检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Qian, Rui Lai, Xin Li, Xirong Key Lab of Data Engineering and Knowledge Engineering Renmin University of China Beijing100872 China School of Mathematics Renmin University of China Beijing100872 China

Currently, existing state-of-the-art 3D object detectors are in two-stage paradigm. These methods typically comprise two steps: 1) Utilize a region proposal network to propose a handful of high-quality proposals in a bottom-up fashion. 2) Resize and pool the semantic features from the proposed regions to summarize RoI-wise representations for further refinement. Note that these RoI-wise representations in step 2) are considered individually as uncorrelated entries when fed to following detection headers. Nevertheless, we observe these proposals generated by step 1) offset from ground truth somehow, emerging in local neighborhood densely with an underlying probability. Challenges arise in the case where a proposal largely forsakes its boundary information due to coordinate offset while existing networks lack corresponding information compensation mechanism. In this paper, we propose BADet for 3D object detection from point clouds. Specifically, instead of refining each proposal independently as previous works do, we represent each proposal as a node for graph construction within a given cut-off threshold, associating proposals in the form of local neighborhood graph, with boundary correlations of an object being explicitly exploited. Besides, we devise a lightweight Region Feature Aggregation Module to fully exploit voxel-wise, pixel-wise, and point-wise features with expanding receptive fields for more informative RoI-wise representations. We validate BADet both on widely used KITTI dataset and highly challenging nuScenes dataset. As of Apr. 17th, 2021, our BADet achieves on par performance on KITTI 3D detection leaderboard and ranks 1st on Moderate difficulty of Car category on KITTI BEV detection leaderboard. The source code is available at https://***/rui-qian/BADet. © 2021, CC BY.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Research on Object-oriented Exploration Algorithm 2020

Research on Object-oriented Exploration Algorithm

引用

Proceedings of the 2020 International Conference on Cyberspace Innovation of Advanced Technologies

作者： Xiajiong Shen Peng Zhang Jiyong Yang Wan Chen Lei Zhang Henan Key Laboratory of Big Data Analysis and Processing School of Computer and Information Engineering Henan University Kaifeng PR China Henan Key Laboratory of Big Data Analysis and Processing School of Computer and Information Engineering Institute of Data and Knowledge Engineering Henan University Kaifeng PR China

ISBN: (纸本)9781450387828

In formal concept analysis, attribute exploration is a very important methodology, which can explore the logical laws between attributes in a continuous and interactive way. Object-oriented exploration is very meaningful while it is similar to attribute exploration. It can explore the implication relationship between objects. But for the existing work, almost all are attribute exploration, object-oriented exploration is rare. Research on object-oriented exploration has great practical value, such as object classification, retrieval and excavation. In order to address this problem, this article takes the object as the main research point in formal concept analysis based on related knowledge of traditional attribute exploration, and proposes theories of object-oriented exploration. According to these related theories and the framework of attribute exploration algorithm, an object-oriented exploration algorithm is proposed in this paper. The algorithm can be used to explore and understand the relationship between objects, which facilitates to understand better the relationship between objects and attributes.

关键词： Formal concept analysis Object exploration Attribute exploration Implication Concept lattice

来源：评论

学校读者我要写书评

暂无评论

Multi-objective Aerial Collaborative Secure Communication Optimization via Generative Diffusion Model-enabled Deep Reinforcement Learning

arXiv

引用

arXiv 2024年

作者： Zhang, Chuang Sun, Geng Li, Jiahui Wu, Qingqing Wang, Jiacheng Niyato, Dusit Liu, Yuanwei The College of Computer Science and Technology Jilin University Changchun130012 China The Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China The College of Computer Science and Technology Jilin University Changchun130012 China The College of Computing and Data Science Nanyang Technological University 639798 Singapore The Department of Electronic Engineering Shanghai Jiao Tong University Shanghai China The College of Computing and Data Science Nanyang Technological University 639798 Singapore The School of Electronic Engineering and Computer Science Queen Mary University of London LondonE1 4NS United Kingdom

Due to flexibility and low-cost, unmanned aerial vehicles (UAVs) are increasingly crucial for enhancing coverage and functionality of wireless networks. However, incorporating UAVs into next-generation wireless communication systems poses significant challenges, particularly in sustaining high-rate and long-range secure communications against eavesdropping attacks. In this work, we consider a UAV swarm-enabled secure surveillance network system, where a UAV swarm forms a virtual antenna array to transmit sensitive surveillance data to a remote base station (RBS) via collaborative beamforming (CB) so as to resist mobile eavesdroppers. Specifically, we formulate an aerial secure communication and energy efficiency multi-objective optimization problem (ASCEE-MOP) to maximize the secrecy rate of the system and to minimize the flight energy consumption of the UAV swarm. To address the non-convex, NP-hard and dynamic ASCEE-MOP, we propose a generative diffusion model-enabled twin delayed deep deterministic policy gradient (GDMTD3) method. Specifically, GDMTD3 leverages an innovative application of diffusion models to determine optimal excitation current weights and position decisions of UAVs. The diffusion models can better capture the complex dynamics and the trade-off of the ASCEE-MOP, thereby yielding promising solutions. Simulation results highlight the superior performance of the proposed approach compared with traditional deployment strategies and some other deep reinforcement learning (DRL) benchmarks. Moreover, performance analysis under various parameter settings of GDMTD3 and different numbers of UAVs verifies the robustness of the proposed approach. Copyright © 2024, The Authors. All rights reserved.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Injecting Numerical Reasoning Skills into knowledge Base Question Answering Models

arXiv

引用

arXiv 2021年

作者： Feng, Yu Zhang, Jing Zhang, Xiaokang Liu, Lemao Li, Cuiping Chen, Hong Key Laboratory of Data Engineering and Knowledge Engineering Ministry of Education China School of Information Renmin University of China China Tencent AI Lab United States

Embedding-based methods are popular for knowledge Base Question Answering (KBQA), but few current models have numerical reasoning skills and thus struggle to answer ordinal constrained questions. This paper proposes a new embedding-based KBQA framework which particularly takes numerical reasoning into account. We present NumericalTransformer on top of NSM, a state-of-the-art embedding-based KBQA model, to create NT-NSM. To enable better training, we propose two pre-training tasks with explicit numerical-oriented loss functions on two generated training datasets and a template-based data augmentation method for enriching ordinal constrained QA dataset. Extensive experiments on KBQA benchmarks demonstrate that with the help of our training algorithm, NT-NSM is empowered with numerical reasoning skills and substantially outperforms the baselines in answering ordinal constrained questions. Copyright © 2021, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

3D Object Detection for Autonomous Driving: A Survey

arXiv

引用

arXiv 2021年

Autonomous driving is regarded as one of the most promising remedies to shield human beings from severe crashes. To this end, 3D object detection serves as the core basis of perception stack especially for the sake of path planning, motion prediction, and collision avoidance etc. Taking a quick glance at the progress we have made, we attribute challenges to visual appearance recovery in the absence of depth information from images, representation learning from partially occluded unstructured point clouds, and semantic alignments over heterogeneous features from cross modalities. Despite existing efforts, 3D object detection for autonomous driving is still in its infancy. Recently, a large body of literature have been investigated to address this 3D vision task. Nevertheless, few investigations have looked into collecting and structuring this growing knowledge. We therefore aim to fill this gap in a comprehensive survey, encompassing all the main concerns including sensors, datasets, performance metrics and the recent state-of-the-art detection methods, together with their pros and cons. Furthermore, we provide quantitative comparisons with the state of the art. A case study on fifteen selected representative methods is presented, involved with runtime analysis, error analysis, and robustness analysis. Finally, we provide concluding remarks after an in-depth analysis of the surveyed works and identify promising directions for future work. © 2021, CC BY.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

An infrastructure with user-centered presentation data model for integrated management of materials data and services

引用

npj Computational Materials 2021年第1期7卷 779-786页

作者： Shilong Liu Yanjing Su Haiqing Yin Dawei Zhang Jie He Haiyou Huang Xue Jiang Xuan Wang Haiyan Gong Zhuang Li Hao Xiu Jiawang Wan Xiaotong Zhang Beijing Advanced Innovation Center for Materials Genome Engineering University of Science and Technology BeijingBeijingChina School of Computer and Communication Engineering University of Science and Technology BeijingBeijingChina Beijing Key Laboratory of Knowledge Engineering for Materials Science BeijingChina Corrosion and Protection Center University of Science and Technology BeijingBeijingChina Collaborative Innovation Center of Steel Technology University of Science and Technology BeijingBeijingChina National Materials Corrosion and Protection Data Center Institute for Advanced Materials and TechnologyUniversity of Science and Technology BeijingBeijingChina Institute for Advanced Materials and Technology University of Science and Technology BeijingBeijingChina Beijing Key Laboratory of Materials Genome Engineering University of Science and Technology BeijingBeijingChina

With scientific research in materials science becoming more data intensive and collaborative after the announcement of the Materials Genome Initiative,the need for modern data infrastructures that facilitate the sharing of materials data and analysis tools is compelling in the materials *** this paper,we describe the challenges of developing such infrastructure and introduce an emerging architecture with high *** call this architecture the Materials Genome engineering databases(MGED).MGED provides cloud-hosted services with features to simplify the process of collecting datasets from diverse data providers,unify data representation forms with user-centered presentation data model,and accelerate data discovery with advanced search *** also provides a standard service management framework to enable finding and sharing of tools for analyzing and processing *** describe MGED’s design,current status,and how MGED supports integrated management of shared data and services.

关键词： services service centered

来源：评论

学校读者我要写书评

暂无评论

SAMPLING LOVÁSZ LOCAL LEMMA FOR GENERAL CONSTRAINT SATISFACTION SOLUTIONS IN NEAR-LINEAR TIME

arXiv

引用

arXiv 2022年

作者： He, Kun Wang, Chunyang Yin, Yitong The Key Lab of Data Engineering and Knowledge Engineering MOE Renmin University of China No. 59 Zhongguancun Street Haidian District Beijing China State Key Laboratory for Novel Software Technology Nanjing University 163 Xianlin Avenue Jiangsu Province Nanjing China

We give a fast algorithm for sampling uniform solutions of general constraint satisfaction problems (CSPs) in a local lemma regime. Suppose that the CSP has n variables with domain size at most q, each constraint contains at most k variables, shares variables with at most Δ constraints, and is violated with probability at most p by a uniform random assignment. The algorithm returns an almost uniform satisfying assignment in expected poly(q,k, Δ) ·(n) time, as long as a local lemma condition is satisfied: k · p · q2 · Δ5 ≤ C0 for a suitably small absolute constant C0. Previously, under similar local lemma conditions, sampling algorithms with running time polynomial in both nand Δ were only known for the almost atomic case, where each constraint is violated by a small number of forbidden local configurations. The key term Δ5 in our local lemma condition also improves the previously best known Δ7 for general CSPs [JPV21b] and Δ5.714 for atomic CSPs, including the special case of k-CNF [JPV21a, HSW21]. Our sampling approach departs from previous fast algorithms for sampling LLL, which were based on Markov chains. A crucial step of our algorithm is a recursive marginal sampler that is of independent interests. Within a local lemma regime, this marginal sampler can draw a random value for a variable according to its marginal distribution, at a cost independent of the size of the CSP. Copyright © 2022, The Authors. All rights reserved.

关键词： Constraint satisfaction problems

来源：评论

学校读者我要写书评

暂无评论

Prompt Tuning Pushes Farther, Contrastive Learning Pulls Closer: A Two-Stage Approach to Mitigate Social Biases

arXiv

引用

arXiv 2023年

作者： Li, Yingji Du, Mengnan Wang, Xin Wang, Ying College of Computer Science and Technology Jilin University Changchun China Department of Data Science New Jersey Institute of Technology Newark United States School of Artificial Intelligence Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China

As the representation capability of Pre-trained Language Models (PLMs) improve, there is growing concern that they will inherit social biases from unprocessed corpora. Most previous debiasing techniques used Counterfactual data Augmentation (CDA) to balance the training corpus. However, CDA slightly modifies the original corpus, limiting the representation distance between different demographic groups to a narrow range. As a result, the debiasing model easily fits the differences between counterfactual pairs, which affects its debiasing performance with limited text resources. In this paper, we propose an adversarial training-inspired two-stage debiasing model using Contrastive learning with Continuous Prompt Augmentation (named CCPA) to mitigate social biases in PLMs’ encoding. In the first stage, we propose a data augmentation method based on continuous prompt tuning to push farther the representation distance between sample pairs along different demographic groups. In the second stage, we utilize contrastive learning to pull closer the representation distance between the augmented sample pairs and then fine-tune PLMs’ parameters to get debiased encoding. Our approach guides the model to achieve stronger debiasing performance by adding difficulty to the training process. Extensive experiments show that CCPA outperforms baselines in terms of debiasing performance. Meanwhile, experimental results on the GLUE benchmark show that CCPA retains the language modeling capability of PLMs. Copyright © 2023, The Authors. All rights reserved.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

Body-Surface Atrial Vector Similarity as a New Way to Investigate Atrial Fibrillation Propagation Dynamics

Body-Surface Atrial Vector Similarity as a New Way to Invest...

引用

2021 Computing in Cardiology, CinC 2021

作者： Bonizzi, Pietro Zeemering, Stef Karel, Joel Lankveld, Theo Schotten, Ulrich Crijns, Harry Peeters, Ralf Meste, Olivier Maastricht University Department of Data Science and Knowledge Engineering Netherlands Department of Physiology Maastricht University Medical Center Netherlands Maastricht University Netherlands Department of Cardiology Maastricht University Medical Center Netherlands Universite Cote D'Azur CNRS I3S France

ISBN: (纸本)9781665479165

Atrial propagation patterns during atrial fibrillation (AF) can be characterized by a certain degree of recurrence (associated with different types of reentrant circuits that can drive the arrhythmia). In this study, we investigated this recurrent activity at the level of the body-surface, by measuring the level of similarity between pairs of consecutive atrial vectors. High-density body surface potential maps (120 anterior, 64 posterior electrodes) were recorded in 75 patients in persistent AF. For each patient, atrial vectors were created by taking the samples from all electrodes at each time instant. Similarity between consecutive vectors was measured in terms of the value of the cosine of the angle between two vectors. In all patients, the series of cosine values showed a quasi-periodic behavior, with atrial vectors alternating between phases of slow motion, and phases of fast motion. Moreover, the frequency of this behavior is about twice the AF dominant frequency, which suggests that within one AF cycle there are two phases of slow motion and two of fast motion, alternating. Finally, the amount of slow phases is positively correlated with a higher long-term recurrent behavior of the atrial propagation patterns. This seems to indicate that atrial vectors may provide a new way to noninvasively investigate atrial fibrillation dynamics. © 2021 Creative Commons.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Adapting End-to-End Speech Recognition for Readable Subtitles

arXiv

引用

arXiv 2020年

作者： Liu, Danni Niehues, Jan Spanakis, Gerasimos Department of Data Science and Knowledge Engineering Maastricht University

Automatic speech recognition (ASR) systems are primarily evaluated on transcription accuracy. However, in some use cases such as subtitling, verbatim transcription would reduce output readability given limited screen size and reading time. Therefore, this work focuses on ASR with output compression, a task challenging for supervised approaches due to the scarcity of training data. We first investigate a cascaded system, where an unsupervised compression model is used to post-edit the transcribed speech. We then compare several methods of end-to-end speech recognition under output length constraints. The experiments show that with limited data far less than needed for training a model from scratch, we can adapt a Transformer-based ASR model to incorporate both transcription and compression capabilities. Furthermore, the best performance in terms of WER and ROUGE scores is achieved by explicitly modeling the length constraints within the end-to-end ASR system. Copyright © 2020, The Authors. All rights reserved.

关键词： Speech recognition

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：