaiwei Zhang Xiongkuo Min Guangtao Zhai Xiaokang Yang School of Computer Science and Technology East China Normal University Shanghai China Shanghai Artificial Intelligence Laboratory Shanghai China Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai China MoE Key Laboratory of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China

To achieve saliency prediction in omnidirectional images (ODIs), the majority of prior works typically adopt the convolutional neural networks (CNNs)-based saliency models to extract semantic features to predict prominent regions in ODIs. Albeit achieving substantially performance gains, these works all employed purely visual computing paradigms and ignore to explore the nature of human visual attention mechanisms. In other words, existing saliency prediction works for ODIs are insufficient to capture the biological characteristics of the visual attention mechanism in the human brain. To establish a more explicit link between saliency prediction performance and brain-like visual attention mechanism, we simulate the mechanism of human retrospective memory in neuropsychology and propose IMRE model, a novel iterative memory-retrospective emergence model can predict and infer the salient features by recalling previously learned information. In IMRE model, we introduce four key modules to simulate the visual attention mechanism for predicting human fixations in the human brain. Firstly, the visual stimulus response module is designed to effectively extract semantic features and capture the intricate relationship between these features, acting as the human visual cortex. Secondly, the retrospective integration module serves to distill valuable information from a fuzzy memory ensemble, resembling the role of the basal ganglia in the neural system. Thirdly, the memory bank module explicitly records and stores subconscious response information and learned knowledge, acting like the hippocampus in neural system. Lastly, the prospective inference module accurately infers saliency maps from the refined useful information, resembling the role of the prefrontal cortex. During prediction, we utilize the introduced memory bank to retrieve and recall previously learned information, which simulates the process of memory emergence from haziness to clarity. Such a process aligns with t

关键词： Visualization Predictive models Feature extraction Brain modeling Prediction methods Solid modeling Computational modeling Attention mechanisms Accuracy Faces

来源：评论

学校读者我要写书评

暂无评论

Multimodal Dialogue Emotion Recognition Based on Label Optimization and Coarse-Grained Assisted Fine-Grained

Multimodal Dialogue Emotion Recognition Based on Label Optim...

引用

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

作者： Zhibo Zhang Zhenyu Yang Yan Huang Baojie Xu Wenyue Hu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Multimodal dialogue emotion recognition integrates data from multiple modalities to accurately identify emotional states in conversations. However, differences in expression and information density across modalities complicate the fusion of features. Traditional methods may introduce redundant information from other utterances, reducing the accuracy of emotion recognition. Existing one-hot labels often fail to capture the full range of emotional expressions, leading to biased results. To address these issues, we propose a model that fuses different modalities within the same utterance to avoid redundancy. It employs a progressive classification process, refining emotion recognition from coarse to fine granularity. Additionally, we use emotion polarity probabilities as weights for fine-grained classification and introduce a multimodal information-rich label that considers both the data and their interactions. Experiments on IEMOCAP and MELD datasets demonstrate the model’s effectiveness, significantly improving dialog emotion recognition accuracy. Our code is available at https://***/r/LOCG-188E.

关键词： Emotion recognition Accuracy Fuses Refining Termination of employment Speech recognition Signal processing Speech processing Optimization Faces

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：