检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Wang, Yunyun Zheng, Weiwen Chen, Songcan The Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Computer Science and Engineering Nanjing University of Posts & Telecommunications Nanjing210046 China The MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Computer Science & Technology/AI Nanjing University of Aeronautics & Astronautics Nanjing210023 China

Previous unsupervised domain adaptation (UDA) methods aim to promote target learning via a single-directional knowledge transfer from label-rich source domain to unlabeled target domain, while its reverse adaption from target to source has not jointly been considered yet so far. In fact, in some real teaching practice, a teacher helps students learn while also gets promotion from students to some extent, which inspires us to explore a dual-directional knowledge transfer between domains, and thus propose a Dual-Correction Adaptation Network (DualCAN) in this paper. However, due to the asymmetrical label knowledge across domains, transfer from unlabeled target to labeled source poses a more difficult challenge than the common source-to-target counterpart. First, the target pseudo-labels predicted by source commonly involve noises due to model bias, hence in the reverse adaptation, they may hurt the source performance and bring a negative target-to-source transfer. Secondly, source domain usually contains innate noises, which will inevitably aggravate the target noises, leading to noise amplification across domains. To this end, we further introduce a Noise Identification and Correction (NIC) module to correct and recycle noises in both domains. To our best knowledge, this is the first naive attempt of dual-directional adaptation for noisy UDA, and naturally applicable to noise-free UDA. A theory justification is given to state the rationality of our intuition. Empirical results confirm the effectiveness of DualCAN with remarkable performance gains over state-of-the-arts, particularly for extreme noisy tasks (e.g., ∼+ 15% on Pw→Pr and Pr→Rw of Office-Home). Copyright © 2022, The Authors. All rights reserved.

关键词： Knowledge management

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Framework of Multimodal Emotion Recognition Based on Collaborative Discriminative Learning

An Adaptive Framework of Multimodal Emotion Recognition Base...

引用

International Workshop on Advanced Computational Intelligence (IWACI)

作者： Yadi Wang Xiaoding Guo Yibo Zhang Yiyuan Ren Wendi Huang Zunyan Liu Yuming Feng Xiangguang Dai Wei Zhang Hangjun Che School of Computer and Information Engineering Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China School of Computer and Information Engineering Henan University Kaifeng China Key Laboratory of Intelligent Information Processing and Control Chongqing Three Gorges University Chongqing China School of Computer Science and Engineering Chongqing Three Gorges University Chongqing China School of Three Gorges Artificial Intelligence Chongqing Three Gorges University Chongqing China College of Electronic and Information Engineering Southwest University Chongqing China

Multimodal emotion recognition has great application scenarios in the field of human-computer interaction, and the main task lies in how to capture and handle the consistency and complementarity of multimodal signals. However, in numerous scenarios, multimodal fusion is significantly challenged by variances in the strengths and weaknesses of different modality signals in carrying emotional information. This paper aims to learn the essential information of strong modalities and inter-modality correlations thus achieving better emotion recognition. We propose an adaptive multimodal emotion recognition framework based on collaborative discriminative learning (AMCDL), a framework for emotion recognition that engages in collaborative learning and adjusts to the information-processing capabilities of various emotion recognition models. AMCDL calculates the inter-modality correlation using Canonical Correlation analysis (CCA) and uses it as an influencing factor to boost the multiplicative combination method to create a class loss function. When trained on several modalities, the class loss function can integrate complementary information to enable strong modal expression, enhancing emotion perception. On the benchmark dataset CMU-MOSI, AMCDL significantly improves classification accuracy when compared to the state-of-the-art models. The experiments showed the flexibility and generality of AMCDL by applying several emotion recognition models to it and producing better classification results than the original model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Answering Subjective Induction Questions on Products by Summarizing Multi-sources Multi-viewpoints Knowledge

arXiv

引用

arXiv 2023年

作者： Zhang, Yufeng Wang, Meng-Xiang Yu, Jianxing School of Artificial Intelligence Sun Yat-sen University Zhuhai519082 China Guangdong Key Laboratory of Big Data Analysis and Processing 510006 China China National Institute of Standardization 100088 China Pazhou Lab Guangzhou510330 China

This paper proposes a new task in the field of Answering Subjective Induction Question on Products (SUBJPQA). The answer to this kind of question is non-unique, but can be interpreted from many perspectives. For example, the answer to ‘whether the phone is heavy’ has a variety of different viewpoints. A satisfied answer should be able to summarize these subjective opinions from multiple sources and provide objective knowledge, such as the weight of a phone. That is quite different from the traditional QA task, in which the answer to a factoid question is unique and can be found from a single data source. To address this new task, we propose a three-steps method. We first retrieve all answer-related clues from multiple knowledge sources on facts and opinions. The implicit commonsense facts are also collected to supplement the necessary but missing contexts. We then capture their relevance with the questions by interactive attention. Next, we design a reinforcement-based summarizer to aggregate all these knowledgeable clues. Based on a template-controlled decoder, we can output a comprehensive and multi-perspective answer. Due to the lack of a relevant evaluated benchmark set for the new task, we construct a large-scale dataset, named SupQA, consisting of 48,352 samples across 15 product domains. Evaluation results show the effectiveness of our approach. © 2023, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Learning Summary-Worthy Visual Representation for Abstractive Summarization in Video

arXiv

引用

arXiv 2023年

作者： Xu, Zenan Meng, Xiaojun Wang, Yasheng Su, Qinliang Qiu, Zexuan Jiang, Xin Liu, Qun School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Noah’s Ark Lab Huawei Technologie The Chinese University of Hong Kong Hong Kong Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China

Multimodal abstractive summarization for videos (MAS) requires generating a concise textual summary to describe the highlights of a video according to multimodal resources, in our case, the video content and its transcript. Inspired by the success of the large-scale generative pre-trained language model (GPLM) in generating high-quality textual content (e.g., summary), recent MAS methods have proposed to adapt the GPLM to this task by equipping it with the visual information, which is often obtained through a general-purpose visual feature extractor. However, the generally extracted visual features may overlook some summary-worthy visual information, which impedes model performance. In this work, we propose a novel approach to learning the summary-worthy visual representation that facilitates abstractive summarization. Our method exploits the summary-worthy information from both the cross-modal transcript data and the knowledge that distills from the pseudo summary. Extensive experiments on three public multimodal datasets show that our method outperforms all competing baselines. Furthermore, with the advantages of summary-worthy visual information, our model can have a significant improvement on small datasets or even datasets with limited training data. Copyright © 2023, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Sparse Deep Neural Network for Nonlinear Partial Differential Equations

arXiv

引用

arXiv 2022年

作者： Xu, Yuesheng Zeng, Taishan Department of Mathematics and Statistics Old Dominion University NorfolkVA23529 United States School of Mathematical Science South China Normal University Guangzhou510631 China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou510006 China

More competent learning models are demanded for data processing due to increasingly greater amounts of data available in applications. data that we encounter often have certain embedded sparsity structures. That is, if they are represented in an appropriate basis, their energies can concentrate on a small number of basis functions. This paper is devoted to a numerical study of adaptive approximation of solutions of nonlinear partial differential equations whose solutions may have singularities, by deep neural networks (DNNs) with a sparse regularization with multiple parameters. Noting that DNNs have an intrinsic multi-scale structure which is favorable for adaptive representation of functions, by employing a penalty with multiple parameters, we develop DNNs with a multi-scale sparse regularization (SDNN) for effectively representing functions having certain singularities. We then apply the proposed SDNN to numerical solutions of the Burgers equation and the Schrödinger equation. Numerical examples confirm that solutions generated by the proposed SDNN are sparse and accurate. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

EasyHPC: An online programming platform for learning high performance computing

EasyHPC: An online programming platform for learning high pe...

引用

IEEE International Conference on Teaching, Assessment and Learning for Engineering (TALE)

作者： Zhepeng Zou Yuxiao Zhang Jiang Li Xiaojun Hei Yunfei Du Di Wu Guangdong Province Key Laboratory of Big Data Analysis and Processing Guangzhou China School of Data and Computer Science Sun Yat-sen University Guangzhou China National Supercomputer Center in Guangzhou Guangzhou China School of Electronic Information and Communications Huazhong University of Science and Technology Wuhan China

Lacking of appropriate learning facilities, the traditional approach to learn high-performance computing (HPC) is commonly theory-oriented without sufficient hands-on programming experiences. To improve the hands-on experiences of HPC learners, we design and implement a flexible and adaptive online HPC learning platform in this paper, called EasyHPC. This platform contains various online course modules such as quiz bank, interactive community, and virtual laboratory. In our system, various HPC theoretical and experimental learning activities can be conducted online, such as assigning HPC parallel programming tasks, and creating HPC questions and collecting students' submissions. It is convenient for students to study HPC-related courses in our platform, submit course assignments, exchange ideas, and complete HPC programming tasks. Our preliminary learning trials have shown that our system can effectively improve the hands-on experience of our students by providing an integrated HPC learning and programming environment. Our students are able to achieve various HPC capstone projects in our platform to develop their system capability.

关键词： Programming profession Servers High performance computing Education Supercomputers

来源：评论

学校读者我要写书评

暂无评论

Cross-view Asymmetric Metric Learning for Unsupervised Person Re-identification

arXiv

引用

arXiv 2017年

作者： Yu, Hong-Xing Wu, Ancong Zheng, Wei-Shi School of Data and Computer Science Sun Yat-sen University China School of Electronics and Information Technology Sun Yat-sen University China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Collaborative Innovation Center of High Performance Computing NUDT China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China

While metric learning is important for Person reidentification (RE-ID), a significant problem in visual surveillance for cross-view pedestrian matching, existing metric models for RE-ID are mostly based on supervised learning that requires quantities of labeled samples in all pairs of camera views for training. However, this limits their scalabilities to realistic applications, in which a large amount of data over multiple disjoint camera views is available but not labelled. To overcome the problem, we propose unsupervised asymmetric metric learning for unsupervised RE-ID. Our model aims to learn an asymmetric metric, i.e., specific projection for each view, based on asymmetric clustering on cross-view person images. Our model finds a shared space where view-specific bias is alleviated and thus better matching performance can be achieved. Extensive experiments have been conducted on a baseline and five large-scale RE-ID datasets to demonstrate the effectiveness of the proposed model. Through the comparison, we show that our model works much more suitable for unsupervised RE-ID compared to classical unsupervised metric learning models. We also compare with existing unsupervised REID methods, and our model outperforms them with notable margins. Specifically, we report the results on large-scale unlabelled RE-ID dataset, which is important but unfortunately less concerned in literatures. Copyright © 2017, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Meta Neural Heuristic for Multi-Objective Combinatorial Optimization

arXiv

引用

arXiv 2023年

作者： Chen, Jinbiao Wang, Jiahai Zhang, Zizhen Cao, Zhiguang Ye, Te Chen, Siyuan School of Computer Science and Engineering Sun Yat-sen University China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Sun Yat-sen University China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China School of Computing and Information Systems Singapore Management University Singapore

Recently, neural heuristics based on deep reinforcement learning have exhibited promise in solving multi-objective combinatorial optimization problems (MOCOPs). However, they are still struggling to achieve high learning efficiency and solution quality. To tackle this issue, we propose an efficient meta neural heuristic (EMNH), in which a meta-model is first trained and then fine-tuned with a few steps to solve corresponding single-objective subproblems. Specifically, for the training process, a (partial) architecture-shared multi-task model is leveraged to achieve parallel learning for the meta-model, so as to speed up the training;meanwhile, a scaled symmetric sampling method with respect to the weight vectors is designed to stabilize the training. For the fine-tuning process, an efficient hierarchical method is proposed to systematically tackle all the subproblems. Experimental results on the multi-objective traveling salesman problem (MOTSP), multi-objective capacitated vehicle routing problem (MOCVRP), and multi-objective knapsack problem (MOKP) show that, EMNH is able to outperform the state-of-the-art neural heuristics in terms of solution quality and learning efficiency, and yield competitive solutions to the strong traditional heuristics while consuming much shorter time. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A queueing-theoretic framework for vehicle dispatching in dynamic car-hailing [technical report]

arXiv

引用

arXiv 2021年

作者： Cheng, Peng Jin, Jiabao Zheng, Libin Chen, Lei Lin, Xuemin East China Normal University Shanghai China The Hong Kong University of Science and Technology Hong Kong Guangdong Key Laboratory of Big Data Analysis and Processing Sun Yat-Sen University Guangzhou China The University of New South Wales Sydney Australia

With the rapid development of smart mobile devices, the car-hailing platforms (e.g., Uber or Lyft) have attracted much attention from the academia and the industry. In this paper, we consider a dynamic car-hailing problem, namely maximum revenue vehicle dispatching (MRVD), in which rider requests dynamically arrive and drivers need to serve riders such that the entire revenue of the platform is maximized. We prove that the MRVD problem is NP-hard and intractable. To handle the MRVD problem, we propose a queueing-based vehicle dispatching framework, which first uses existing machine learning models to predict the future vehicle demand of each region, then estimates the idle time periods of drivers through a double-sided queueing model for each region. With the information of the predicted vehicle demands and estimated idle time periods of drivers, we propose two batch-based vehicle dispatching algorithms to efficiently assign suitable drivers to riders such that the expected overall revenue of the platform is maximized during each batch processing. Through extensive experiments, we demonstrate the efficiency and effectiveness of our proposed approaches over both real and synthetic datasets. In summary, our methods can achieve 3% ∼ 10% increase on overall revenue without sacrificing on running speed compared with the state-of-the-art solutions. Copyright © 2021, The Authors. All rights reserved.

关键词： Queueing theory

来源：评论

学校读者我要写书评

暂无评论

Virtual Reality: A Survey of Enabling Technologies and its Applications in IoT

arXiv

引用

arXiv 2021年

作者： Hu, Miao Luo, Xianzhuo Chen, Jiawen Lee, Young Choon Zhou, Yipeng Wu, Di School of Computer Science and Engineering Sun Yat-sen University Guangzhou510275 China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou510006 China Department of Computing Faculty of Science and Engineering Macquarie University SydneyNSW2109 Australia

Virtual Reality (VR) has shown great potential to revolutionize the market by providing users immersive experiences with freedom of movement. Compared to traditional video streaming, VR is with ultra high-definition and dynamically changes with users’ head and eye movements, which poses significant challenges for the realization of such potential. In this paper, we provide a detailed and systematic survey of enabling technologies of virtual reality and its applications in Internet of Things (IoT). We identify major challenges of virtual reality on system design, view prediction, computation, streaming, and quality of experience evaluation. We discuss each of them by extensively surveying and reviewing related papers in the recent years. We also introduce several use cases of VR for IoT. Last, issues and future research directions are also identified and discussed. Copyright © 2021, The Authors. All rights reserved.

关键词： Virtual reality

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：