检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Huang, Jing Wen, Hao Zhou, Tianyi Lin, Haozhe Lai, Yu-Kun Li, Kun College of Intelligence and Computing Tianjin University Tianjin300350 China Beijing National Research Center for Information Science and Technology Tsinghua University Beijing10084 China School of Computer Science and Informatics Cardiff University CardiffCF24 4AG United Kingdom

This paper aims to reconstruct hundreds of people's 3D poses, shapes, and locations from a single image with unknown camera parameters. Due to the small and highly varying 2D human scales, depth ambiguity, and perspective distortion, no existing methods can achieve globally consistent reconstruction and accurate reprojection. To address these challenges, we first propose Crowd3D which leverages a new concept, Human-scene Virtual Interaction Point (HVIP), to convert the complex 3D human localization into 2D-pixel localization with robust camera and ground estimation to achieve globally consistent reconstruction. To achieve stable generalization on different camera FoVs without test-time optimization, we propose an extended version, Crowd3D++, which eliminates the influence of camera parameters and the cropping operation by the proposed canonical upright space and ground-aware normalization transform. In the defined upright space, Crowd3D++ also designs an HVIPNet to regress 2D HVIP and infer the depths. Besides, we contribute two benchmark datasets, LargeCrowd and Synthetic- Crowd, for evaluating crowd reconstruction in large scenes. Experimental results demonstrate the effectiveness of the proposed method. The source code and data will be made publicly available for research *** Codes I.4.8 Scene Analysis Motion Shape Copyright © 2024, The Authors. All rights reserved.

关键词： Crowdsourcing

来源：评论

学校读者我要写书评

暂无评论

Reliable Source Approximation: Source-Free Unsupervised Domain Adaptation for Vestibular Schwannoma MRI Segmentation

arXiv

引用

arXiv 2024年

作者： Zeng, Hongye Zou, Ke Chen, Zhihao Zheng, Rui Fu, Huazhu School of Information Science and Technology ShanghaiTech University Shanghai China National Key Laboratory of Fundamental Science on Synthetic Vision College of Computer Science Sichuan University Chengdu China College of Intelligence and Computing from Tianjin University China Shanghai Engineering Research Center of Intelligent Vision and Imaging Shanghai China Singapore138632 Singapore

Source-Free Unsupervised Domain Adaptation (SFUDA) has recently become a focus in the medical image domain adaptation, as it only utilizes the source model and does not require annotated target data. However, current SFUDA approaches cannot tackle the complex segmentation task across different MRI sequences, such as the vestibular schwannoma segmentation. To address this problem, we proposed Reliable Source Approximation (RSA), which can generate source-like and structure-preserved images from the target domain for updating model parameters and adapting domain shifts. Specifically, RSA deploys a conditional diffusion model to generate multiple source-like images under the guidance of varying edges of one target image. An uncertainty estimation module is then introduced to predict and refine reliable pseudo labels of generated images, and the prediction consistency is developed to select the most reliable generations. Subsequently, all reliable generated images and their pseudo labels are utilized to update the model. Our RSA is validated on vestibular schwannoma segmentation across multi-modality MRI. The experimental results demonstrate that RSA consistently improves domain adaptation performance over other state-of-the-art SFUDA methods. Code is available at https://***/zenghy96/Reliable-Source-Approximation. © 2024, CC BY.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Temporal Feature Aggregation for Efficient 2D Video Grounding

Temporal Feature Aggregation for Efficient 2D Video Groundin...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Mohan Chen Yiren Zhang Jueqi Wei Yuejie Zhang Rui Feng Tao Zhang Shang Gao School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University School of Information Management and Engineering Shanghai Key Laboratory of Financial Information Technology Shanghai University of Finance and Economics School of Information Technology Deakin University

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Video grounding aims to locate the target video moment in an untrimmed video based on a text query. Most existing methods employ 3D CNNs as the video feature extractor, incurring substantial computational costs. Only a few methods use 2D backbones for video feature extraction, and they suffer from diminished accuracy due to the inherent lack of temporal information within 2D features. To address this problem, we propose a novel 2D video grounding method called TFA that improves accuracy while minimizing computational costs. Our approach involves a query-guided temporal feature aggregation module designed to explicitly capture temporal information. We disentangle time intervals of input video frames and prediction spans to reduce computational overhead. Additionally, we introduce deformable attention into the multi-modal encoder for further enhancement. Extensive experiments on two public datasets demonstrate that our method outperforms previous 2D video grounding methods and achieves competitive results with most 3D methods at significantly reduced costs.

关键词： Three-dimensional displays Accuracy Costs Grounding Streaming media Feature extraction Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

CroPrompt: Cross-task Interactive Prompting for Zero-shot Spoken Language Understanding

CroPrompt: Cross-task Interactive Prompting for Zero-shot Sp...

引用

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

作者： Libo Qin Fuxuan Wei Qiguang Chen Jingxuan Zhou Shijue Huang Jiasheng Si Wenpeng Lu Wanxiang Che School of Computer Science and Engineering Central South University China Key Laboratory of Data Intelligence and Advanced Computing in Provincial Universities Soochow University China Research Center for Social Computing and Information Retrieval Harbin Institute of Technology China Harbin Institute of Technology Shenzhen China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology (Shandong Academy of Sciences)

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Slot filling and intent detection are two highly correlated tasks in spoken language understanding (SLU). Recent SLU research attempts to explore zero-shot prompting techniques in large language models to alleviate the data scarcity problem. Nevertheless, the existing prompting work ignores the cross-task interaction information for SLU, which leads to sub-optimal performance. To solve this problem, we present the pioneering work of Cross-task Interactive Prompting (CroPrompt) for SLU, which enables the model to interactively leverage the information exchange across the correlated tasks in SLU. Additionally, we further introduce a multi-task self-consistency mechanism to mitigate the error propagation caused by the intent information injection. We conduct extensive experiments on the standard SLU benchmark and the results reveal that CroPrompt consistently outperforms the existing prompting approaches. In addition, the multi-task self-consistency mechanism can effectively ease the error propagation issue, thereby enhancing the performance. We hope this work can inspire more research on cross-task prompting for SLU.

关键词： Large language models Signal processing Benchmark testing Multitasking Filling Acoustics Speech processing Information exchange Standards

来源：评论

学校读者我要写书评

暂无评论

GEDI: A Graph-based End-to-end Data Imputation Framework

GEDI: A Graph-based End-to-end Data Imputation Framework

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Katrina Chen Xiuqin Liang Zheng Ma Zhibin Zhang Dept. of Statistical and Actuarial Science University of Waterloo Waterloo Canada Data Science Center of Excellence Deloitte Consulting Beijing China Cheriton School of Computer Science University of Waterloo Waterloo Canada Chinese Academy of Sciences Institute of Computing Technology Beijing China

Data imputation is an effective way to handle missing data, which is common in practical applications. In this study, we propose and test a novel data imputation process that achieves two important goals: 1) preserving the row-wise similarities among observations and column-wise contextual relationships among features in the feature matrix. 2) tailoring the imputation process to some specific downstream label prediction task. The proposed imputation process uses Transformer and graph structure learning to iteratively refine the contextual relationships among features and similarities among observations. Moreover, it implements a meta-learning framework to select features that are influential to the downstream prediction task of interest. We conduct experiments on real-world datasets, and show that the proposed method consistently improves imputation and label prediction performance over a variety of benchmark methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Dental Caries Identification with Deep Learning: A Study of Convolutional Neural Networks and Transfer Learning Approaches

SSRN

引用

SSRN 2024年

作者： Mannan, Fayqa Adeel, Muhammad Arif, Erssa Li, Jianqiang Ullah, Amin Nawazish, Samra Mahmood, Tariq Rehman, Amjad Shoukat, Ijaz Faculty of Information Technology Beijing University of Technology Beijing100124 China Department of Computer Science Government College University Faisalabad38000 Pakistan Department of Computer Science School of Science National Textile University Faisalabad37610 Pakistan Department of Computer Science Faculty of Computing Riphah International University Faisalabad38000 Pakistan Beijing Engineering Research Center for IoT Software and Systems 100124 China Department of Computer Science Faculty of IT and Computer Science University of Central Punjab Lahore Pakistan School of Computer Science and Engineering Southeast University Nanjing China Software Engineering Department University of Engineering and Technology Taxila Pakistan Artificial Intelligence & Data Analytics Lab CCIS Prince Sultan University Riyadh11586 Saudi Arabia Faculty of information Sciences University of Education Vehari Campus Vehari61100 Pakistan

Various deep learning techniques have been employed to diagnose dental caries using X-ray images. In this study, we utilized deep learning models, including Convolutional Neural Networks (CNNs) and transfer learning models such as Visual Geometry Group (VGG16), VGG19, ResNet50, and Inception V3, to identify dental caries in periapical radiographs. The traditional CNN model comprises three sets of 2D convolutional layers, followed by an activation layer, a max-pooling layer, a flatten layer, one dense layer, another activation layer, dropout, another dense layer, and a final activation layer. For the VGG models, ResNet50, and Inception V3, the top convolutional layers were frozen to prevent retraining of the model, with only the last layers trained to produce the required output. The accuracy achieved by CNN, VGG16, VGG19, ResNet50, and Inception V3 was 90%, 96%, 73%, 70%, and 73%, respectively. VGG16 exhibited the highest accuracy among the models. Hyperparameters were carefully selected using a grid search approach, and the results were validated using the Shuffle-Split-Cross (SSC) validation method. These findings underscore the effectiveness of transfer learning in analyzing medical images, particularly in the diagnosis of dental caries. © 2024, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of the Coulomb’s and Franklin’s Laws Inspired Algorithm (CFA) with Modern Evolutionary Algorithms for Numerical Optimization 1st

A Comparative Study of the Coulomb’s and Franklin’s Laws I...

引用

1st International Conference on Pervasive Knowledge and Collective Intelligence on Web and Social Media, PerSOM 2022

作者： Ghasemi, Mojtaba Zare, Mohsen Zahedi, Amir Hemmati, Rasul Abualigah, Laith Forestiero, Agostino Department of Electronics and Electrical Engineering Shiraz University of Technology Shiraz Iran Department of Electrical Engineering Faculty of Engineering Jahrom University Fras Jahrom Iran Department of Electrical and Computer Engineering Tarbiat Modares University Tehran Iran Department of Electrical and Computer Engineering Marquette University MilwaukeeWI United States Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman Jordan Faculty of Information Technology Middle East University Amman11831 Jordan Applied Science Research Center Applied Science Private University Amman11931 Jordan School of Computer Sciences Universiti Sains Malaysia Pulau Pinang George Town11800 Malaysia Computer Science Department Prince Hussein Bin Abdullah Faculty for Information Technology Al Al-Bayt University Mafraq25113 Jordan Institute for High Performance Computing and Networking National Research Council of Italy Rende Italy

ISBN: (纸本)9783031314681

Coulomb and Franklin’s electricity laws are used in this paper to model an efficient optimization algorithm based on electric particle searches, which has been named CFA. For the CFA optimizer, the influence of electrically charged particles on each other in charged things has been predicated on the forces of attraction and repulsion. Evolutionary algorithms (EA) such as hybrid real coded genetic algorithm (RCGA) which combines the global and local search (GL-25), differential evolution (DE) with strategy adaptation (SaDE), composite DE (CoDE), the improved standard particle swarm optimization 2011 (SPSO2013) and the grouped comprehensive learning PSO (GCLPSO) are compared to the CFA optimizer for finding global solutions of seven basic benchmark functions of high dimension D = 50. (GCLPSO). Experiments have shown that the suggested CFA optimizer is quite effective and competitive for the benchmark functions. Note that the source code of the CFA algorithm is publicly available at https://***/projects/cfa, https://***/matlabcentral/fileexchange/127727-franklin-s-laws-inspired-algorithm-cfa. © 2023, ICST Institute for computer sciences, Social Informatics and Telecommunications Engineering.

关键词： Charged particles

来源：评论

学校读者我要写书评

暂无评论

3D Human Mesh Estimation from Virtual Markers

3D Human Mesh Estimation from Virtual Markers

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Xiaoxuan Ma Jiajun Su Chunyu Wang Wentao Zhu Yizhou Wang School of Computer Science Center on Frontiers of Computing Studies Peking University Microsoft Research Asia Inst. for Artificial Intelligence Peking University Nat'l Eng. Research Center of Visual Technology

Inspired by the success of volumetric 3D pose estimation, some recent human mesh estimators propose to estimate 3D skeletons as intermediate representations, from which, the dense 3D meshes are regressed by exploiting the mesh topology. However, body shape information is lost in extracting skeletons, leading to mediocre performance. The advanced motion capture systems solve the problem by placing dense physical markers on the body surface, which allows to extract realistic meshes from their non-rigid motions. However, they cannot be applied to wild images without markers. In this work, we present an intermediate representation, named virtual markers, which learns 64 landmark keypoints on the body surface based on the large-scale mocap data in a generative style, mimicking the effects of physical markers. The virtual markers can be accurately detected from wild images and can reconstruct the intact meshes with realistic shapes by simple interpolation. Our approach outperforms the state-of-the-art methods on three datasets. In particular, it surpasses the existing methods by a notable margin on the SURREAL dataset, which has diverse body shapes. Code is available at https://***/ShirleyMaxx/VirtualMarker

关键词：

来源：评论

学校读者我要写书评

暂无评论

Zero-shot Object Detection Based on Dynamic Semantic Vectors

Zero-shot Object Detection Based on Dynamic Semantic Vectors

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Haoyu Li Jilin Mei Jiancong Zhou Yu Hu Research Center for Advanced Computing Systems Zhejiang Laboratory Hangzhou China UCAS Hangzhou Institute for Advanced Study Hangzhou China Research Center for Intelligent Computing Systems Chinese Academy of Sciences Institute of Computing Technology Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

Zero-shot object detection has shown its ability to overcome the problems of data scarcity and novel classes. Existing methods generally utilize static semantic vectors to classify objects and guide the network to map visual features to semantic vectors. However, the distribution of semantic vectors cannot adequately represent visual features, which makes migration from seen to unseen classes difficult. This work explores the dynamic semantic vector method to align the distributions of semantic vectors and visual features. The main challenge is to get a more reasonable distribution of semantic vectors. To address this issue, we proposed a two-way classification branch network and introduce N-pair loss into the dynamic semantic vector optimization process. Experiments on the MS-COCO dataset and SiTi (a real-world autonomous driving dataset collected by us) demonstrate the effectiveness and generalization of our method. Our code is available at https://***/HaoyuLizju/ZSD_tcb

关键词：

来源：评论

学校读者我要写书评

暂无评论

SecureBoost Hyperparameter Tuning via Multi-Objective Federated Learning

arXiv

引用

arXiv 2023年

作者： Ren, Ziyao Kang, Yan Fan, Lixin Yang, Linghua Tong, Yongxin Yang, Qiang State Key Laboratory of Software Development Environment Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing School of Computer Science Beihang University China Webank China Hong Kong University of Science and Technology Hong Kong

SecureBoost is a tree-boosting algorithm leveraging homomorphic encryption to protect data privacy in vertical federated learning setting. It is widely used in fields such as finance and healthcare due to its interpretability, effectiveness, and privacy-preserving capability. However, SecureBoost suffers from high computational complexity and risk of label leakage. To harness the full potential of SecureBoost, hyperparameters of SecureBoost should be carefully chosen to strike an optimal balance between utility, efficiency, and privacy. Existing methods either set hyperparameters empirically or heuristically, which are far from optimal. To fill this gap, we propose a Constrained Multi-Objective SecureBoost (CMOSB) algorithm to find Pareto optimal solutions that each solution is a set of hyperparameters achieving optimal tradeoff between utility loss, training cost, and privacy leakage. We design measurements of the three objectives. In particular, the privacy leakage is measured using our proposed instance clustering attack. Experimental results demonstrate that the CMOSB yields not only hyperparameters superior to the baseline but also optimal sets of hyperparameters that can support the flexible requirements of FL participants. Copyright © 2023, The Authors. All rights reserved.

关键词： Trees (mathematics)

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：