检索结果-内蒙古大学图书馆

Dual Adaptive Representation Alignment for Cross-Domain Few-Shot Learning

IEEE Transactions on Pattern Analysis and Machine Intelligence 2023年第10期45卷 11720-11732页

作者： Zhao, Yifan Zhang, Tong Li, Jia Tian, Yonghong Peking University The School of Computer Science Beijing100871 China Beihang University The State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing100191 China The Pengcheng Laboratory Guangdong Shenzhen518055 China Peking University Shenzhen Granduate School The School of Electronic and Computer Engineering Guangdong Shenzhen518055 China

Few-shot learning aims to recognize novel queries with limited support samples by learning from base knowledge. Recent progress in this setting assumes that the base knowledge and novel query samples are distributed in the same domains, which are usually infeasible for realistic applications. Toward this issue, we propose to address the cross-domain few-shot learning problem where only extremely few samples are available in target domains. Under this realistic setting, we focus on the fast adaptation capability of meta-learners by proposing an effective dual adaptive representation alignment approach. In our approach, a prototypical feature alignment is first proposed to recalibrate support instances as prototypes and reproject these prototypes with a differentiable closed-form solution. Therefore feature spaces of learned knowledge can be adaptively transformed to query spaces by the cross-instance and cross-prototype relations. Besides the feature alignment, we further present a normalized distribution alignment module, which exploits prior statistics of query samples for solving the covariant shifts among the support and query samples. With these two modules, a progressive meta-learning framework is constructed to perform the fast adaptation with extremely few-shot samples while maintaining its generalization capabilities. Experimental evidence demonstrates our approach achieves new state-of-the-art results on 4 CDFSL benchmarks and 4 fine-grained cross-domain benchmarks. © 1979-2012 IEEE.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

LipText: Lip Tracking Based Text Entry in VR 1st

LipText: Lip Tracking Based Text Entry in VR

引用

1st International Conference on Extended reality, ICXR 2024

作者： Leng, Jiaye Wang, Zijun Wu, Jian Wang, Lili School of Creative Media City University of Hong Kong Kowloon Tong Hong Kong State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China

ISBN: (纸本)9789819636785

Text entry is an important task in virtual reality (VR), and most existing methods require hand involvement, while hands-free typing has great potential for applications in mobile scenarios. Existing hands-free text entry methods are usually implemented by combining the head and eyes with techniques such as Dwell, Blink and Gesture, which can easily fatigue the user. In this paper, we propose LipText, a lip-tracking-based text entry method in VR. We use a neural network to perform letter-level prediction on the lip data captured by the facial tracker and use head-based selection as an auxiliary to improve the accuracy. We conduct a user study to evaluate our method, the results show a typing speed of 8.63 WPM for the novice group, 9.81 WPM for the potential expert group, and the highest recorded typing speed is 11.13 WPM achieved by a potential expert. Our method is also novice-friendly, and their typing speed increased by 64.38% over a six-day practice. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： virtual environments

来源：评论

学校读者我要写书评

暂无评论

Optimized Breast Lesion Segmentation in Ultrasound Videos Across Varied Resource-Scant Environments 17th

Optimized Breast Lesion Segmentation in Ultrasound Videos A...

引用

17th Asian Conference on computer vision, ACCV 2024

作者： Li, Yunhao Chen, Zibin Yan, Junming Ding, Ziyu Li, Jie Huang, Teng Pei, Xiaoqing Zhang, Zheng Wang, Qiong Pang, Yan Institute of Artificial Intelligence Guangzhou University Guangzhou China Cancer Center Sun Yat-sen University Guangzhou China Moxibustion and Rehabilitation Guangzhou University of Chinese Medicine Guangzhou China Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9789819609659

Medical video segmentation plays a crucial role in clinical diagnosis and therapeutic procedures by enabling dynamic tracking of breast lesions across frames in ultrasound videos, thereby improving segmentation accuracy. However, the existing methods struggle to strike a balance between segmentation accuracy and inference speed, which impedes their real-time deployment in resource-limited medical environments. To overcome these challenges, we introduce a rapid breast lesion segmentation framework named RbS. RbS employs the Stem module and RbSBlock to enhance representations through intra-frame analysis of ultrasound videos. Moreover, we have developed two versions of RbS: RbS-S boasts enhanced segmentation accuracy, while RbS-L ensures faster inference speeds. Experimental evidence indicates that RbS surpasses current leading models in both segmentation efficiency and prediction accuracy, particularly on resource-limited devices. Our contribution significantly propels the progress of developing efficient medical video segmentation frameworks suitable for various medical platforms. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

DualFed: Enjoying both Generalization and Personalization in Federated Learning via Hierachical Representations 24

DualFed: Enjoying both Generalization and Personalization in...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Zhu, Guogang Liu, Xuefeng Niu, Jianwei Tang, Shaojie Wu, Xinghao Zhang, Jiayuan State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Zhongguancun Laboratory Beijing China Department of Management Science and Systems University at Buffalo BuffaloNY United States

ISBN: (纸本)9798400706868

In personalized federated learning (PFL), it is widely recognized that achieving both high model generalization and effective personalization poses a significant challenge due to their conflicting nature. As a result, existing PFL methods can only manage a trade-off between these two objectives. This raises an interesting question: Is it feasible to develop a model capable of achieving both objectives simultaneously? Our paper presents an affirmative answer, and the key lies in the observation that deep models inherently exhibit hierarchical architectures, which produce representations with various levels of generalization and personalization at different stages. A straightforward approach stemming from this observation is to select multiple representations from these layers and combine them to concurrently achieve generalization and personalization. However, the number of candidate representations is commonly huge, which makes this method infeasible due to high computational costs. To address this problem, we propose DualFed, a new method that can directly yield dual representations correspond to generalization and personalization respectively, thereby simplifying the optimization task. Specifically, DualFed inserts a personalized projection network between the encoder and classifier. The pre-projection representations are able to capture generalized information shareable across clients, and the post-projection representations are effective to capture task-specific information on local clients. This design minimizes the mutual interference between generalization and personalization, thereby achieving a win-win situation. Extensive experiments show that DualFed can outperform other FL methods. Code is available at https://***/GuogangZhu/DualFed. © 2024 ACM.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Exploring the Factors of Students' Online Learning Based on Structural Equation Modeling 11

Exploring the Factors of Students' Online Learning Based on ...

引用

11th IEEE International Conference on Teaching, Assessment and Learning for Engineering, TALE 2022

作者： Wan, Han Luo, Hongzhen Zhong, Zihao Yang, Jianlei Beihang University School of Computer Science and Engineering State Key Laboratory of Virtual Reality Technology and Systems Beijing China

ISBN: (纸本)9781665491174

Due to the COVID-19 pandemic, traditional teaching has been migrated online. Different from traditional face-to-face teaching, when students learn online, the online learning platform will generate various data. And these data make it possible for us to analyze students' final academic performance. In this paper, we use structural equation modeling (SEM) to analyze the relationship between students' learning factors. It is found that students' lab scores (LS), exercise scores (LS) and participation in the discussion (PID) have a direct impact on their final programming scores (FPS). This paper also finds that students' assignment submissions have an indirect influence on their final programming scores (FPS) but have a direct effect on lab scores (LS). In addition, students' participation in the discussion (PID) has an indirect influence on assignment submissions (AS) and lab scores (LS). The research in this paper can provide instructional designers with references for instructional design. © 2022 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Radiographic Reports Generation via Retrieval Enhanced Cross-modal Fusion

Radiographic Reports Generation via Retrieval Enhanced Cross...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Hou, Xia Luo, Yifan Song, Wenfeng Guo, Yuting You, Wenzhe Li, Shuai Beijing Information Science and Technology University School of Computer Science Beijing China Beihang University The State Key Laboratory of Virtual Reality Technology and Systems Beijing China Stomatology Center of China-Japan Friendship Hospital Beijing China

ISBN: (纸本)9798350386226

Accurate radiographic reports are crucial for effective clinical decision-making and patient safety, as they directly influence diagnosis and treatment plans. Existing models for radiographic report generation often struggle with integrating medical image and textual report features and addressing data imbalances. To overcome these limitations, we propose an enhanced cross-modal aligned retrieval-driven network (EARnet). Our model incorporates two key innovations: Enhanced Cross-modal Alignment (ECA) module and Case-based Retrieval Augmenter (CRA) module. ECA ensures the effective integration of medical visual and textual data by aligning these modalities. CRA helps mitigate data imbalance by improving the representation of medical information and ensuring a more balanced and comprehensive coverage of both normal and abnormal cases. This dual-module approach significantly improves the coherence and accuracy of the generated medical reports. Evaluation results demonstrate that our EARnet model substantially outperforms existing methods in terms of report quality and accuracy across multiple metrics. Our codes and models are available at https://***/lyf616/EARnet. © 2024 IEEE.

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

Multi-Target Distributed Maximum Correntropy Kalman Filter 24

Multi-Target Distributed Maximum Correntropy Kalman Filter

引用

12th International Conference on Communications and Broadband Networking, ICCBN 2024

作者： Deng, Xingyu Han, Hongyu Zhang, Sheng Xu, Yin College of Computer Science and Visual Computing Virtual Reality Key Laboratory of Sichuan Province Sichuan Normal University Chengdu610066 China The School of Information Science and Technology Southwest Jiaotong University Chengdu611756 China

ISBN: (纸本)9798400717109

Multi-target tracking in sensor networks is a challenging problem, especially in scenarios where sensor observations are limited. Conventional centralized Kalman filters and distributed Kalman filters (DKFs) require each sensor to observe all targets, which is often difficult to achieve in practical distributed applications. With this in mind, and inspired by the promising robustness of the maximum correntropy criterion in non-Gaussian noise environments, this paper proposes a novel multi-target distributed maximum correntropy Kalman filter, named MT-DMCKF. The proposed algorithm can operate effectively in distributed multi-target scenarios and provide accurate and consistent tracking performance even when the number of sensors mounted on targets is limited. Within a single period, the algorithm requires only one exchange of information among sensors, thus reducing communication overhead compared to existing distributed Kalman filters. Simulation experiments validate the effectiveness and robustness of the proposed MT-DMCKF. © 2024 ACM.

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

Generative Cooperative Network for Person Image Generation 6

Generative Cooperative Network for Person Image Generation

引用

6th IEEE International Conference on Universal Village, UV 2022

作者： Liu, Yang Wang, Shuai Wu, Yubin Sheng, Hao Xiong, Zhang Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing China

ISBN: (纸本)9781665474771

Person image generation is to synthesize realistic pedestrian images that follow the same distribution as the given dataset. Previous attempts can be generally categorized into two classes: some methods use human pose information as guidance and others try to generate person images from scratch. The former is to transfer the pose of a source image to a reference pose. The generated person image have the same identity as the source image. The latter takes a random noise from latent space as input, and the real person images are only used as references for the discriminator. While pose-guided person image generation is widely studied, generating-from-scratch methods are also worth exploring because they can synthesize person image with new identity, which is a useful manner of data augmentation. These two types of generating methods have their different advantages and disadvantages, and sometimes they are complementary. In this work, the authors design a Generative Cooperative Network (GCN) to jointly train two types of GANs. The two GANs serve different purposes, and can learn from each other during the cooperative learning procedure. The proposed approach is verified on public datasets, and the results show that our GCN improves the performance of the baseline methods. Comparisons with state-of-the-art methods also prove the effectiveness of the proposed method. © 2022 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Attention-Based Deep Learning Model for Image Desaturation of SDO/AIA

引用

Research in Astronomy and Astrophysics 2023年第8期23卷 92-102页

作者： Xinze Zhang Long Xu Zhixiang Ren Xuexin Yu Jia Li State Key Laboratory of Space Weather National Space Science CenterChinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China Peng Cheng Laboratory Shenzhen 518000China Department of Automation Tsinghua UniversityBeijing 100084China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China

The Atmospheric Imaging Assembly(AIA)onboard the Solar Dynamics Observatory(SDO)captures full-disk solar images in seven extreme ultraviolet wave *** a violent solar flare occurs,incoming photoflux may exceed the threshold of an optical imaging system,resulting in regional saturation/overexposure of ***,the lost signal can be partially retrieved from non-local unsaturated regions of an image according to scattering and diffraction principle,which is well consistent with the attention mechanism in deep ***,an attention augmented convolutional neural network(AANet)is proposed to perform image desaturation of SDO/AIA in this *** is built on a U-Net backbone network with partial convolution and adversarial *** addition,a lightweight attention model,namely criss-cross attention,is embedded between each two convolution layers to enhance the backbone *** results validate the superiority of the proposed AANet beyond state-of-the-arts from both quantitative and qualitative comparisons.

关键词： techniques image processing-Sun atmosphere-Sun flares

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Martian Dust Storm Removal via Disentangled Representation Learning

引用

Research in Astronomy and Astrophysics 2022年第9期22卷 255-266页

作者： Dong Zhao Jia Li Hongyu Li Long Xu State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBejing 100191China State Key Laboratory of Space Weather National Space Science CenterChinese Academy of SciencesBeijing 100190China Peng Cheng Laboratory Shenzhen 518000China

Mars exploration has become a hot spot in recent years and is still advancing rapidly. However, Mars has massive dust storms that may cover many areas of the planet and last for weeks or even months. The local/global dust storms are so influential that they can significantly reduce visibility, and thereby the images captured by the cameras on the Mars rover are degraded severely. This work presents an unsupervised Martian dust storm removal network via disentangled representation learning(DRL). The core idea of the DRL framework is to use the content encoder and dust storm encoder to disentangle the degraded images into content features(on domain-invariant space) and dust storm features(on domain-specific space). The dust storm features carry the full dust storm-relevant prior knowledge from the dust storm images. The “cleaned” content features can be effectively decoded to generate more natural, faithful, clear *** primary advantages of this framework are twofold. First, it is among the first to perform unsupervised training in Martian dust storm removal with a single image, avoiding the synthetic data requirements. Second, the model can implicitly learn the dust storm-relevant prior knowledge from the real-world dust storm data sets, avoiding the design of the complicated handcrafted priors. Extensive experiments demonstrate the DRL framework’s effectiveness and show the promising performance of our network for Martian dust storm removal.

关键词： planets and satellites:atmospheres planets and satellites:general planets and satellites:surfaces

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：