检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Ji, Zhong Hu, Junhua Liu, Deyin Wu, Lin Yuanbo Zhao, Ye The School of Electrical and Information Engineering Tianjin University Tianjin300072 China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Artificial Intelligence Anhui University Hefei230039 China Department of Computer Science Swansea University SA1 8EN United Kingdom The Key Laboratory of Knowledge Engineering with Big Data School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China

Text-based person search (TBPS) is of significant importance in intelligent surveillance, which aims to retrieve pedestrian images with high semantic relevance to a given text description. This retrieval task is characterized with both modal heterogeneity and fine-grained matching. To implement this task, one needs to extract multi-scale features from both image and text domains, and then perform the cross-modal alignment. However, most existing approaches only consider the alignment confined at their individual scales, e.g., an image-sentence or a region-phrase scale. Such a strategy adopts the presumable alignment in feature extraction, while overlooking the cross-scale alignment, e.g., image-phrase. In this paper, we present a transformer-based model to extract multi-scale representations, and perform Asymmetric Cross-Scale Alignment (ACSA) to precisely align the two modalities. Specifically, ACSA consists of a global-level alignment module and an asymmetric cross-attention module, where the former aligns an image and texts on a global scale, and the latter applies the cross-attention mechanism to dynamically align the cross-modal entities in region/image-phrase scales. Extensive experiments on two benchmark datasets CUHK-PEDES and RSTPReid demonstrate the effectiveness of our approach. Codes are available at https://***/mulhjh/ACSA. Copyright © 2022, The Authors. All rights reserved.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Elucidating Spatial Complex Structures from Mass Spectrometry Imaging with Deep Multimodal Model

Elucidating Spatial Complex Structures from Mass Spectrometr...

引用

Medical Artificial Intelligence (MedAI), IEEE International Conference on

作者： Jiangnan Cui Junjie Xia Xuan Li Yan Wang Fufang Qiu Yaochen Xu Keren Xu Chunman Zuo School of Computer Science and Technology Institute of Artificial Intelligence Donghua University Shanghai China Institute of Artificial Intelligence Donghua University Shanghai China College of Computer Science and Technology Jilin University Changchun China Department of Neurosurgery Huashan Hospital Shanghai China CAS Key Laboratory of Systems Biology Shanghai Institute of Biochemistry and Cell Biology Center for Excellence in Molecular Cell Science Chinese Academy of Sciences Shanghai China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China

Spatial mass spectrometry imaging (SMSI) technology has enabled the characterization of biomolecule patterns within the tissue microenvironment, yet its analyses suffer from substantial noise. The lack of effective methods for exploiting multi-view features (e.g., spatial location) has hindered their elucidation ability for tissue heterogeneity. Here, we propose MSG, a multimodal modal that integrates histology, spatial location, and MSI data, in deciphering tissue structure by graph neural network. Specifically, MSG learns low-dimensional representations by aggregating histomorphological features from neighboring tiles via graph attention autoencoder. MSG outperforms other methods in identifying spatial domains and denoising data. The subsequent domain-guided differential expression analysis of the denoised data enables the identification of ions with significantly enriched patterns within the recognized domains. MSG exhibits its versatility in handling SMSI data from various platforms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The superalignment of superhuman intelligence with large language models

引用

science China Information sciences 2025年第6期68卷

作者： Huang, Minlie Wang, Yingkang Cui, Shiyao Ke, Pei Tang, Jie The CoAI Group Department of Computer Science and Technology Tsinghua University Beijing100084 China Laboratory of Intelligent Collaborative Computing University of Electronic Science and Technology of China Chengdu611731 China Knowledge Engineering Group Department of Computer Science and Technology Tsinghua University Beijing100084 China

We have witnessed the emergence of superhuman intelligence thanks to the fast development of large language models (LLMs) and multimodal language models. As the application of such superhuman models becomes increasingly popular, a critical question arises: how can we ensure they still remain safe, reliable, and aligned well with human values encompassing moral values, Schwartz’s Values, ethics, and many more? In this position paper, we discuss the concept of superalignment from a learning perspective to answer this question by outlining the learning paradigm shift from large-scale pretraining and supervised fine-tuning, to alignment training. We define superalignment as designing effective and efficient alignment algorithms to learn from noisy-labeled data (point-wise samples or pair-wise preference data) in a scalable way when the task is very complex for human experts to annotate and when the model is stronger than human experts. We highlight some key research problems in superalignment, namely, weak-to-strong generalization, scalable oversight, and evaluation. We then present a conceptual framework for superalignment, which comprises three modules: an attacker which generates the adversary queries trying to expose the weaknesses of a learner model, a learner which refines itself by learning from scalable feedbacks generated by a critic model with minimal human experts, and a critic which generates critics or explanations for a given query-response pair, with a target of improving the learner by criticizing. We discuss some important research problems in each component of this framework and highlight some interesting research ideas that are closely related to our proposed framework, for instance, self-alignment, self-play, self-refinement, and more. Last, we highlight some future research directions for superalignment, including the identification of new emergent risks and multi-dimensional alignment. © science China Press 2025.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

BERST: An Engine and Tool for Exploring Biomedical Entities and Relationships

引用

Chinese Journal of Electronics 2019年第4期28卷 797-804页

作者： BAI Tian GE Yan YANG Changqing LIU Xiaohua GONG Leiguang WANG Ye HUANG Lan College of Computer Science and Technology Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Yantai Intelligent Information Technologies Ltd. Department of Computer Science and Technology Zhuhai College of Jilin University

To facilitate the search of rapidly growing biomedical knowledge in literature, we developed a Biomedical entity-relationship search tool(BERST). It is also a biomedical knowledge integration framework, which presently contains six popular databases represented in terms of a network of concepts and relations extracted from these knowledge sources. Users search the integrated knowledge network by entering keywords, and BERST returns a sub-network matching and representing the keywords and their relationships. The resulting graph can be navigated interactively allowing users to explore specific paths between any two nodes representing potentially interesting relationships between them. A graphical UI was developed to provide a more intuitive and overall view of the information being searched and studied. BERST framework can be naturally expanded to integrate other biomedical knowledge sources. BERST is implemented as a Java web application.

关键词： Biomedical ontology Relationship mining Relationship searching tool

来源：评论

学校读者我要写书评

暂无评论

Drive: An Adjustable Parallel Architecture Based on Evidence Awareness for Fake News Detection

SSRN

引用

SSRN 2024年

作者： Cong, Mou Liu, Lu Han, Jiayu Zhu, Beibei Yuan, Xiaosong Peng, Tao College of Computer Science and Technology Jilin University 2699 Qianjin Street Jilin Changchun130012 China College of Software Jilin University 2699 Qianjin Street Jilin Changchun130012 China Key Laboratory of Symbol Computation and Knowledge Engineering Ministry of Education Jilin University 2699 Qianjin Street Jilin Changchun130012 China Department of Linguistics University of Washington SeattleWA98195 United States

Fake news detection becomes a critical challenge in NLP. Batch processing with attention-derivative models is a popular solution for fake news detection. Models with attention mechanisms could mitigate the long-distance dependence problem. However, we find that extracting local dependencies using convolutional networks is as important as extracting global dependencies using attention mechanisms. Besides, fake news datasets often suffer from problems such as imbalance and are hard to understand by current models. To address these problems, we propose DRIVE, which is short for an adjustable parallel architecture based on evidence awareness for fake news detection to alleviate the above problems, in which we introduce Claim as a supporting clue to enhance the model’s comprehension ability. Specifically, we propose a novel method for unbalanced datasets and design adjustable parallel branches, using Claim Additives Network (ClaimAddNet) and the MLP with convolutional gating mechanism (CPMLP) to capture global and local information in distinct branches, respectively. Experiments conducted on 5 public datasets demonstrate that DRIVE outperforms all baselines, improving accuracy by approximately 1.7 %. Furthermore, we implement an anti-noise interference test and evaluate the weighted average of the two branches along with ablation studies. © 2024, The Authors. All rights reserved.

关键词： Parallel architectures

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Approach to Classify Biomedical Acoustic Features for Baby Cries

引用

Journal of Voice 2023年

作者： Aggarwal, Gaurav Jhajharia, Kavita Izhar, Jaweria Kumar, Manoj Abualigah, Laith Department of Information Technology and Engineering Amity University in Tashkent Uzbekistan Department of Information Technology Manipal University Jaipur India Department of Engineering and Information Sciences School of Computer Science FEIS University of Wollongong in Dubai Dubai Knowledge Park Dubai United Arab Emirates Department of Information Technology Al al-Bayt University Jordan and MEU Research Unit Faculty of Information Technology Middle East University Amman 11831 Jordan

Communication is imperative for living beings for exchanging information. But for newborns, the only way of communicating with the world is through crying, and it is the only medium through which caregivers can know about the needs of their children. Timely addressing baby cries is very important so that the child is relieved at the earliest. It has been a challenge, especially for new parents. The literature says newborn babies use The Dustan Baby Language to communicate. According to this language, there are five words to understand a baby's needs, which are “Neh” (hungry), “Eh” (burp is needed), “Owh/Oah” (fatigue), “Eair/Eargghh” (cramps), “Heh” (feel hot or wet, physical discomfort). This research aims to develop a model for recognizing baby cries and distinguishing between different kinds of baby cries. Here we more broadly focus on whether the infant is in pain due to hunger or discomfort. The study proposes a comparative approach using four classification models: random forest, support vector machine, logistic regression, and decision tree. These algorithms learn from the spectral features: chroma_stft, spectral_centroid, bandwidth, spectral_rolloff, mel-frequency cepstral coefficients, linear predictive coding, res, zero_crossing_rate extracted from the infant cry. The support vector machine model outperforms other classifiers for correctly classifying infant cries. © 2023 The Voice Foundation

关键词： Acoustic features Classification Cry Discomfort Hunger Spectral features SVM

来源：评论

学校读者我要写书评

暂无评论

Generative Classifier for Domain Generalization

arXiv

引用

arXiv 2025年

作者： Long, Shaocong Zhou, Qianyu Li, Xiangtai Ying, Chenhao Tong, Yunhai Ma, Lizhuang Luo, Yuan Tao, Dacheng Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China College of Computer Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun China Nanyang Technological University Singapore Peking University Beijing China

Domain generalization (DG) aims to improve the generalizability of computer vision models toward distribution shifts. The mainstream DG methods predominantly focus on learning domain invariance across domains, however, such methods overlook the untapped potential inherent in domain-specific information. While the prevailing practice of discriminative linear classifier has been tailored to domain-invariant features, it struggles when confronted with diverse domain-specific information, e.g., intra-class shifts, that exhibits multi-modality. To address these issues, we explore the theoretical implications of relying on domain-invariant features, revealing the crucial role of domain-specific information in mitigating the target risk for DG. Drawing from these insights, we propose Generative Classifier-driven Domain Generalization (GCDG), introducing a generative paradigm for the DG classifier based on Gaussian Mixture Models (GMMs) for each class across domains. GCDG consists of three key modules: Heterogeneity Learning Classifier (HLC), Spurious Correlation Blocking (SCB), and Diverse Component Balancing (DCB). Concretely, HLC attempts to model the feature distributions and thereby capture valuable domain-specific information via GMMs. SCB identifies the neural units containing spurious correlations and perturbs them, mitigating the risk of HLC learning irrelevant spurious patterns. Meanwhile, DCB ensures a balanced contribution of components within HLC, preventing the underestimation or neglect of critical components. In this way, GCDG excels in capturing the nuances of domain-specific information characterized by diverse distributions. GCDG demonstrates the potential to reduce the target risk and encourage flat minima, improving the model’s generalizability. Extensive experiments show GCDG’s comparable performance on five DG benchmarks and one face anti-spoofing dataset, seamlessly integrating into existing DG methods with consistent improvements. Code will be avail

关键词： Discriminant analysis

来源：评论

学校读者我要写书评

暂无评论

RPR-Net: A Point Cloud-based Rotation-aware Large Scale Place Recognition Network

arXiv

引用

arXiv 2021年

作者： Fan, Zhaoxin Song, Zhenbo Zhang, Wenping Liu, Hongyan He, Jun Du, Xiaoyong Key Laboratory of Data Engineering and Knowledge Engineering of MOE School of Information Renmin University of China Beijing100872 China Department of Management Science and Engineering Tsinghua University Beijing100084 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China

Point cloud-based large scale place recognition is an important but challenging task for many applications such as Simultaneous Localization and Mapping (SLAM). Taking the task as a point cloud retrieval problem, previous methods have made delightful achievements. However, how to deal with catastrophic collapse caused by rotation problems is still under-explored. In this paper, to tackle the issue, we propose a novel Point Cloud-based Rotation-aware Large Scale Place Recognition Network (RPR-Net). In particular, to solve the problem, we propose to learn rotation-invariant features in three steps. First, we design three kinds of novel Rotation-Invariant Features (RIFs), which are low-level features that can hold the rotation-invariant property. Second, using these RIFs, we design an attentive module to learn rotation-invariant kernels. Third, we apply these kernels to previous point cloud features to generate new features, which is the well-known SO(3) mapping process. By doing so, high-level scene-specific rotation-invariant features can be learned. We call the above process an Attentive Rotation-Invariant Convolution (ARIConv). To achieve the place recognition goal, we build RPR-Net, which takes ARIConv as a basic unit to construct a dense network architecture. Then, powerful global descriptors used for retrieval-based place recognition can be sufficiently extracted from RPR-Net. Experimental results on prevalent datasets show that our method achieves comparable results to existing state-of-the-art place recognition models and significantly outperforms other rotation-invariant baseline models when solving rotation problems. Copyright © 2021, The Authors. All rights reserved.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Secure storage allocation scheme using fuzzy based heuristic algorithm for cloud

引用

Journal of Ambient Intelligence and Humanized Computing 2020年第5期12卷 5609-5617页

作者： Sivaram, M. Kaliappan, M. Shobana, S. Jeya Prakash, M. Viju Porkodi, V. Vijayalakshmi, K. Vimal, S. Suresh, A. Department of Computer Networking College of Engineering and Computer Science Lebanese French University Erbil Iraq Department of Computer Science and Engineering Ramco Institute of Technology Rajapalayam India Department of Computer Science College of Science Knowledge University Erbil Iraq Department of Information Technology College of Engineering and Computer Science Lebanese French University Erbil Iraq Department of Information Technology National Engineering College Kovilpatti India Department of Computer Science and Engineering Nehru Institute of Engineering and Technology Coimbatore India

Cloud computing is a paradigm in the modern era for the development of secure storage and secure job scheduling process in a cloud-based system. The cloud technology provides a user interface in the sense of raw data management with the relational databases to improve flexibility and scalability. Fuzzy-based Heuristic algorithm is proposed for secure storage allocation in a cloud environment. In this work, client systems are clustered using a fuzzy-based rule mechanism. The server generates a distributed public key using RSA for ensuring security and resolve memory recycling issues. It enhances the usage of the client over the cloud data storage in secure manner. It also improves the efficiency of data storage globally by implementing heuristic techniques. The K-nearest neighbors approach is used for efficient query searching for data storage in the clusters by the client. The proposed load-balanced scheduling approach enhances power consumption and efficiency. In the simulation, the results reveal that the proposed scheme provides better performance than existing approaches in terms of load balancing with security.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sequential Solutions in Machine Scheduling Games 16th

Sequential Solutions in Machine Scheduling Games

引用

16th International Conference on Web and Internet Economics, WINE 2020

作者： Chen, Cong Giessler, Paul Mamageishvili, Akaki Mihalák, Matúš Penna, Paolo School of Business Administration South China University of Technology Guangzhou China Department of Data Science and Knowledge Engineering Maastricht University Maastricht Netherlands Department of Management Technology and Economics ETH Zurich Zurich Switzerland Department of Computer Science ETH Zurich Zurich Switzerland

ISBN: (纸本)9783030649456

We consider the classical machine scheduling, where n jobs need to be scheduled on m machines, and where job j scheduled on machine i contributes pi,j∈ R to the load of machine i, with the goal of minimizing the makespan, i.e., the maximum load of any machine in the schedule. We study inefficiency of schedules that are obtained when jobs arrive sequentially one by one, and the jobs choose themselves the machine on which they will be scheduled, aiming at being scheduled on a machine with small load. We measure the inefficiency of a schedule as the ratio of the makespan obtained in the worst-case equilibrium schedule, and of the optimum makespan. This ratio is known as the sequential price of anarchy (SPoA). We also introduce two alternative inefficiency measures, which allow for a favorable choice of the order in which the jobs make their decisions. As our first result, we disprove the conjecture of [22] claiming that the sequential price of anarchy for m= 2 machines is at most 3. We show that the sequential price of anarchy grows at least linearly with the number n of players, assuming arbitrary tie-breaking rules. That is, we show SPoA∈ Ω(n). Complementing this result, we show that SPoA∈ O(n), reducing previously known exponential bound for 2 machines. Furthermore, we show that there exists an order of the jobs, resulting in makespan that is at most linearly larger than the optimum makespan. To the end, we show that if an authority can change the order of the jobs adaptively to the decisions made by the jobs so far (but cannot influence the decisions of the jobs), then there exists an adaptive ordering in which the jobs end up in an optimum schedule. © 2020, Springer Nature Switzerland AG.

关键词： Scheduling

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：