检索结果-内蒙古大学图书馆

17th Asian Conference on Computer Vision, ACCV 2024

作者： Huang, Xianliang Chen, Shuhang Zhong, Zhizhou Gou, Jiajie Guan, Jihong Zhou, Shuigeng Shanghai Key Lab of Intelligent Information Processing and School of Computer Science Fudan University Shanghai China School of Computer Science and Technology Tongji University Shanghai China

ISBN: (纸本)9789819609710

Recent developments in Neural Radiance Fields (NeRF) have showcased notable progress in the synthesis of novel views. Nevertheless, there is limited research on inpainting 3D scenes using implicit representations. Traditional approaches utilizing 3D networks for direct 3D inpainting often falter in high-resolution settings, mainly due to GPU memory constraints. This paper introduces Hi-NeRF, an innovative 3D inpainting approach designed to remove arbitrary 3D objects by hybridizing 2D inpainting strategies with NeRF techniques. Recognizing that prevailing 2D inpainting methods often fail to grasp the 3D geometric intricacies of scenes, we leverage the unique capability of NeRF in capturing these structures. Additionally, we propose a multi-view perceptual loss (MVPL) to harness multi-view data, ensuring that 2D inpainting and implicit 3D representations can mutually compensate for each other. Furthermore, we refine the output from the Segment Anything Model (SAM) using image dilation to produce accurate multi-view masks. To finalize the process, we employ Instant-NGP to efficiently retrieve 3D-consistent scenes from 3D-consistent inpainted images. As there is no multi-view 3D scene datasets with corresponding masks, we construct both real-world and synthetic scenes for the multi-view 3D scene inpainting task, which serves as a benchmark dataset. Experimental results on both indoor and outdoor scenes highlight the superiority of our approach over the existing 2D inpainting methods and NeRF-based baselines. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

RBDQ: A Reliable LLM-based Text-to-SQL System for Business data Queries 25

RBDQ: A Reliable LLM-based Text-to-SQL System for Business D...

引用

Companion Proceedings of the ACM on Web Conference 2025

作者： Fenglin Bi Dongdong Cao Zhiyu Wang Yang Chen Fangliang Zhao Tao Hu Zhi Li Yanbin Zhang Wei Wang School of Data Science and Engineering East China Normal University Shanghai China ByteDance Inc Shanghai China School of Computer Science Fudan University Shanghai China and Shanghai Key Lab of Intelligent Information Processing Shanghai China

ISBN: (纸本)9798400713316

Using large language models (LLMs) to convert natural language (NL) into SQL simplifies data access for users by allowing them to use everyday language. However, business departments often distrust LLM-based text-to-SQL systems due to the probabilistic nature of SQL generation, which can result in incorrect but executable SQL queries caused by model hallucinations. This leads to significant concerns regarding the accuracy and reliability of the queried data. In this paper, we present RBDQ, a novel LLM-based text-to-SQL system designed to address the unique challenges of business data queries. RBDQ innovatively introduces the Hierarchical Metrics Query Method and integrates advanced Retrieval-Augmented Generation (RAG) methods along with a self-reflection mechanism to tackle these challenges. RBDQ effectively meets the requirements of business metric queries in real-world scenarios. Currently implemented in the Quality Assurance department at ByteDance, RBDQ has significantly improved operational efficiency and query flexibility. Our experiments demonstrate the system's effectiveness, achieving an Execution Accuracy of 96.20%.

关键词： business data queries

来源：评论

学校读者我要写书评

暂无评论

Boosting semi-supervised federated learning by effectively exploiting server-side knowledge and client-side unconfident samples

引用

Neural Networks 2025年 188卷 107440页

作者： Liu, Hongquan Mi, Yuxi Tang, Yateng Guan, Jihong Zhou, Shuigeng Shanghai Key Lab of Intelligent Information Processing and School of Computer Science Fudan University Shanghai China School of Computer Science and Technology Tongji University Shanghai China Wechat Tencent Inc. Shenzhen China

Semi-supervised federated learning (SSFL) has emerged as a promising paradigm to reduce the need for fully labeled data in training federated learning (FL) models. This paper focuses on the label-at-server scenario, where clients’ data are entirely unlabeled and the server possesses only a limited amount of labeled data. In this setting, the non-independent and identically distributed (non-IID) local data and the incorrect pseudo-labels will possibly introduce bias into the model during local training. Prior works try to alleviate the bias by fine-tuning the global model with clean labeled data, ignoring explicitly leveraging server-side knowledge to guide local training. Additionally, existing methods typically discard samples with unconfident pseudo-labels, resulting in many samples being not used, consequently suboptimal performance and slow convergence. This paper introduces a novel method to enhance SSFL performance by effectively exploiting server-side clean knowledge and client-side unconfident samples. Specifically, we propose a representation alignment module that mitigates the influence of non-IID data by aligning local features with the class proxies of the server labeled data. Furthermore, we employ a shrink loss to reduce the risk associated with unreliable pseudo-labels, ensuring the exploitation of valuable information contained in the entire unlabeled dataset. Extensive experiments on five benchmark datasets under various settings demonstrate the effectiveness and generality of the proposed method, which not only outperforms existing methods but also reduces the communication cost required to achieve the target performance. © 2025 Elsevier Ltd

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Automated Clinical Summary Generation via Integrating Structured and Unstructured data 12th

Automated Clinical Summary Generation via Integrating Struct...

引用

12th CCF Conference on Bigdata, Bigdata 2024

作者： Fu, Jiaojiao Yang, Bowen Guo, Yi Zhou, Yangfan Wang, Xin School of Information Science and Engineering East China University of Science and Technology Shanghai China Shanghai Key Lab. of Intelligent Information Processing Fudan University Shanghai China School of Computer Science Fudan University Shanghai China

ISBN: (纸本)9789819610235

Automatically generating clinical texts can significantly reduce the time physicians spend on clinical data recording, which is particularly important for developing countries where physicians are extremely busy due to a severe shortage. This work automatically generates discharge summaries as a case to explore the methods and feasibilities of automatic clinical text summarization. Existing work typically uses either structured or unstructured data alone to generate discharge summaries. However, the content generated often has issues such as being overly verbose, lacking focus, or omitting significant information, especially key indicators and medications. This work innovatively proposes a data integration-based clinical text generation approach, using content generated from unstructured clinical data as the basis and supplementing it with text generated from structured clinical data. This study utilizes advanced natural language processing algorithms and models to create clinical texts. It addresses the challenges of lacking datasets suitable for fine-tuning pre-trained models and combining the advantages rather than the disadvantages of both types to produce discharge summaries. Experimental results show that the structured supplementation approach can effectively improve the generation of clinical texts. This work demonstrates that clinical texts generated using existing natural language processing technologies still do not meet the demands of medical practice, pointing out the need to develop further text generation technologies tailored to the characteristics of clinical data. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： data assimilation

来源：评论

学校读者我要写书评

暂无评论

Single-cell omics: experimental workflow, data analyses and applications

引用

science China(Life sciences) 2025年第1期68卷 5-102页

作者： Fengying Sun Haoyan Li Dongqing Sun Shaliu Fu Lei Gu Xin Shao Qinqin Wang Xin Dong Bin Duan Feiyang Xing Jun Wu Minmin Xiao Fangqing Zhao Jing-Dong J.Han Qi Liu Xiaohui Fan Chen Li Chenfei Wang Tieliu Shi Department of Clinical Laboratory the Affiliated Wuhu Hospital of East China Normal University(The Second People’s Hospital of Wuhu City)Wuhu 241000China Pharmaceutical Informatics Institute College of Pharmaceutical SciencesZhejiang UniversityHangzhou 310058China Key Laboratory of Spine and Spinal Cord Injury Repair and Regeneration(Tongji University) Ministry of EducationOrthopaedic DepartmentTongji HospitalBioinformatics DepartmentSchool of Life Sciences and TechnologyTongji UniversityShanghai 200082China Frontier Science Center for Stem Cells School of Life Sciences and TechnologyTongji UniversityShanghai 200092China Translational Medical Center for Stem Cell Therapy and Institute for Regenerative Medicine Shanghai East HospitalBioinformatics DepartmentSchool of Life Sciences and TechnologyTongji UniversityShanghai 200082China Research Institute of Intelligent Computing Zhejiang LabHangzhou 311121China Shanghai Research Institute for Intelligent Autonomous Systems Shanghai 201210China Center for Single-cell Omics School of Public HealthShanghai Jiao Tong University School of MedicineShanghai 200025China National Key Laboratory of Chinese Medicine Modernization Innovation Center of Yangtze River DeltaZhejiang UniversityJiaxing 314103China Center for Bioinformatics and Computational Biology Shanghai Key Laboratory of Regulatory Biologythe Institute of Biomedical Sciences and School of Life SciencesEast China Normal UniversityShanghai 200241China Beijing Institutes of Life Science Chinese Academy of SciencesBeijing 100101China Peking-Tsinghua Center for Life Sciences Academy for Advanced Interdisciplinary StudiesCenter for Quantitative Biology(CQB)Peking UniversityBeijing 100871China Zhejiang Key Laboratory of Precision Diagnosis and Therapy for Major Gynecological Diseases Women’s HospitalZhejiang University School of MedicineHangzhou 310006China Key Laboratory of Advanced Theory and Application in Statistics and Data Science-MOE School of StatisticsEast China Normal U

Cells are the fundamental units of biological systems and exhibit unique development trajectories and molecular *** exploration of how the genomes orchestrate the formation and maintenance of each cell,and control the cellular phenotypes of various organismsis,is both captivating and *** the inception of the first single-cell RNA technology,technologies related to single-cell sequencing have experienced rapid advancements in recent *** technologies have expanded horizontally to include single-cell genome,epigenome,proteome,and metabolome,while vertically,they have progressed to integrate multiple omics data and incorporate additional information such as spatial scRNA-seq and CRISPR ***-cell omics represent a groundbreaking advancement in the biomedical field,offering profound insights into the understanding of complex diseases,including ***,we comprehensively summarize recent advances in single-cell omics technologies,with a specific focus on the methodology *** overview aims to guide researchers in selecting appropriate methods for single-cell sequencing and related data analysis.

关键词： single-cell sequencing genome epigenome proteomics metabolomics multimodal spatial transcriptomics CRISPR screening

来源：评论

学校读者我要写书评

暂无评论

FediLive: A Framework for Collecting and Preprocessing Snapshots of Decentralized Online Social Networks 25

FediLive: A Framework for Collecting and Preprocessing Snaps...

引用

Companion Proceedings of the ACM on Web Conference 2025

作者： Shaojie Min Shaobin Wang Yaxiao Luo Min Gao Qingyuan Gong Yu Xiao Yang Chen Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China Research Institute of Intelligent Complex Systems Fudan University Shanghai China Department of Information and Communications Engineering Aalto University Espoo Finland

ISBN: (纸本)9798400713316

Decentralized online social networks such as Mastodon have emerged quickly during the past years, and offer unique opportunities to investigate user behavior, moderation strategies, and community evolution. However, their decentralized nature imposes challenges for data collection and preprocessing, particularly for obtaining a real-time snapshot in a timely manner. This paper introduces FediLive, a framework designed to rapidly collect and preprocess the live feeds from Mastodon, generate a comprehensive snapshot in real-time, including user-generated contents, interaction networks, and users' demographic attributes. Such a snapshot could further be leveraged for data analysis from different angles, leading to a deeper understanding of user activities on Mastodon. Using FediLive, we collected a 13-day snapshot of Mastodon, covering the publicly-visible activities of all Mastodon users. Our study demonstrates the usefulness of FediLive, and reveals its potential in facilitating data-driven analysis for decentralized online social networks.

关键词： decentralized online social networks

来源：评论

学校读者我要写书评

暂无评论

DFE: Deep Flow Embedding for Robust Network Traffic Classification

引用

IEEE Transactions on Network science and Engineering 2025年第3期12卷 1597-1612页

作者： Wang, Zhijiong Zhang, Anguo Li, Hung Chun Yin, Yadong Chen, Wei Lam, Chan Tong Mak, Peng Un Vai, Mang I. Gao, Yueming Pun, Sio Hang Zhuhai UM Science and Technology Research Institute Lingyange Semiconductor Incorporated Joint Laboratory Zhuhai519031 China Lingyange Semiconductor Inc. Zhuhai519030 China University of Macau State Key Laboratory of Analog and Mixed-Signal VLSI Institute of Microelectronics 999078 China Fuzhou University School of Physics and Information Engineering Fuzhou350108 China Fudan University Center for Intelligent Medical Electronics School of Information Science and Technology Human Phenome Institute Shanghai200437 China Fudan University Human Phenome Institute Shanghai200437 China Macau Polytechnic University Faculty of Applied Sciences 999078 China University of Macau Department of Electrical and Computer Engineering Faculty of Science and Technology 999078 China Fuzhou University Key Lab of Medical Instrumentation and Pharmaceutical Technology of Fujian Province Fuzhou350108 China

People's increasing demand for high-quality network services has prompted the continuous attention and development of network traffic classification (NTC). In recent years, deep flow inspection (DFI) is considered to be the most effective and promising method to solve the NTC. However, DFI still cannot effectively address the problem of changes in flow characteristics of complex packet flows and the discovery of new traffic categories. In this paper, we propose a metric learning based deep learning solution with feature compressor, named deep flow embedding (DFE). The feature compressor is used to compress the feature information transmitted layer by layer in DL backbone while maintaining the computational accuracy, so that the backbone can remove as much noise, redundancy, and other irrelevant information from the input data as possible, and achieve more robust feature extraction of network traffic flow. The deep learning (DL) backbone generates an embedding vector for each network packet flow. Then the embedding vector is compared with the vector template preset for each traffic type in the template library to determine the category of the packet flow. Experimental results verify that our method is more effective than the traditional DFI methods in overcoming the problems of flow characteristics variation and new category discovery. © 2013 IEEE.

关键词： Network embeddings

来源：评论

学校读者我要写书评

暂无评论

DeTrack: In-model Latent Denoising Learning for Visual Object Tracking

arXiv

引用

arXiv 2025年

作者： Zhou, Xinyu Li, Jinglun Hong, Lingyi Jiang, Kaixun Guo, Pinxue Ge, Weifeng Zhang, Wenqiang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China Shanghai Engineering Research Center of AI & Robotics Academy for Engineering and Technology Fudan University Shanghai China

Previous visual object tracking methods employ image-feature regression models or coordinate autoregression models for bounding box prediction. Image-feature regression methods heavily depend on matching results and do not utilize positional prior, while the autoregressive approach can only be trained using bounding boxes available in the training set, potentially resulting in suboptimal performance during testing with unseen data. Inspired by the diffusion model, denoising learning enhances the model's robustness to unseen data. Therefore, We introduce noise to bounding boxes, generating noisy boxes for training, thus enhancing model robustness on testing data. We propose a new paradigm to formulate the visual object tracking problem as a denoising learning process. However, tracking algorithms are usually asked to run in real-time, directly applying the diffusion model to object tracking would severely impair tracking speed. Therefore, we decompose the denoising learning process into every denoising block within a model, not by running the model multiple times, and thus we summarize the proposed paradigm as an in-model latent denoising learning process. Specifically, we propose a denoising Vision Transformer (ViT), which is composed of multiple denoising blocks. In the denoising block, template and search embeddings are projected into every denoising block as conditions. A denoising block is responsible for removing the noise in a predicted bounding box, and multiple stacked denoising blocks cooperate to accomplish the whole denoising process. Subsequently, we utilize image features and trajectory information to refine the denoised bounding box. Besides, we also utilize trajectory memory and visual memory to improve tracking stability. Experimental results validate the effectiveness of our approach, achieving competitive performance on several challenging datasets. The proposed in-model latent denoising tracker achieve real-time speed, rendering denoising learning

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

Video Action Recognition Method Based on Personalized Federated Learning and Spatiotemporal Features

引用

Computers, Materials and Continua 2025年第3期83卷 4961-4978页

作者： Wu, Rongsen Xu, Jie Zhang, Yuhang Zhao, Changming Xie, Yiweng Wu, Zelei Li, Yunji Guo, Jinhong Tang, Shiyang School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu 611731 China School of Computer Science Chengdu University of Information Technology Chengdu 610225 China Shanghai Key Lab of Intelligent Information Processing School of CS Fudan University Shanghai 200433 China School of Sensing Science and Engineering Shanghai Jiao Tong University Shanghai 200240 China School of Mechanical and Manufacturing Engineering University of New South Wales Sydney 2052 Australia School of Electronics and Computer Science University of Southampton Southampton SO17 1BJ United Kingdom

With the rapid development of artificial intelligence and Internet of Things technologies, video action recognition technology is widely applied in various scenarios, such as personal life and industrial production. However, while enjoying the convenience brought by this technology, it is crucial to effectively protect the privacy of users’ video data. Therefore, this paper proposes a video action recognition method based on personalized federated learning and spatiotemporal features. Under the framework of federated learning, a video action recognition method leveraging spatiotemporal features is designed. For the local spatiotemporal features of the video, a new differential information extraction scheme is proposed to extract differential features with a single RGB frame as the center, and a spatial-temporal module based on local information is designed to improve the effectiveness of local feature extraction;for the global temporal features, a method of extracting action rhythm features using differential technology is proposed, and a time module based on global information is designed. Different translational strides are used in the module to obtain bidirectional differential features under different action rhythms. Additionally, to address user data privacy issues, the method divides model parameters into local private parameters and public parameters based on the structure of the video action recognition model. This approach enhances model training performance and ensures the security of video data. The experimental results show that under personalized federated learning conditions, an average accuracy of 97.792% was achieved on the UCF-101 dataset, which is non-independent and identically distributed (non-IID). This research provides technical support for privacy protection in video action recognition. Copyright © 2025 The Authors.

关键词： data privacy personalized federated learning spatiotemporal features Video action recognition

来源：评论

学校读者我要写书评

暂无评论

EnsembleFollower: A Hybrid Car-Following Framework Based on Hierarchical Planning and Reinforcement Learning

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Han, Xu Chen, Xianda Zhu, Meixin Cai, Pinlong Zhou, Jianshan Chu, Xiaowen Data Science and Analytics Thrust Information Hub Guangzhou China Intelligent Transportation Thrust Systems Hub Guangzhou China Sensing and Computation for Ubiquitous Internet of Things Guangdong Provincial Key Lab of Integrated Communication China Southeast University School of Transportation Nanjing211189 China Shanghai Artificial Intelligence Laboratory Shanghai China Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems & Safety Control State Key Laboratory of Intelligent Transportation Systems China Beihang University School of Transportation Science and Engineering Beijing100191 China

Car-following models have made significant contributions to our understanding of longitudinal driving behavior. However, they often exhibit limited accuracy and flexibility, as they cannot fully capture the complexity inherent in car-following processes, or may struggle in unseen scenarios due to their reliance on confined driving skills present in training data. It is worth noting that each car-following model possesses its own strengths and weaknesses depending on specific driving scenarios. Therefore, we propose EnsembleFollower, a closed-loop hierarchical planning framework for achieving human-like autonomous car-following. The EnsembleFollower framework involves a high-level Reinforcement Learning-based agent responsible for judiciously managing multiple low-level models (such as intelligent Driver Model and Gipps model) according to the current state, either by selecting an appropriate car-following model to perform an action or by allocating different weights across all primitive models. Moreover, we propose a jerk-constrained kinematic model for more convincing microscopic traffic simulations. We evaluate the proposed method based on real-world driving data from the HighD dataset. The experimental results illustrate that EnsembleFollower yields an improved accuracy of human-like behavior and achieves effectiveness in combining hybrid models, demonstrating that our proposed framework can handle diverse driving conditions by leveraging the strengths of various car-following models. © 1967-2012 IEEE.

关键词： Deep reinforcement learning

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：