检索结果-内蒙古大学图书馆

arXiv 2023年

作者： He, Tao Gao, Lianli Song, Jingkuan Li, Yuan-Fang Laboratory of Intelligent Collaborative Computing University of Electronic Science and Technology of China China Department of Data Science and AI Faculty of Information Technology Monash University Australia Center for Future Media University of Electronic Science and Technology of China China

Scene graph generation (SGG) and human-object interaction (HOI) detection are two important visual tasks aiming at localising and recognising relationships between objects, and interactions between humans and objects, respectively. Prevailing works treat these tasks as distinct tasks, leading to the development of task-specific models tailored to individual datasets. However, we posit that the presence of visual relationships can furnish crucial contextual and intricate relational cues that significantly augment the inference of human-object interactions. This motivates us to think if there is a natural intrinsic relationship between the two tasks, where scene graphs can serve as a source for inferring human-object interactions. In light of this, we introduce SG2HOI+, a unified one-step model based on the Transformer architecture. Our approach employs two interactive hierarchical Transformers to seamlessly unify the tasks of SGG and HOI detection. Concretely, we initiate a relation Transformer tasked with generating relation triples from a suite of visual features. Subsequently, we employ another transformer-based decoder to predict human-object interactions based on the generated relation triples. A comprehensive series of experiments conducted across established benchmark datasets including Visual Genome, V-COCO, and HICO-DET demonstrates the compelling performance of our SG2HOI+ model in comparison to prevalent one-stage SGG models. Remarkably, our approach achieves competitive performance when compared to state-of-the-art HOI methods. Additionally, we observe that our SG2HOI+ jointly trained on both SGG and HOI tasks in an end-to-end manner yields substantial improvements for both tasks compared to individualized training paradigms. © 2023, CC BY.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

A Spectral Bipartite Analogue of the Erdős-Sós Conjecture

SSRN

引用

SSRN 2024年

作者： Geng, Xianya Wei, Wei Feng, Zhiming Center of Intelligent Computing and Applied Statistics School of Mathematics Physics and Statistics Shanghai University of Engineering Science Shanghai China School of Mathematics and Big Data Anhui University of Science & Technology Huainan China School of Mathematics and Statistics Xinyang Normal University Xinyang China

A well-known conjecture of Erdős and Sós states that each graph on ν vertices with size more than ν(t2−1) contains every tree with order t + 1 as a subgraph. In 2010, Nikiforov presented the spectral Erdős-Sós conjecture: Let G be a graph with sufficiently large order ν and spectral radius λ(G), and let t ≥ 2 be an integer, (i) if λ(G) ≥ λ(Kt ∨ Kν−t), then G contains all trees of order 2t + 2 unless G ∼= Kt ∨ Kν−t;(ii) if λ(G) ≥ λ(Kt ∨ (Kν−t−2 ∪ K2)), then G contains all trees of order 2t + 3 unless G ∼= Kt ∨ (Kν−t−2 ∪ K2). Recently, this conjecture was confirmed by Cioabă, Desai and Tait (2022). In this contribution, we resolve the spectral bipartite analogue of the Erdős-Sós conjecture. For sufficiently large ν and positive integer t ≥ 2, we show that the complete bipartite graph Kt,ν−t uniquely maximizes the spectral radius over the set of ν-vertex bipartite graphs each of which does not contain some trees with order 2t + 2 (resp. 2t + 3) as subgraphs. Our proof technique is mainly based on the Zarankiewicz number of a tree, and with the aid of the eigenvector method from Cioabă, Desai and Tait (2022). Some problems are proposed in the end for future research. © 2024, The Authors. All rights reserved.

关键词： Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

High-Level Synthesis for Microfluidic Biochips Considering Actual Volume Management and Channel Storage

High-Level Synthesis for Microfluidic Biochips Considering A...

引用

IEEE International Symposium on Quality Electronic Design

作者： Zhengyang Chen Yuhan Zhu Zhen Chen Zhisheng Chen Genggeng Liu College of Computer and Data Science Fuzhou University Fuzhou China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou China Fujian Key Laboratory of Network Computing and Intelligent Information Processing (Fuzhou University) Fuzhou China School of Informatics Xiamen University Xiamen China

ISBN: (数字)9798350309270

ISBN: (纸本)9798350309287

In recent years, microfluidic biochips have been widely applied in various fields of human society. The emergence of distributed channel-storage architecture enables fluid to be directly cached within the flow channels without being transported to the dedicated storage. However, the volume of the flow channels is limited, it is important to carefully consider the fluid volume to be cached to ensure it can be accommodated within the appropriate flow channels. In this paper, we propose a high-level synthesis method considering actual volume management and channel storage through integer linear programming, providing a rational analysis of fluid caching and the temporal relationships between different fluid-handling tasks. Experimental results conducted on multiple benchmark tests demonstrate the effectiveness of the proposed method in reducing the completion time of bioassay, the number of caches, the maximum fluid caching volume, and the number of fluid-handling tasks.

关键词： Fluids Biochips Estimation Cells (biology) Integer linear programming Benchmark testing Task analysis

来源：评论

学校读者我要写书评

暂无评论

Deformable registration framework for glioma images with absent correspondence based on auxiliary-image-aided intensity-consistency constraint

Deformable registration framework for glioma images with abs...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Tang, Kun Wang, Lihui Yang, Menglong Xu, Jingwen Cheng, Xinyu Zhang, Jian Zhu, Yuemin Wei, Hongjiang Ministry of Education State Key Laboratory of Public Big Data College of Computer Science and Technology Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province Engineering Research Center of Text Computing & Cognitive Intelligence Guiyang China Univ Lyon Insa Lyon Cnrs Inserm Creatis Umr 5220 U1206 Lyon France Shanghai Jiao Tong University School of Biomedical Engineering Shanghai200240 China

ISBN: (纸本)9798350386226

Considering the tumor aggressive nature and the significant changes in anatomical structure, aligning the preoperative and follow up scans of glioma patients remains a challenge due to the presence of regions with absent correspondence. To address this challenge, this work proposed a novel bidirectional unsupervised deformable image registration framework for image pairs with missing correspondence based on an auxiliary-image-aided intensity-consistency constraint (ICC) strategy. Specifically, for any fixed and moving image pairs, we introduced an auxiliary image and warped it directly to fixed/moving image or warped it twice through a transition of moving/fixed image. By comparing the difference between these warped images, the weighting maps to identify and exclude regions with absent correspondence between fixed and moving image pairs can be generated. To verify the effectiveness of the proposed framework, we combined it with several deep learning-based registration models and tested it on BraTS-Reg challenge dataset, the results demonstrated that the proposed ICC strategy can improve the registration performance for all the models, with the improvement of average target registration error (TRE) and success rate (SR) being up to 44.9% and 66.7%, respectively. Comparing against the best existing forward-backward consistency strategy for dealing with missing correspondence registration, our auxiliary-image-aided ICC strategy can also decrease average TRE by 2.9%, demonstrating the superiority of the proposed framework. The present work is not limited to the glioma images, it can be used to address the registration problems for any image pairs with absent correspondence or inconsistent intensity. © 2024 IEEE.

关键词： Image registration

来源：评论

学校读者我要写书评

暂无评论

A DQN-Based Approach for Online Service Placement in Mobile Edge computing 16th

A DQN-Based Approach for Online Service Placement in Mobile ...

引用

16th EAI International Conference on Collaborative computing: Networking, Applications, and Worksharing, CollaborateCom 2020

作者： Jie, Xiaogan Liu, Tong Gao, Honghao Cao, Chenhong Wang, Peng Tong, Weiqin School of Computer Engineering and Science Shanghai University Shanghai China Shanghai Key Laboratory of Data Science Shanghai China Shanghai Institute for Advanced Communication and Data Science Shanghai University Shanghai China Shanghai Engineering Research Center of Intelligent Computing System Shanghai China

ISBN: (纸本)9783030675394

Due to the development of 5G networks, computation intensive applications on mobile devices have emerged, such as augmented reality and video stream analysis. Mobile edge computing is put forward as a new computing paradigm, to meet the low-latency requirements of applications, by moving services from the cloud to the network edge like base stations. Due to the limited storage space and computing capacity of an edge server, service placement is an important issue, determining which services are deployed at edge to serve corresponding tasks. The problem becomes particularly complicated, with considering the stochastic arrivals of tasks, the additional latency incurred by service migration, and the time spent for waiting in queues for processing at edge. Benefiting from reinforcement learning, we propose a deep Q network based approach, by formulating service placement as a Markov decision process. Real-time service placement strategies are output, to minimize the total latency of arrived tasks in a long term. Extensive simulation results demonstrate that our approach works effectively. © 2021, ICST Institute for Computer sciences, Social Informatics and Telecommunications Engineering.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

An Efficient and Truthful Online Incentive Mechanism for a Social Crowdsensing Network 16th

An Efficient and Truthful Online Incentive Mechanism for a S...

引用

16th EAI International Conference on Collaborative computing: Networking, Applications, and Worksharing, CollaborateCom 2020

作者： Fang, Lu Liu, Tong Gao, Honghao Cao, Chenhong Li, Weimin Tong, Weiqin School of Computer Engineering and Science Shanghai University Shanghai China Shanghai Key Laboratory of Data Science Shanghai China Shanghai Institute for Advanced Communication and Data Science Shanghai University Shanghai China Shanghai Engineering Research Center of Intelligent Computing System Shanghai China

ISBN: (纸本)9783030675363

Crowdsening plays an important role in spatiotemporal data collection by leveraging ubiquitous smart devices equipped with sensors. Considering rational and strategic device users, designing a truthful incentive mechanism is a crucial issue. Moreover, another key challenge is that there may not exist adequate participating users in reality. To encourage more users to participate, the social relationship among them can be leveraged, as users may be significantly influenced by their social friends. In this paper, we assume recruited users to diffuse uncompleted sensing tasks to their friends, and propose an efficient and truthful online incentive mechanism for a such social crowdsensing network. Specially, we model the time-varying social influence of a user by extending two metrics of node centrality used in social networks. In order to maximize the accumulated social welfare achieved by the network, we design a user selection algorithm and a payment determination algorithm respectively, in which payments given to participants not only depend on data qualities but also related with social influences. We theoretically prove that our mechanism achieves properties of computational efficiency, individual rationality, and truthfulness. Extensive simulations are conducted, and the results show the superiority of our mechanism. © 2021, ICST Institute for Computer sciences, Social Informatics and Telecommunications Engineering.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Rethinking Super-Resolution as Text-Guided Details Generation

arXiv

引用

arXiv 2022年

作者： Ma, Chenxi Yan, Bo Lin, Qing Tan, Weimin Chen, Siming School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University China School of Data Science Fudan University China

Deep neural networks have greatly promoted the performance of single image super-resolution (SISR). Conventional methods still resort to restoring the single high-resolution (HR) solution only based on the input of image modality. However, the image-level information is insufficient to predict adequate details and photo-realistic visual quality facing large upscaling factors (×8, ×16). In this paper, we propose a new perspective that regards the SISR as a semantic image detail enhancement problem to generate semantically reasonable HR image that are faithful to the ground truth. To enhance the semantic accuracy and the visual quality of the reconstructed image, we explore the multi-modal fusion learning in SISR by proposing a Text-Guided Super-Resolution (TGSR) framework, which can effectively utilize the information from the text and image modalities. Different from existing methods, the proposed TGSR could generate HR image details that match the text descriptions through a coarse-to-fine process. Extensive experiments and ablation studies demonstrate the effect of the TGSR, which exploits the text reference to recover realistic images. © 2022, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Outlier detection algorithm based on density and distance

Outlier detection algorithm based on density and distance

引用

2021 3rd International Conference on Applied Machine Learning and data science, ICAMLDS 2021

作者： Qu, Ying Guo, Fei School of Economics and Management Hebei University of Science and Technology Shijiazhuang Hebei050018 China Data Science and Intelligent Computing Research Center Hebei University of Science and Technology Shijiazhuang Hebei050018 China

In order to solve the problem that the existing outlier detection algorithm is difficult to detect the one-dimensional integer data set with uneven frequency distribution and uniform distance distribution and low accuracy, the advantages of density outlier detection and distance outlier detection can be combined. An outlier detection algorithm DAD (Density and Distance) based on density and distance was proposed. In order to improve the possibility of outlier sample distance, the algorithm can define the weight distance;introduce the global density outlier factor combined with the weight distance as the relative distance, and use the cutting edge strategy to quickly cut the outliers based on the minimum spanning tree. Then, an artificial data set was used to test the algorithm. Experimental results showed that the algorithm had a good outlier detection accuracy in dealing with data sets with uneven frequency distribution and uniform distance distribution. © Published under licence by IOP Publishing Ltd.

关键词： Signal detection

来源：评论

学校读者我要写书评

暂无评论

Multi-consensus decentralized accelerated gradient descent

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2023年第1期24卷 14474-14523页

作者： Haishan Ye Luo Luo Ziang Zhou Tong Zhang Center for Intelligent Decision-Making and Machine Learning School of Management Xi'an Jiaotong University Xi'an China School of Data Science Fudan University Shanghai China Department of Computing The Hong Kong Polytechnic University Hong Kong China Computer Science & Mathematics The Hong Kong University of Science and Technology Hong Kong China

This paper considers the decentralized convex optimization problem, which has a wide range of applications in large-scale machine learning, sensor networks, and control theory. We propose novel algorithms that achieve optimal computation complexity and near optimal communication complexity. Our theoretical results give affirmative answers to the open problem on whether there exists an algorithm that can achieve a communication complexity (nearly) matching the lower bound depending on the global condition number instead of the local one. Furthermore, the linear convergence of our algorithms only depends on the strong convexity of global objective and it does not require the local functions to be convex. The design of our methods relies on a novel integration of well-known techniques including Nesterov's acceleration, multi-consensus and gradient-tracking. Empirical studies show the outperformance of our methods for machine learning applications.

关键词： consensus optimization decentralized algorithm accelerated gradient descent gradient tracking composite optimization

来源：评论

学校读者我要写书评

暂无评论

Multi-scale cyclical similarity prototype refinement for few-shot breast ultrasound image segmentation

Multi-scale cyclical similarity prototype refinement for few...

引用

International Conference on Signal Processing Proceedings (ICSP)

作者： Yingfeng Ou Xing Yang Jian Zhang Caiqing Jian Lihui Wang Engineering Research Center of Text Computing Ministry of Education Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang China

ISBN: (数字)9798350387384

ISBN: (纸本)9798350387391

Few-shot learning based methods can address the reliance on large-scale labeled samples in current breast tumor segmentation. However, previous methods typically rely on a few support samples to extract abstract, coarse-grained semantic prototypes, without considering the interaction between support and query data. In this study, we aim to provide each query image with relevant and information-rich support information. By integrating the difficult point selection module and the multi-scale cyclical prototype refinement module, we progressively refine coarse-grained support prototypes into more informative, fine-grained class prototypes, thereby better matching the highly variable breast ultrasound query data. Experiments on two datasets demonstrate that our proposed multi-scale cyclical similarity prototype refinement network (CSPRNet) achieves remarkable improvements compared to previous state-of-the-art methods. Specifically, using ResNet50 as the backbone, we achieve 57.93%/57.92% and 57.58%/59.24% mIoU for 1-shot and 5-shot segmentation, respectively, on public and private datasets, outperforming the suboptimal method by 8.18%/2.55% and 2.77%/4.48%.

关键词： Image segmentation Ultrasonic imaging Breast tumors Semantics Prototypes Signal processing data mining Few shot learning Residual neural networks

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：