检索结果-内蒙古大学图书馆

Neural transmitted radiance fields 22

学校读者我要写书评

暂无评论

Neural transmitted radiance fields

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Chengxuan Zhu Renjie Wan Boxin Shi Nat'l Eng. Research Center of Visual Technology School of Computer Science Peking University Department of Computer Science Hong Kong Baptist University

ISBN: (纸本)9781713871088

Neural radiance fields (NeRF) have brought tremendous progress to novel view synthesis. Though NeRF enables the rendering of subtle details in a scene by learning from a dense set of images, it also reconstructs the undesired reflections when we capture images through glass. As a commonly observed interference, the reflection would undermine the visibility of the desired transmitted scene behind glass by occluding the transmitted light rays. In this paper, we aim at addressing the problem of rendering novel transmitted views given a set of reflection-corrupted images. By introducing the transmission encoder and recurring edge constraints as guidance, our neural transmitted radiance fields can resist such reflection interference during rendering and reconstruct high-fidelity results even under sparse views. The proposed method achieves superior performance from the experiments on a newly collected dataset compared with state-of-the-art methods.

关键词：

Systematic Review on Reinforcement Learning in the field of Fintech

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Malibari, Nadeem Katib, Iyad Mehmood, Rashid Department of Computer Science Faculty of Computing and Information Technology King Abdulaziz University Jeddah21589 Saudi Arabia High Performance Computing Center King Abdulaziz University Jeddah21589 Saudi Arabia

Applications of Reinforcement Learning in the Finance Technology (Fintech) have acquired a lot of admiration lately. Undoubtedly Reinforcement Learning, through its vast competence and proficiency, has aided remarkable results in the field of Fintech. The objective of this systematic survey is to perform an exploratory study on a correlation between reinforcement learning and Fintech to highlight the prediction accuracy, complexity, scalability, risks, profitability and performance. Major uses of reinforcement learning in finance or Fintech include portfolio optimization, credit risk reduction, investment capital management, profit maximization, effective recommendation systems, and better price setting strategies. Several studies have addressed the actual contribution of reinforcement learning to the performance of financial institutions. The latest studies included in this survey are publications from 2018 onward. The survey is conducted using PRISMA technique which focuses on the reporting of reviews and is based on a checklist and four-phase flow diagram. The conducted survey indicates that the performance of RL-based strategies in Fintech fields proves to perform considerably better than other state-of-the-art algorithms. The present work discusses the use of reinforcement learning algorithms in diverse decision-making challenges in Fintech and concludes that the organizations dealing with finance can benefit greatly from Robo-advising, smart order channelling, market making, hedging and options pricing, portfolio optimization, and optimal execution. © 2023, CC BY.

关键词： Reinforcement learning

IC-CViT: Inverse-Consistent Convolutional Vision Transformer for Diffeomorphic Image Registration

学校读者我要写书评

暂无评论

IC-CViT: Inverse-Consistent Convolutional Vision Transformer...

International Joint Conference on Neural Networks (IJCNN)

作者： Tao Xu Ting Jiang Xiaoning Li College of Computer Science Sichuan Normal University Chengdu China Visual Computing and Virtual Reality Key Laboratory of Sichuan Province Chengdu China Sichuan 2011 Collaborative Innovation Center for Educational Big Data Chengdu China

Diffeomorphic registration plays a crucial role in medical image analysis due to the invertible and one-to-one mapping transformation. In recent years, with the development of deep learning technology, convolutional neural networks (CNNs) have been a broad focus of research in medical image registration, and CNN-based methods have made great progress. However, the results of most existing methods generally are not necessarily diffeomorphic, generating implausibly bijective mappings between images due to the interpolation and discrete representation. Furthermore, the performances of CNNs may be limited by a lack of precise comprehension of global and long-range cross-image spatial relevance. Vision Transformer (ViT) is capable of enhancing the long-distance information interaction ability to identify the semantically anatomically correspondences of medical images. Compared with CNN, ViT has weak local feature extraction ability due to less inductive bias, especially in small-scale training datasets, meaning that the samples between adjacent pixels cannot be exploited adequately. To address the above challenges, we propose a novel Inverse-Consistent Convolutional Vision Transformer (IC-CViT) network for diffeomorphic image registration. Specifically, image pairs can explicitly conduct bi-directional registration through the predicted deformation filed, generated within the diffeomorphic mappings space and restricted by the proposed inverse consistent loss term. We verify our method on two 3D brain MRI scan datasets including OASIS and LPBA40. Comprehensive results demonstrate that IC-CViT achieves state-of-the-art registration accuracy while maintaining desired diffeomorphic properties.

关键词：

DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Hui Wang, Zheng Wu, Zuxuan Jiang, Yu-Gang Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University China Shanghai Collaborative Innovation Center of Intelligent Visual Computing China School of Computer Science Zhejiang University of Technology China

Anomaly detection has garnered extensive applications in real industrial manufacturing due to its remarkable effectiveness and efficiency. However, previous generative-based models have been limited by suboptimal reconstruction quality, hampering their overall performance. We introduce DiffusionAD, a novel anomaly detection pipeline comprising a reconstruction sub-network and a segmentation sub-network. A fundamental enhancement lies in our reformulation of the reconstruction process using a diffusion model into a noise-to-norm paradigm. Here, anomalous regions are perturbed with Gaussian noise and reconstructed as normal, overcoming the limitations of previous models by facilitating anomaly-free restoration. Additionally, we propose a rapid one-step denoising paradigm, significantly faster than the traditional iterative denoising in diffusion models. Furthermore, the introduction of the norm-guided paradigm elevates the accuracy and fidelity of reconstructions. The segmentation sub-network predicts pixel-level anomaly scores using the input image and its anomaly-free restoration. Comprehensive evaluations on four standard and challenging benchmarks reveal that DiffusionAD outperforms current state-of-the-art approaches, demonstrating the effectiveness and broad applicability of the proposed pipeline. Copyright © 2023, The Authors. All rights reserved.

关键词： Anomaly detection

Multi-Disease-Aware Training Strategy for Cardiac MR Image Segmentation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zheng, Hong Chen, Yucheng Mu, Nan Li, Xiaoning College of Computer Science Sichuan Normal University Chengdu610101 China School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China Department of Cardiology West China Hospital Sichuan University Chengdu610041 China Visual Computing and Virtual Reality Key Laboratory of Sichuan Province Chengdu610066 China Sichuan 2011 Collaborative Innovation Center for Educational Big Data Chengdu610066 China

Accurate segmentation of the ventricles from cardiac magnetic resonance images (CMRIs) is crucial for enhancing the diagnosis and analysis of heart conditions. Deep learning-based segmentation methods have recently garnered significant attention due to their impressive performance. However, these segmentation methods are typically good at partitioning regularly shaped organs, such as the left ventricle (LV) and the myocardium (MYO), whereas they perform poorly on irregularly shaped organs, such as the right ventricle (RV). In this study, we argue that this limitation of segmentation models stems from their insufficient generalization ability to address the distribution shift of segmentation targets across slices, cardiac phases, and disease conditions. To overcome this issue, we present a Multi-Disease-Aware Training Strategy (MTS) and restructure the introduced CMRI datasets into multi-disease datasets. Additionally, we propose a specialized data processing technique for preprocessing input images to support the MTS. To validate the effectiveness of our method, we performed control group experiments and cross-validation tests. The experimental results show that (1) network models trained using our proposed strategy achieved superior segmentation performance, particularly in RV segmentation, and (2) these networks exhibited robust performance even when applied to data from unknown diseases. Copyright © 2025, The Authors. All rights reserved.

关键词： Image segmentation

On Differentially Private String Distances

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hu, Jerry Yao-Chieh Liu, Erzhi Liu, Han Song, Zhao Zhang, Lichen Ensemble AI San FranciscoCA United States Center for Foundation Models and Generative AI Department of Computer Science Northwestern University EvanstonIL United States Center for Foundation Models and Generative AI Department of Computer Science Department of Statistics and Data Science Northwestern University EvanstonIL United States Simons Institute for the Theory of Computing UC Berkeley BerkeleyCA United States Department of Mathematics & Computer Science and Artificial Intelligence Laboratory MIT CambridgeMA United States

Given a database of bit strings A1, . . ., Am ∈ {0, 1}n, a fundamental data structure task is to estimate the distances between a given query B ∈ {0, 1}n with all the strings in the database. In addition, one might further want to ensure the integrity of the database by releasing these distance statistics in a secure manner. In this work, we propose differentially private (DP) data structures for this type of tasks, with a focus on Hamming and edit distance. On top of the strong privacy guarantees, our data structures are also time- and space-efficient. In particular, our data structure is ǫ-DP against any sequence of queries of arbitrary length, and for any query B such that the maximum distance to any string in the database is at most k, we output m distance estimates. Moreover, • For Hamming distance, our data structure answers any query in Oe(mk + n) time and each estimate deviates from the true distance by at most Oe(k/eǫ/ log k);• For edit distance, our data structure answers any query in Oe(mk2 + n) time and each estimate deviates from the true distance by at most Oe(k/eǫ/(log k log n)). For moderate k, both data structures support sublinear query operations. We obtain these results via a novel adaptation of the randomized response technique as a bit flipping procedure, applied to the sketched strings. © 2024, CC BY-NC-SA.

关键词： Structured Query Language

A Secure Authentication Framework for Consumer Mobile Crowdsourcing Networks

学校读者我要写书评

暂无评论

IEEE Transactions on Consumer Electronics 2024年

作者： Aldosary, Abdallah Tanveer, Muhammad Ahmad, Musheer Maghrabi, Louai A. Ahmed, Emad A. Hussain, Amir El-Latif, Ahmed A. Abd Department of Computer Engineering Prince Sattam bin Abdulaziz University Riyadh Wadi Addwasir11991 Saudi Arabia University of Management and Technology Department of Computer Science Lahore54770 Pakistan Jamia Millia Islamia Department of Computer Engineering New Delhi110025 India University of Business and Technology College of Engineering Department of Software Engineering Jeddah Saudi Arabia South Valley University Faculty of Computers and Information Department of Computer Science Qena Egypt Edinburgh Napier University United Kingdom Prince Sultan University EIAS Data Science Lab College of Computer and Information Sciences Center of Excellence in Quantum and Intelligent Computing Riyadh11586 Saudi Arabia Menoufia University Faculty of Science Department of Mathematics and Computer Science Shebin El-Koom32511 Egypt

The Mobile crowdsourcing network (MCN) leverages collaborative intelligence to solve complex tasks through group cooperation. It comprises three main components: the end-user, the service provider, and the mobile user. The end-user requests crowd-sensing and computing services from the service provider, who handles task decomposition, distribution, re-composition, and recommendation. Mobile users perform the crowd sensing and computing tasks. Despite its benefits, MCN faces significant security and privacy challenges. Communications between the service provider and the end-user involve sensitive data, and mobile users and service providers communicate over open channels, making them vulnerable to security threats. To address these concerns, we propose a secure authentication framework for MCN, called SAF-MCN. This framework combines the lightweight cryptographic primitive ' ASCON' with elliptic curve cryptography. SAF-MCN allows the service provider to authenticate mobile users before they join the MCN. Once authenticated, a secure channel is established for encrypted communication over the public Internet. The security of SAFMCN is validated using both formal and informal methods, demonstrating its resilience against potential attacks. The use of Scyther further ensures the security of SAF-MCN. Comparative analysis shows that SAF-MCN is superior in terms of security features, computational efficiency, and communication cost. © 1975-2011 IEEE.

关键词： ASCON Authenticated Encryption Authentication Mobile Crowdsourcing Network Scyther Security

Predictive Modelling of Protest Event Signatures: Analyzing Temporal Dynamics and Digital Activism Discourse Across Global Movements

学校读者我要写书评

暂无评论

Journal of Social computing 2025年第1期6卷 43-50页

作者： Amila Chethana Nanayakkara B. T. G. Samantha Kumara R. M. Kapila Tharanga Rathnayaka Center for Computer Studies Sabaragamuwa University of Sri Lanka Belihuloya Sri Lanka Department of Data Science Faculty of Computing Sabaragamuwa University of Sri Lanka Belihuloya Sri Lanka Department of Physical Sciences and Technology Faculty of Applied Sciences Sabaragamuwa University of Sri Lanka Belihuloya Sri Lanka

This research introduced a predictive modeling framework to analyze the temporal dynamics of social media discourse during three global movements: the Mahsa Amini Protests (2022), South African Unrest (2021), and the Black Lives Matter Movement (2020). By utilizing Twitter data, the study developed a Protest Social Media Archetype to capture the evolution of tweet activity during key protest periods, identifying common patterns and notable variations in public engagement. Techniques such as LOESS regression and correlation analysis were used to model fluctuations in online activity and assess the impact of social media on public mobilization during socio-political unrest. The findings revealed distinct temporal signatures for each movement, showing similarities in initial engagement and differences in sustained activity across various contexts. These insights underscore the role of digital platforms in protest organization and global solidarity, offering a framework for future studies on digital activism and protest dynamics.

关键词： Analytical models Social computing Fluctuations Social networking (online) Blogs Refining Organizations Predictive models Real-time systems Mathematics

From Hypergraph Energy Functions to Hypergraph Neural Networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Yuxin Gan, Quan Qiu, Xipeng Huang, Xuanjing Wipf, David School of Computer Science Fudan University China Institute of Modern Languages and Linguistics Fudan University China Amazon United States Peng Cheng Laboratory China Shanghai Collaborative Innovation Center of Intelligent Visual Computing China

Hypergraphs are a powerful abstraction for representing higher-order interactions between entities of interest. To exploit these relationships in making downstream predictions, a variety of hypergraph neural network architectures have recently been proposed, in large part building upon precursors from the more traditional graph neural network (GNN) literature. Somewhat differently, in this paper we begin by presenting an expressive family of parameterized, hypergraph-regularized energy functions. We then demonstrate how minimizers of these energies effectively serve as node embeddings that, when paired with a parameterized classifier, can be trained end-to-end via a supervised bilevel optimization process. Later, we draw parallels between the implicit architecture of the predictive models emerging from the proposed bilevel hypergraph optimization, and existing GNN architectures in common use. Empirically, we demonstrate state-of-the-art results on various hypergraph node classification benchmarks. Code is available at https://***/yxzwang/PhenomNN. Copyright © 2023, The Authors. All rights reserved.

关键词： Graph neural networks