检索结果-内蒙古大学图书馆

Multi-Grained Query-Guided Set Prediction Network for Grounded Multimodal Named Entity Recognition

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Tang, Jielong Wang, Zhenxing Gong, Ziyang Yu, Jianxing Zhu, Xiangwei Yin, Jian School of Artificial Intelligence Sun Yat-sen University Zhuhai China School of Atmospheric Sciences Sun Yat-sen University Zhuhai China School of Electronics and Communication Engineering Sun Yat-sen University Guangzhou China State Key Laboratory of Intelligent Game Institute of Software Chinese Academy of Sciences Beijing China Pazhou Lab Guangzhou510330 China

Grounded Multimodal Named Entity Recognition (GMNER) is an emerging information extraction (IE) task, aiming to simultaneously extract entity spans, types, and corresponding visual regions of entities from given sentence-image pairs data. Recent unified methods employing machine reading comprehension or sequence generation-based frameworks show limitations in this difficult task. The former, utilizing human-designed type queries, struggles to differentiate ambiguous entities, such as Jordan (Person) and off-White x Jordan (Shoes). The latter, following the one-by-one decoding order, suffers from exposure bias issues. We maintain that these works misunderstand the relationships of multimodal entities. To tackle these, we propose a novel unified framework named Multi-grained Query-guided Set Prediction Network (MQSPN) to learn appropriate relationships at intra-entity and inter-entity levels. Specifically, MQSPN explicitly aligns textual entities with visual regions by employing a set of learnable queries to strengthen intra-entity connections. Based on distinct intra-entity modeling, MQSPN reformulates GMNER as a set prediction, guiding models to establish appropriate inter-entity relationships from a optimal global matching perspective. Additionally, we incorporate a query-guided Fusion Net (QFNet) as a glue network to boost better alignment of two-level relationships. Extensive experiments demonstrate that our approach achieves state-of-the-art performances in widely used benchmarks. Copyright © 2024, The Authors. All rights reserved.

关键词： Information retrieval

Attacks and defences on intelligent connected vehicles:a survey

学校读者我要写书评

暂无评论

Digital Communications and Networks 2020年第4期6卷 399-421页

作者： Mahdi Dibaei Xi Zheng Kun Jiang Robert Abbas Shigang Liu Yuexin Zhang Yang Xiang Shui Yu Department of Computing Macquarie UniversitySydneyNSWAustralia China State Key Lab of Automotive Safety and Energy Tsinghua UniversityBeijingChina School of Engineering Macquarie UniversitySydneyNSWAustralia School of Software and Electrical Engineering Swinburne University of TechnologyHawthornVICAustralia School of Software University of Technology SydneyAustralia

Intelligent vehicles are advancing at a fast speed with the improvement of automation and connectivity,which opens up new possibilities for different cyber-attacks,including in-vehicle attacks(e.g.,hijacking attacks)and vehicle-to-everything communicationattacks(e.g.,data theft).These problems are becoming increasingly serious with the development of 4G LTE and 5G communication *** many efforts are made to improve the resilience to cyber attacks,there are still many unsolved *** paper first identifies some major security attacks on intelligent connected ***,we investigate and summarize the available defences against these attacks and classify them into four categories:cryptography,network security,software vulnerability detection,and malware *** challenges and future directions for preventing attacks on intelligent vehicle systems have been discussed as well.

关键词： Intelligent vehicles Vehicular networks software vulnerabilities Deep learning 3GPP software defined security

An Efficient DeFi-based DataWarehousing Approach in Supply Chain Finance 5

学校读者我要写书评

暂无评论

An Efficient DeFi-based DataWarehousing Approach in Supply C...

5th International Conference on Future Networks and Distributed Systems: The Premier Conference on Smart Next Generation Networking Technologies, ICFNDS 2021

作者： Rabieinejad, Elnaz Yazdinejad, Abbas Hasani, Tahereh Parizi, Reza M. Hammoudeh, Mohammad Cyber Science Lab School of Computer Science University of Guelph ON Canada Lang School of Business and Economics ON Canada College of Computing and Software Engineering Kennesaw State University GA United States Department of Computing & Mathematics Manchester Metropolitan University Manchester United Kingdom

ISBN: (纸本)9781450387347

In today's world, industries are looking to improve their productivity through effective logistics and supply chain management. The efficiency of the supply chain in dealing with the huge volumes of data plays a key role in the overall performance of businesses. Supply Chain Finance (SCF) aims to improve the robustness and efficiency of companies' supply lines. However, SCF suffers from problems like fraudulent transactions, information inconsistencies, and delays in financial transfers. Decentralized finance (Defi) is a new blockchain paradigm that tackles traditional finance problems. This paper proposes a Defi-based model on a hybrid private-public blockchain for SCF. Our model improves the efficiency of SCF by eliminating costs of using centralized financial institutions, reducing overload costs due to better estimation of the required amount of products, and also decreasing supply delays for the requested products. We also evaluated our model using the SWOT technique for adopting it in the supply chain. © 2021 ACM.

关键词： Smart contract

Modeling Inter-Intra Heterogeneity for Graph Federated Learning 39

学校读者我要写书评

暂无评论

Modeling Inter-Intra Heterogeneity for Graph Federated Learn...

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Yu, Wentao Chen, Shuo Tong, Yongxin Gu, Tianlong Gong, Chen School of Computer Science and Engineering Nanjing University of Science and Technology China Center for Advanced Intelligence Project RIKEN Japan State Key Laboratory of Complex & Critical Software Environment Beihang University China Engineering Research Center of Trustworthy AI Ministry of Education Jinan University China Department of Automation Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

ISBN: (纸本)157735897X

Heterogeneity is a fundamental and challenging issue in federated learning, especially for the graph data due to the complex relationships among the graph nodes. To deal with the heterogeneity, lots of existing methods perform the weighted federation based on their calculated similarities between pairwise clients (i.e., subgraphs). However, their inter-subgraph similarities estimated with the outputs of local models are less reliable, because the final outputs of local models may not comprehensively represent the real distribution of subgraph data. In addition, they ignore the critical intra-heterogeneity which usually exists within each subgraph itself. To address these issues, we propose a novel Federated learning method by integrally modeling the Inter-Intra Heterogeneity (FedIIH). For the inter-subgraph relationship, we propose a novel hierarchical variational model to infer the whole distribution of subgraph data in a multi-level form, so that we can accurately characterize the inter-subgraph similarities with the global perspective. For the intra-heterogeneity, we disentangle the subgraph into multiple latent factors and partition the model parameters into multiple parts, where each part corresponds to a single latent factor. Our FedIIH not only properly computes the distribution similarities between subgraphs, but also learns disentangled representations that are robust to irrelevant factors within subgraphs, so that it successfully considers the inter- and intra- heterogeneity simultaneously. Extensive experiments on six homophilic and five heterophilic graph datasets in both non-overlapping and overlapping settings demonstrate the effectiveness of our method when compared with nine state-of-the-art methods. Specifically, FedIIH averagely outperforms the second-best method by a large margin of 5.79% on all heterophilic datasets. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Federated learning

Generalizable Medical Image Segmentation via Random Amplitude Mixup and Domain-Specific Image Restoration

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhou, Ziqi Qi, Lei Shi, Yinghuan State Key Laboratory for Novel Software Technology Nanjing University China National Institute of Healthcare Data Science Nanjing University China School of Computer Science and Engineering Southeast University China

For medical image analysis, segmentation models trained on one or several domains lack generalization ability to unseen domains due to discrepancies between different data acquisition policies. We argue that the degeneration in segmentation performance is mainly attributed to overfitting to source domains and domain shift. To this end, we present a novel generalizable medical image segmentation method. To be specific, we design our approach as a multi-task paradigm by combining the segmentation model with a self-supervision domain-specific image restoration (DSIR) module for model regularization. We also design a random amplitude mixup (RAM) module, which incorporates low-level frequency information of different domain images to synthesize new images. To guide our model be resistant to domain shift, we introduce a semantic consistency loss. We demonstrate the performance of our method on two public generalizable segmentation benchmarks in medical images, which validates our method could achieve the state-of-the-art performance. ‡ Copyright © 2022, The Authors. All rights reserved.

关键词： Image reconstruction

VS-Net: A Voxel Encoding and Sparse Convolution Embedded Network for LiDAR 3D Object Detection

学校读者我要写书评

暂无评论

VS-Net: A Voxel Encoding and Sparse Convolution Embedded Net...

IEEE International Conference on Robotics and Biomimetics

作者： Meng Liu Jianwei Niu Yu Liu China North Artificial Intelligence and Innovation Research Institute Beijing China China North Vehicle Research Institute Beijing China State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Hangzhou Innovation Institute Beihang University Hangzhou China Zhengzhou University Research Institute of Industrial Technology School of Information Engineering Zhengzhou University Zhengzhou China State Key Laboratory of Software Development Envi-ronment School of Computer Science and Engineering Beihang University Beijing China

ISBN: (纸本)9781665481106

Accurate and efficient 3D object detection in LiDAR point cloud is critical for autonomous driving. In this paper, we provide a solution for LiDAR-only detection which employs voxel features and a sparse convolution network. Specifically, we utilized voxel centers to encode point clouds' voxel features. Then, combining the sparse convolution method, we leveraged residual learning to design the backbone network. The detector output predicted results for multi-category and multi-object detection. Our method was evaluated on three popular and challenging datasets (KITTI, nuScence and Waymo). Experimental results demonstrated that the accuracy and speed (27.8 FPS) of our model could effectively support object detection for autonomous driving in various scenarios.

关键词： Point cloud compression Laser radar Three-dimensional displays Convolution Object detection Detectors Feature extraction

Learning Self-Target Knowledge for Few-Shot Segmentation

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Chen, Yadang Chen, Sihan Yang, Zhi-Xin Wu, Enhua Engineering Research Center of Digital Forensics Ministry of Education Nanjing University of Information Science and Technology Nanjing210044 China School of Computer Science Nanjing University of Information Science and Technology Nanjing210044 China State Key Laboratory of Internet of Things for Smart City Department of Electromechanical Engineering University of Macau 999078 China State Key Laboratory of Computer Science Institute of Software University of Chinese Academy of Sciences Beijing100190 China

Few-shot semantic segmentation uses a few annotated data of a specific class in the support set to segment the target of the same class in the query set. Most existing approaches fail to perform well when there are significant intra-class variances. This paper alleviates the problem by concentrating on mining the query image and using the support set as supplementary information. First, it proposes a Query Prototype Generation Module to generate a query foreground prototype from the query features. Specifically, we use both prototype-level and pixel-level similarity matching to generate two complementary initial prototypes, which we then integrate to create a discriminative query foreground prototype. Second, we propose a Support Auxiliary Refinement Module to further guide the final precise prediction of the query image by leveraging the target category information of the support set through step-by-step mining. Specifically, we generate a query-support mixture prototype based on the support prototype representation obtained using the attention mechanism. Then we generate a support supplement prototype to complement the missing information by encoding over the foreground regions that the query-support mixture prototype fails to segment out. Extensive experiments on PASCAL-5i and COCO-20i demonstrate that our model outperforms the prior works of few-shot segmentation. © 2023, The Authors. All rights reserved.

关键词： Semantics

A Quantum Federated Learning Framework for Classical Clients

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Song, Yanqi Wu, Yusen Wu, Shengyao Li, Dandan Wen, Qiaoyan Qin, Sujuan Gao, Fei State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China Department of Physics The University of Western Australia PerthWA6009 Australia School of Computer Science National Pilot Software Engineering School Beijing University of Posts and Telecommunications Beijing100876 China

Quantum Federated Learning (QFL) enables collaborative training of a Quantum Machine Learning (QML) model among multiple clients possessing quantum computing capabilities, without the need to share their respective local data. However, the limited availability of quantum computing resources poses a challenge for each client to acquire quantum computing capabilities. This raises a natural question: Can quantum computing capabilities be deployed on the server instead? In this paper, we propose a QFL framework specifically designed for classical clients, referred to as CC-QFL, in response to this question. In each iteration, the collaborative training of the QML model is assisted by the shadow tomography technique, eliminating the need for quantum computing capabilities of clients. Specifically, the server constructs a classical representation of the QML model and transmits it to the clients. The clients encode their local data onto observables and use this classical representation to calculate local gradients. These local gradients are then utilized to update the parameters of the QML model. We evaluate the effectiveness of our framework through extensive numerical simulations using handwritten digit images from the MNIST dataset. Our framework provides valuable insights into QFL, particularly in scenarios where quantum computing resources are scarce. Copyright © 2023, The Authors. All rights reserved.

关键词： Iterative methods

3Deformer: A Common Framework for Image-Guided Mesh Deformation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Su, Hao Liu, Xuefeng Niu, Jianwei Wan, Ji Wu, Xinghao State Key Lab of VR Technology and System School of Computer Science and Engineering Beihang University Beijing100000 China Industrial Technology Research Institute School of Information Engineering Zhengzhou University Henan450000 China Hangzhou Innovation Institute Beihang University Zhejiang 310000 China

We propose 3Deformer, a general-purpose framework for interactive 3D shape editing. Given a source 3D mesh with semantic materials, and a user-specified semantic image, 3Deformer can accurately edit the source mesh following the shape guidance of the semantic image, while preserving the source topology as rigid as possible. Recent studies of 3D shape editing mostly focus on learning neural networks to predict 3D shapes, which requires high-cost 3D training datasets and is limited to handling objects involved in the datasets. Unlike these studies, our 3Deformer is a non-training and common framework, which only requires supervision of readily-available semantic images, and is compatible with editing various objects unlimited by datasets. In 3Deformer, the source mesh is deformed utilizing the differentiable renderer technique, according to the correspondences between semantic images and mesh materials. However, guiding complex 3D shapes with a simple 2D image incurs extra challenges, that is, the deform accuracy, surface smoothness, geometric rigidity, and global synchronization of the edited mesh should be guaranteed. To address these challenges, we propose a hierarchical optimization architecture to balance the global and local shape features, and propose further various strategies and losses to improve properties of accuracy, smoothness, rigidity, and so on. Extensive experiments show that our 3Deformer is able to produce impressive results and reaches the state-of-the-art level. Copyright © 2023, The Authors. All rights reserved.

关键词： Rigidity