检索结果-内蒙古大学图书馆

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Wenfeng Song Xingliang Jin Shuai Li Chenglizhao Chen Aimin Hao Xia Hou Ning Li Hong Qin Beijing Information Science and Technology University China Zhongguancun Laboratory China State Key Laboratory of Virtual Reality Technology and Systems Beihang University College of Computer Science and Technology China University of Petroleum (East China) Research Unit of Virtual Human and Virtual Surgery (2019RU004) Chinese Academy of Medical Sciences Department of Computer Science Stony Brook University (SUNY at Stony Brook) Stony Brook New York USA

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

computer animation's quest to bridge content and style has historically been a challenging venture, with previous efforts often leaning toward one at the expense of the other. This paper tackles the inherent challenge of content-style duality, ensuring a harmonious fusion where the core narrative of the content is both preserved and elevated through stylistic enhancements. We propose a novel Multi-condition Motion Latent Diffusion Model (MCM-LDM) for Arbitrary Motion Style Transfer (AMST). Our MCM-LDM significantly emphasizes preserving trajectories, recognizing their fundamental role in defining the essence and fluidity of motion content. Our MCM-LDM's cornerstone lies in its ability first to disentangle and then intricately weave together motion's tripartite components: motion trajectory, motion content, and motion style. The critical insight of MCM-LDM is to embed multiple conditions with distinct priorities. The content channel serves as the primary flow, guiding the overall structure and movement, while the trajectory and style channels act as auxiliary components and synchronize with the primary one dynamically. This mechanism ensures that multi-conditions can seamlessly integrate into the main flow, enhancing the overall animation without overshadowing the core content. Empirical evaluations underscore the model's proficiency in achieving fluid and authentic motion style transfers, setting a new benchmark in the realm of computer animation. The source code and model are available at https://***/XingliangJin/***.

关键词： Bridges computer vision Fluids Computational modeling Source coding Animation Diffusion models

来源：评论

学校读者我要写书评

暂无评论

A universal multiple instance learning framework for whole slide image analysis

引用

computers in Biology and Medicine 2024年 178卷 108714-108714页

作者： Zhang, Xueqin Liu, Chang Zhu, Huitong Wang, Tianqi Du, Zunguo Ding, Weihong College of Information Science and Engineering East China University of Science and Technology Shanghai200237 China Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai201112 China Department of Pathology Huashan Hospital Affiliated to Fudan University Shanghai200040 China Department of Urology Huashan Hospital Affiliated to Fudan University Shanghai200040 China

Background: The emergence of digital whole slide image (WSI) has driven the development of computational pathology. However, obtaining patch-level annotations is challenging and time-consuming due to the high resolution of WSI, which limits the applicability of fully supervised methods. We aim to address the challenges related to patch-level annotations. Methods: We propose a universal framework for weakly supervised WSI analysis based on Multiple Instance Learning (MIL). To achieve effective aggregation of instance features, we design a feature aggregation module from multiple dimensions by considering feature distribution, instances correlation and instance-level evaluation. First, we implement instance-level standardization layer and deep projection unit to improve the separation of instances in the feature space. Then, a self-attention mechanism is employed to explore dependencies between instances. Additionally, an instance-level pseudo-label evaluation method is introduced to enhance the available information during the weak supervision process. Finally, a bag-level classifier is used to obtain preliminary WSI classification results. To achieve even more accurate WSI label predictions, we have designed a key instance selection module that strengthens the learning of local features for instances. Combining the results from both modules leads to an improvement in WSI prediction accuracy. Results: Experiments conducted on Camelyon16, TCGA-NSCLC, SICAPv2, PANDA and classical MIL benchmark datasets demonstrate that our proposed method achieves a competitive performance compared to some recent methods, with maximum improvement of 14.6 % in terms of classification accuracy. Conclusion: Our method can improve the classification accuracy of whole slide images in a weakly supervised way, and more accurately detect lesion areas. © 2024 Elsevier Ltd

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Towards Gradient Equalization and Feature Diversification for Long-Tailed Multi-Label Image Recognition

SSRN

引用

SSRN 2023年

作者： Chen, Zhaomin Cui, Quan Zhang, Xiaoqin Deng, Ruoxi Xia, Chaoqun Lu, Shijian The National Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China The College of Computer Science Artificial Intelligence Wenzhou University Wenzhou325035 China The Graduate School of Information Production and Systems Waseda University Fukuoka1698050 Japan School of Computer Science and Engineering Nanyang Technological University 639798 Singapore

Multi-label image recognition with convolutional neural networks has achieved remarkable progress in the past few years. However, most existing multi-label image recognition methods suffer from the long-tailed data distribution problem, \ie, head categories occupy most training samples, while tailed classes have few samples. This work firstly studies the influence of long-tailed data distribution on existing multi-label image recognition methods. Based on this, two crucial issues of the existing methods are identified: 1) severe gradient imbalance between head and tailed categories, even though re-balancing strategies are adopted;2) the lack of diversity of tail category training samples. To tackle the first issue, this paper proposes a group sampling strategy to create group-wise balanced data distribution. Meanwhile, a dynamic gradient balancing loss is proposed to equalize the gradient for all categories. To tackle the second issue, this paper proposes a diversity enhancement module to fuse the information across all categories, preventing the network from overfitting tail classes. Furthermore, it also balances the gradient, promoting the discriminability of learned classifiers. Our method significantly outperforms the baseline method and achieves competitive performance with state-of-the-art methods on VOC-LT and COCO-LT datasets. Extensive ablation studies are conducted to verify the effectiveness of the essential proposals. © 2023, The Authors. All rights reserved.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Beyond Model Scale Limits: End-Edge-Cloud Federated Learning with Self-Rectified Knowledge Agglomeration

arXiv

引用

arXiv 2024年

作者： Wu, Zhiyuan Sun, Sheng Wang, Yuwei Liu, Min Xu, Ke Pan, Quyang Gao, Bo Wen, Tian The State Key Lab of Processers Institute of Computing Technology Chinese Academy of Sciences Beijing China The University of Chinese Academy of Sciences Beijing China The Zhongguancun Laboratory Beijing China The Department of Computer Science and Technology Tsinghua University Beijing China The School of Computer Science and Technology The Engineering Research Center of Network Management Technology for High-Speed Railway of Ministry of Education Beijing Jiaotong University Beijing China

The rise of End-Edge-Cloud Collaboration (EECC) offers a promising paradigm for Artificial Intelligence (AI) model training across end devices, edge servers, and cloud data centers, providing enhanced reliability and reduced latency. Hierarchical Federated Learning (HFL) can benefit from this paradigm by enabling multi-tier model aggregation across distributed computing nodes. However, the potential of HFL is significantly constrained by the inherent heterogeneity and dynamic characteristics of EECC environments. Specifically, the uniform model structure bounded by the least powerful end device across all computing nodes imposes a performance bottleneck. Meanwhile, coupled heterogeneity in data distributions and resource capabilities across tiers disrupts hierarchical knowledge transfer, leading to biased updates and degraded performance. Furthermore, the mobility and fluctuating connectivity of computing nodes in EECC environments introduce complexities in dynamic node migration, further compromising the robustness of the training process. To address multiple challenges within a unified framework, we propose End-Edge-Cloud Federated Learning with Self-Rectified Knowledge Agglomeration (FedEEC), which is a novel EECC-empowered FL framework that allows the trained models from end, edge, to cloud to grow larger in size and stronger in generalization ability. FedEEC introduces two key innovations: (1) Bridge Sample Based Online Distillation Protocol (BSBODP), which enables knowledge transfer between neighboring nodes through generated bridge samples, and (2) Self-Knowledge Rectification (SKR), which refines the transferred knowledge to prevent suboptimal cloud model optimization. The proposed framework effectively handles both cross-tier resource heterogeneity and effective knowledge transfer between neighboring nodes, while satisfying the migration-resilient requirements of EECC. Extensive experiments on three datasets demonstrate that FedEEC achieves significantly hi

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

HERO: On the chaos when PATH meets modules

arXiv

引用

arXiv 2021年

作者： Wang, Ying Qiao, Liang Xu, Chang Liu, Yepang Cheung, Shing-Chi Meng, Na Yu, Hai Zhu, Zhiliang Software College Northeastern University China State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University China Southern University of Science and Technology China Hong Kong University of Science and Technology China Virginia Tech United States

Ever since its first release in 2009, the Go programming language (Golang) has been well received by software communities. A major reason for its success is the powerful support of library-based development, where a Golang project can be conveniently built on top of other projects by referencing them as libraries. As Golang evolves, it recommends the use of a new library-referencing mode to overcome the limitations of the original one. While these two library modes are incompatible, both are supported by the Golang ecosystem. The heterogeneous use of library-referencing modes across Golang projects has caused numerous dependency management (DM) issues, incurring reference inconsistencies and even build failures. Motivated by the problem, we conducted an empirical study to characterize the DM issues, understand their root causes, and examine their fixing solutions. Based on our findings, we developed HERO, an automated technique to detect DM issues and suggest proper fixing solutions. We applied HERO to 19,000 popular Golang projects. The results showed that HERO achieved a high detection rate of 98.5% on a DM issue benchmark and found 2,422 new DM issues in 2,356 popular Golang projects. We reported 280 issues, among which 181 (64.6%) issues have been confirmed, and 160 of them (88.4%) have been fixed or are under fixing. Almost all the fixes have adopted our fixing suggestions. Copyright © 2021, The Authors. All rights reserved.

关键词： Ecosystems

来源：评论

学校读者我要写书评

暂无评论

Achieving Distributed and Privacy-Preserving Cross-Chain Transactions in Account-Model Blockchain Systems

Achieving Distributed and Privacy-Preserving Cross-Chain Tra...

引用

Metaverse Computing, Networking and Applications (MetaCom), IEEE International Conference on

作者： Chuan Zhang Weijie Wang Weiting Zhang Jiangtian Nie Jinwen Liang Liehuang Zhu School of Cyberspace Science and Technology Beijing Institute of Technology Beijing China Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies Guangdong China School of Computer Science & Technology Beijing Institute of Technology Beijing China School of Electronic and Information Engineering Beijing Jiaotong University Beijing China School of Computer Science and Engineering Nanyang Technological University Singapore Department of Computing Hong Kong Polytechnic University China

Cross-Chain is an emerging technology to enable transaction circulation across different blockchain systems, breaking down transaction isolation among decentralized ecosystems. Existing cross-chain solutions are often constructed based on centralized trusted third parties, which introduce additional threats to users’ identities due to potentially compromised risks on the centralized third parties. To exclude the single-point compromised risk in centralized systems, this paper focuses on a fully decentralized scenario and develops a distributed cross-chain transaction scheme, which enables cross-chain transaction exchanges while ensuring the unlinkability between payees and payers. Specifically, we first propose a cross-chain cryptocurrency exchange scheme by leveraging Ethereum’s smart contracts, which achieves transaction exchanges in decentralized settings. Then, we leverage zero-knowledge succinct non-interactive argument of knowledge (i.e., zk-SNARKs) to explore a privacy-preserving method for cross-chain transactions in account-model blockchain systems, such that the unlinkability between payees and payers and the privacy of cross-chain participants can be guaranteed. Security analysis and experimental evaluations demonstrate that the proposed scheme achieves the security goal at acceptable costs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic Graph Transformer with Correlated Spatial-Temporal Positional Encoding

arXiv

引用

arXiv 2024年

作者： Wang, Zhe Zhou, Sheng Chen, Jiawei Zhang, Zhen Hu, Binbin Feng, Yan Chen, Chun Wang, Can Zhejiang University College of Computer Science Hangzhou China National University of Singapore Singapore Zhejiang University School of Software Technology Ningbo China Ant Group Hangzhou China Zhejiang University The State Key Laboratory of Blockchain and Data Security Hangzhou China

Learning effective representations for Continuous-Time Dynamic Graphs (CTDGs) has garnered significant research interest, largely due to its powerful capabilities in modeling complex interactions between nodes. A fundamental and crucial requirement for representation learning in CTDGs is the appropriate estimation and preservation of proximity. However, due to the sparse and evolving characteristics of CTDGs, the spatial-temporal properties inherent in high-order proximity remain largely unexplored. Despite its importance, this property presents significant challenges due to the computationally intensive nature of personalized interaction intensity estimation and the dynamic attributes of CTDGs. To this end, we propose a novel Correlated Spatial-Temporal Positional encoding that incorporates a parameter-free personalized interaction intensity estimation under the weak assumption of the Poisson Point Process. Building on this, we introduce the Dynamic Graph Transformer with Correlated Spatial-Temporal Positional Encoding (CorDGT), which efficiently retains the evolving spatial-temporal high-order proximity for effective node representation learning in CTDGs. Extensive experiments on seven small and two large-scale datasets demonstrate the superior performance and scalability of the proposed CorDGT. The code is available at: https://***/wangz3066/CorDGT. © 2024, CC BY.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

SPT-Code: Sequence-to-Sequence Pre-Training for Learning Source Code Representations

arXiv

引用

arXiv 2022年

作者： Niu, Changan Li, Chuanyi Ng, Vincent Ge, Jidong Huang, Liguo Luo, Bin State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Human Language Technology Research Institute University of Texas at Dallas RichardsonTX United States Dept. of Computer Science Southern Methodist University DallasTX United States

Recent years have seen the successful application of large pre-trained models to code representation learning, resulting in substantial improvements on many code-related downstream tasks. But there are issues surrounding their application to SE tasks. First, the majority of the pre-trained models focus on pre-training only the encoder of the Transformer. For generation tasks that are addressed using models with the encoder-decoder architecture, however, there is no reason why the decoder should be left out during pre-training. Second, many existing pre-trained models, including state-of-the-art models such as T5-learning, simply reuse the pre-training tasks designed for natural languages. Moreover, to learn the natural language description of source code needed eventually for code-related tasks such as code summarization, existing pre-training tasks require a bilingual corpus composed of source code and the associated natural language description, which severely limits the amount of data for pre-training. To this end, we propose SPT-Code, a sequence-to-sequence pre-trained model for source code. In order to pre-train SPT-Code in a sequence-to-sequence manner and address the aforementioned weaknesses associated with existing pre-training tasks, we introduce three pre-training tasks that are specifically designed to enable SPT-Code to learn knowledge of source code, the corresponding code structure, as well as a natural language description of the code without relying on any bilingual corpus, and eventually exploit these three sources of information when it is applied to downstream tasks. Experimental results demonstrate that SPT-Code achieves state-of-the-art performance on five code-related downstream tasks after fine-tuning. © 2022, CC BY.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Bringing Efficient Synthetic Transmit Aperture Imaging to Consumer technology: IoT-Enabled Portable Ultrasound Systems

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Wang, Wenping He, Qiong Peng, Fan Feng, Ziliang Sichuan University National Key Laboratory of Fundamental Science on Synthetic Vision Chengdu610065 China Tsinghua University School of Medicine Department of Biomedical Engineering Beijing100084 China Chengdu University of Technology College of Computer Science and Cyber Security Pilot Software College Chengdu610059 China

This work advances consumer technology in holographic visualization and medical imaging by introducing an effective synthetic transmit aperture (STA) imaging technique for Internet of Things (IoT)-enabled portable high-frequency ultrasound (HFUS) equipment. The technique drastically lowers data size and computing requirements while preserving good imaging performance by using sign coherence factor (SCF) compounding and phase rotation beamforming using in-phase/quadrature (IQ) data. Real-time deployment in resource-constrained IoT-based systems is made possible by experimental results that demonstrate a 42% decrease in computing complexity when compared to traditional STA-IQ imaging. For effective processing, baseband IQ data is subjected to intricate demodulation, downsampling, and phase correction, which is in line with contemporary consumer technology-driven healthcare solutions. Even at low sampling rates, SCF improves contrast performance, maintaining a lateral resolution of 150 lm and providing a contrast-to-noise ratio (CNR) enhancement of 3.5 dB, which is equivalent to typical STA-IQ methods. Its enhanced image quality is further supported by simulations and in-vivo studies that show a peak signal-to-noise ratio (PSNR) enhancement of 2.8 dB. Furthermore, by combining this method with real-time holographic ultrasound imaging, high-fidelity 3D reconstructions are made possible, enhancing depth accuracy and spatial coherence while reducing phase distortion aberrations by 30%. These improvements enable real-time holographic imaging for telemedicine and preclinical applications, as well as IoT-based remote diagnostics. Thus, the suggested approach offers a low-power, high-accuracy imaging solution that promotes innovation in holographic display and medical imaging technologies while also advancing consumer healthcare diagnostics. © 1975-2011 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Recognition of Unknown Objects for Open-World Object Detection

arXiv

引用

arXiv 2023年

作者： Fang, Ruohuan Pang, Guansong Zhou, Lei Bai, Xiao Zheng, Jin School of Computer Science and Engineering State Key Laboratory of Software Development Environment Jiangxi Research Institute Beihang University China School of Computing and Information Systems Singapore Management University Singapore School of Computer Science and Artificial Intelligence Wuhan University of Technology China

Open-World Object Detection (OWOD) extends object detection problem to a realistic and dynamic scenario, where a detection model is required to be capable of detecting both known and unknown objects and incrementally learning newly introduced knowledge. Current OWOD models, such as ORE and OW-DETR, focus on pseudo-labeling regions with high objectness scores as unknowns, whose performance relies heavily on the supervision of known objects. While they can detect the unknowns that exhibit similar features to the known objects, they suffer from a severe label bias problem that they tend to detect all regions (including unknown object regions) that are dissimilar to the known objects as part of the background. To eliminate the label bias, this paper proposes a novel approach that learns an unsupervised discriminative model to recognize true unknown objects from raw pseudo labels generated by unsupervised region proposal methods. The resulting model can be further refined by a classification-free self-training method which iteratively extends pseudo unknown objects to the unlabeled regions. Experimental results show that our method 1) significantly outperforms the prior SOTA in detecting unknown objects while maintaining competitive performance of detecting known object classes on the MS COCO dataset, and 2) achieves better generalization ability on the LVIS and Objects365 datasets. Code is available at https://***/frh23333/mepu-owod. Copyright © 2023, The Authors. All rights reserved.

关键词： Object detection

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：