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

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

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 Chengdu611731 China School of Computer Science Chengdu University of Information Technology Chengdu610225 China Shanghai Key Lab of Intelligent Information Processing School of CS Fudan University Shanghai200433 China School of Sensing Science and Engineering Shanghai Jiao Tong University Shanghai200240 China School of Mechanical and Manufacturing Engineering University of New South Wales Sydney2052 Australia School of Electronics and Computer Science University of Southampton SouthamptonSO17 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： Federated learning

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

Anomize: Better Open Vocabulary Video Anomaly Detection

arXiv

引用

arXiv 2025年

作者： Li, Fei Liu, Wenxuan Chen, Jingjing Zhang, Ruixu Wang, Yuran Zhong, Xian Wang, Zheng National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China State Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China Hubei Key Laboratory of Transportation Internet of Things Wuhan University of Technology China

Open Vocabulary Video Anomaly Detection (OVVAD) seeks to detect and classify both base and novel anomalies. However, existing methods face two specific challenges related to novel anomalies. The first challenge is detection ambiguity, where the model struggles to assign accurate anomaly scores to unfamiliar anomalies. The second challenge is categorization confusion, where novel anomalies are often misclassified as visually similar base instances. To address these challenges, we explore supplementary information from multiple sources to mitigate detection ambiguity by leveraging multiple levels of visual data alongside matching textual information. Furthermore, we propose incorporating label relations to guide the encoding of new labels, thereby improving alignment between novel videos and their corresponding labels, which helps reduce categorization confusion. The resulting Anomize framework effectively tackles these issues, achieving superior performance on UCF-CRIME and XD-VIOLENCE datasets, demonstrating its effectiveness in OVVAD. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AN EMPIRICAL ANALYSIS OF UNCERTAINTY IN LARGE LANGUAGE MODEL EVALUATIONS

arXiv

引用

arXiv 2025年

作者： Xie, Qiujie Li, Qingqiu Yu, Zhuohao Zhang, Yuejie Zhang, Yue Yang, Linyi Zhejiang University China School of Engineering Westlake University China School of Computer Science Shanghai Key Lab of Intelligent Information Processing Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University China Peking University China Westlake Institute for Advanced Study China University College London United Kingdom Huawei Noah’s Ark Lab Hong Kong

As LLM-as-a-Judge emerges as a new paradigm for assessing large language models (LLMs), concerns have been raised regarding the alignment, bias, and stability of LLM evaluators. While substantial work has focused on alignment and bias, little research has concentrated on the stability of LLM evaluators. In this paper, we conduct extensive experiments involving 9 widely used LLM evaluators across 2 different evaluation settings to investigate the uncertainty in model-based LLM evaluations. We pinpoint that LLM evaluators exhibit varying uncertainty based on model families and sizes. With careful comparative analyses, we find that employing special prompting strategies, whether during inference or post-training, can alleviate evaluation uncertainty to some extent. By utilizing uncertainty to enhance LLM’s reliability and detection capability in Out-Of-Distribution (OOD) data, we further fine-tune an uncertainty-aware LLM evaluator named ConfiLM using a human-annotated fine-tuning set and assess ConfiLM’s OOD evaluation ability on a manually designed test set sourced from the 2024 Olympics. Experimental results demonstrate that incorporating uncertainty as additional information during the fine-tuning phase can largely improve the model’s evaluation performance in OOD scenarios. The code and data are released at: https://***/hasakiXie123/LLM-Evaluator-Uncertainty. © 2025, CC BY-NC-SA.

关键词： Digital elevation model

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：