Yi Liu, Changsheng Zhang, Xingjun Dong, Jiaxu Ning
With the rapid development of 3D acquisition technology, point clouds have received increasing attention. In recent years, point cloud-based deep learning has been applied to various industrial scenarios, promoting industrial intelligence. However, there is still a lack of review on the application of point cloud-based deep learning in industrial production. To bridge this gap and inspire future research, this paper provides a review of current point cloud-based deep learning methods applied to industrial production from the perspective of different application scenarios, including pose estimation, defect inspection, measurement and estimation, etc. Considering the real-time requirement of industrial production, this paper also summarizes real-time point cloud-based deep learning methods in each application scenario. Then, this paper introduces commonly used evaluation metrics and public industrial point cloud datasets. Finally, from the aspects of the dataset, speed and industrial product specificity, the challenges faced by current point cloud-based deep learning methods in industrial production are discussed, and future research directions are prospected.
{"title":"Point Cloud-Based Deep Learning in Industrial Production: A Survey","authors":"Yi Liu, Changsheng Zhang, Xingjun Dong, Jiaxu Ning","doi":"10.1145/3715851","DOIUrl":"https://doi.org/10.1145/3715851","url":null,"abstract":"With the rapid development of 3D acquisition technology, point clouds have received increasing attention. In recent years, point cloud-based deep learning has been applied to various industrial scenarios, promoting industrial intelligence. However, there is still a lack of review on the application of point cloud-based deep learning in industrial production. To bridge this gap and inspire future research, this paper provides a review of current point cloud-based deep learning methods applied to industrial production from the perspective of different application scenarios, including pose estimation, defect inspection, measurement and estimation, etc. Considering the real-time requirement of industrial production, this paper also summarizes real-time point cloud-based deep learning methods in each application scenario. Then, this paper introduces commonly used evaluation metrics and public industrial point cloud datasets. Finally, from the aspects of the dataset, speed and industrial product specificity, the challenges faced by current point cloud-based deep learning methods in industrial production are discussed, and future research directions are prospected.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"121 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143050684","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Despite recent increase in research on improvement of non-functional properties of software, such as energy usage or program size, there is a lack of standard benchmarks for such work. This absence hinders progress in the field, and raises questions about the representativeness of current benchmarks of real-world software. To address these issues and facilitate further research on improvement of non-functional properties of software, we conducted a comprehensive survey on the benchmarks used in the field thus far. We searched five major online repositories of research work, collecting 5499 publications (4066 unique), and systematically identified relevant papers to construct a rich and diverse corpus of 425 relevant studies. We find that execution time is the most frequently improved property in research work (63%), while multi-objective improvement is rarely considered (7%). Static approaches for improvement of non-functional software properties are prevalent (51%), with exploratory approaches (18% evolutionary and 15% non-evolutionary) increasingly popular in the last 10 years. Only 39% of the 425 papers describe work that uses benchmark suites, rather than single software, of those SPEC is most popular (63 papers). We also provide recommendations for future work, noting, for instance, lack of benchmarks for non-functional improvement that covers Python, JavaScript, or mobile devices. All the details regarding the 425 identified papers are available on our dedicated webpage: https://bloa.github.io/nfunc_survey.
{"title":"A Comprehensive Survey of Benchmarks for Improvement of Software's Non-Functional Properties","authors":"Aymeric Blot, Justyna Petke","doi":"10.1145/3711119","DOIUrl":"https://doi.org/10.1145/3711119","url":null,"abstract":"Despite recent increase in research on improvement of non-functional properties of software, such as energy usage or program size, there is a lack of standard benchmarks for such work. This absence hinders progress in the field, and raises questions about the representativeness of current benchmarks of real-world software. To address these issues and facilitate further research on improvement of non-functional properties of software, we conducted a comprehensive survey on the benchmarks used in the field thus far. We searched five major online repositories of research work, collecting 5499 publications (4066 unique), and systematically identified relevant papers to construct a rich and diverse corpus of 425 relevant studies. We find that execution time is the most frequently improved property in research work (63%), while multi-objective improvement is rarely considered (7%). Static approaches for improvement of non-functional software properties are prevalent (51%), with exploratory approaches (18% evolutionary and 15% non-evolutionary) increasingly popular in the last 10 years. Only 39% of the 425 papers describe work that uses benchmark suites, rather than single software, of those SPEC is most popular (63 papers). We also provide recommendations for future work, noting, for instance, lack of benchmarks for non-functional improvement that covers Python, JavaScript, or mobile devices. All the details regarding the 425 identified papers are available on our dedicated webpage: https://bloa.github.io/nfunc_survey.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"20 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143050573","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Vasileios Leon, Muhammad Abdullah Hanif, Giorgos Armeniakos, Xun Jiao, Muhammad Shafique, Kiamal Pekmestzi, Dimitrios Soudris
The challenging deployment of compute-intensive applications from domains such as Artificial Intelligence (AI) and Digital Signal Processing (DSP), forces the community of computing systems to explore new design approaches. Approximate Computing appears as an emerging solution, allowing to tune the quality of results in the design of a system in order to improve the energy efficiency and/or performance. This radical paradigm shift has attracted interest from both academia and industry, resulting in significant research on approximation techniques and methodologies at different design layers (from system down to integrated circuits). Motivated by the wide appeal of Approximate Computing over the last 10 years, we conduct a two-part survey to cover key aspects (e.g., terminology and applications) and review the state-of-the art approximation techniques from all layers of the traditional computing stack. Part II of the survey classifies and presents the technical details of application-specific and architectural approximation techniques, which both target the design of resource-efficient processors/accelerators and systems. Moreover, it reports a quantitative analysis of the techniques and a detailed analysis of the application spectrum of Approximate Computing, and finally, it discusses open challenges and future directions.
{"title":"Approximate Computing Survey, Part II: Application-Specific & Architectural Approximation Techniques and Applications","authors":"Vasileios Leon, Muhammad Abdullah Hanif, Giorgos Armeniakos, Xun Jiao, Muhammad Shafique, Kiamal Pekmestzi, Dimitrios Soudris","doi":"10.1145/3711683","DOIUrl":"https://doi.org/10.1145/3711683","url":null,"abstract":"The challenging deployment of compute-intensive applications from domains such as Artificial Intelligence (AI) and Digital Signal Processing (DSP), forces the community of computing systems to explore new design approaches. <jats:italic>Approximate Computing</jats:italic> appears as an emerging solution, allowing to tune the quality of results in the design of a system in order to improve the energy efficiency and/or performance. This radical paradigm shift has attracted interest from both academia and industry, resulting in significant research on approximation techniques and methodologies at different design layers (from system down to integrated circuits). Motivated by the wide appeal of Approximate Computing over the last 10 years, we conduct a two-part survey to cover key aspects (e.g., terminology and applications) and review the state-of-the art approximation techniques from all layers of the traditional computing stack. Part II of the survey classifies and presents the technical details of application-specific and architectural approximation techniques, which both target the design of resource-efficient processors/accelerators and systems. Moreover, it reports a quantitative analysis of the techniques and a detailed analysis of the application spectrum of Approximate Computing, and finally, it discusses open challenges and future directions.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"10 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143050722","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Adaptive schemes in physical layer security, designed to dynamically respond to the evolving conditions of wireless channels, play a crucial role in fortifying the security of wireless communication systems. We offer a thorough analysis of the current state of research on adaptive schemes in physical layer security, introducing a novel taxonomy to categorize and understand these schemes more effectively. A detailed comparison is drawn between the insights provided in this survey and those from the literature, highlighting the unique contributions of our work. We delve into the contributions and challenges associated with various adaptive schemes, providing valuable lessons and summaries to guide further research. The future research directions of the adaptive scheme are discussed in Part 2 of the Appendix, aiming to address the current and emerging demands of wireless communication systems. Through this survey, we aim to enrich the discourse on adaptive schemes in physical layer security, paving the way for advanced research and development in enhancing the security of wireless networks.
{"title":"Adaptive Strategies in Enhancing Physical Layer Security: A Comprehensive Survey","authors":"Zhuoying Duan, Zikai Chang, Ning Xie, Weize Sun, Dusit (Tao) Niyato","doi":"10.1145/3715319","DOIUrl":"https://doi.org/10.1145/3715319","url":null,"abstract":"Adaptive schemes in physical layer security, designed to dynamically respond to the evolving conditions of wireless channels, play a crucial role in fortifying the security of wireless communication systems. We offer a thorough analysis of the current state of research on adaptive schemes in physical layer security, introducing a novel taxonomy to categorize and understand these schemes more effectively. A detailed comparison is drawn between the insights provided in this survey and those from the literature, highlighting the unique contributions of our work. We delve into the contributions and challenges associated with various adaptive schemes, providing valuable lessons and summaries to guide further research. The future research directions of the adaptive scheme are discussed in Part 2 of the Appendix, aiming to address the current and emerging demands of wireless communication systems. Through this survey, we aim to enrich the discourse on adaptive schemes in physical layer security, paving the way for advanced research and development in enhancing the security of wireless networks.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"84 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143050575","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Large Language Models (LLMs) have emerged as a transformative power in enhancing natural language comprehension, representing a significant stride toward artificial general intelligence. The application of LLMs extends beyond conventional linguistic boundaries, encompassing specialized linguistic systems developed within various scientific disciplines. This growing interest has led to the advent of scientific LLMs, a novel subclass specifically engineered for facilitating scientific discovery. As a burgeoning area in the community of AI for Science, scientific LLMs warrant comprehensive exploration. However, a systematic and up-to-date survey introducing them is currently lacking. In this paper, we endeavor to methodically delineate the concept of “scientific language”, whilst providing a thorough review of the latest advancements in scientific LLMs. Given the expansive realm of scientific disciplines, our analysis adopts a focused lens, concentrating on the biological and chemical domains. This includes an in-depth examination of LLMs for textual knowledge, small molecules, macromolecular proteins, genomic sequences, and their combinations, analyzing them in terms of model architectures, capabilities, datasets, and evaluation. Finally, we critically examine the prevailing challenges and point out promising research directions along with the advances of LLMs. By offering a comprehensive overview of technical developments in this field, this survey aspires to be an invaluable resource for researchers navigating the intricate landscape of scientific LLMs.
{"title":"Scientific Large Language Models: A Survey on Biological & Chemical Domains","authors":"Qiang Zhang, Keyan Ding, Tianwen Lv, Xinda Wang, Qingyu Yin, Yiwen Zhang, Jing Yu, Yuhao Wang, Xiaotong Li, Zhuoyi Xiang, Xiang Zhuang, Zeyuan Wang, Ming Qin, Mengyao Zhang, Jinlu Zhang, Jiyu Cui, Renjun Xu, Hongyang Chen, Xiaohui Fan, Huabin Xing, Huajun Chen","doi":"10.1145/3715318","DOIUrl":"https://doi.org/10.1145/3715318","url":null,"abstract":"Large Language Models (LLMs) have emerged as a transformative power in enhancing natural language comprehension, representing a significant stride toward artificial general intelligence. The application of LLMs extends beyond conventional linguistic boundaries, encompassing specialized linguistic systems developed within various scientific disciplines. This growing interest has led to the advent of scientific LLMs, a novel subclass specifically engineered for facilitating scientific discovery. As a burgeoning area in the community of AI for Science, scientific LLMs warrant comprehensive exploration. However, a systematic and up-to-date survey introducing them is currently lacking. In this paper, we endeavor to methodically delineate the concept of “scientific language”, whilst providing a thorough review of the latest advancements in scientific LLMs. Given the expansive realm of scientific disciplines, our analysis adopts a focused lens, concentrating on the biological and chemical domains. This includes an in-depth examination of LLMs for textual knowledge, small molecules, macromolecular proteins, genomic sequences, and their combinations, analyzing them in terms of model architectures, capabilities, datasets, and evaluation. Finally, we critically examine the prevailing challenges and point out promising research directions along with the advances of LLMs. By offering a comprehensive overview of technical developments in this field, this survey aspires to be an invaluable resource for researchers navigating the intricate landscape of scientific LLMs.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"119 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143044206","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Blockchain applications have emerged in recent decades, among which blockchain secured-networks serve as a prevalent application. This paper provides the potential of networks secured by blockchain technology to enhance various domains and provides a structured view of the current landscape of blockchain applications, capturing the practical applications and potential of blockchain technology. Followed by a background overview, a survey analysis of the latest advancements in blockchain-secured networks is presented, categorized by six application fields: Vehicular Ad-Hoc, Health Care, Smart Home, Unmanned Aerial Vehicle (UAV), Internet of Things (IoT), and Industrial IoT Networks. An in-depth discussion on these key research topics within blockchain-secured networks is provided, enhancing understanding of their application and influence across multiple disciplines. The study overall conveys the versatility of blockchain-secured networks, highlighting their immense potential for application in various practical fields. A comprehensive structured survey analysis of recent advancements in blockchain-secured networks is conducted, and categorized by application fields. By providing a comprehensive understanding of the current trends in blockchain application, this paper enables readers to navigate information effectively and identify key areas of interest, facilitating further exploration and research opportunities in the field of blockchain technology.
{"title":"Secured Network Architectures Based on Blockchain Technologies: A Systematic Review","authors":"Song-Kyoo Kim, Hou Cheng Vong","doi":"10.1145/3715000","DOIUrl":"https://doi.org/10.1145/3715000","url":null,"abstract":"Blockchain applications have emerged in recent decades, among which blockchain secured-networks serve as a prevalent application. This paper provides the potential of networks secured by blockchain technology to enhance various domains and provides a structured view of the current landscape of blockchain applications, capturing the practical applications and potential of blockchain technology. Followed by a background overview, a survey analysis of the latest advancements in blockchain-secured networks is presented, categorized by six application fields: Vehicular Ad-Hoc, Health Care, Smart Home, Unmanned Aerial Vehicle (UAV), Internet of Things (IoT), and Industrial IoT Networks. An in-depth discussion on these key research topics within blockchain-secured networks is provided, enhancing understanding of their application and influence across multiple disciplines. The study overall conveys the versatility of blockchain-secured networks, highlighting their immense potential for application in various practical fields. A comprehensive structured survey analysis of recent advancements in blockchain-secured networks is conducted, and categorized by application fields. By providing a comprehensive understanding of the current trends in blockchain application, this paper enables readers to navigate information effectively and identify key areas of interest, facilitating further exploration and research opportunities in the field of blockchain technology.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"21 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143035152","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Omar Jarkas, Ryan Ko, Naipeng Dong, Redowan Mahmud
Containerization significantly boosts cloud computing efficiency by reducing resource consumption, enhancing scalability, and simplifying orchestration. Yet, these same features introduce notable security vulnerabilities due to the shared Linux kernel and reduced isolation compared to traditional virtual machines (VMs). This architecture, while resource-efficient, increases susceptibility to software vulnerabilities, exposing containers to potential breaches; a single kernel vulnerability could compromise all containers on the same host. Existing academic research on container security is often theoretical and lacks empirical data on the nature of attacks, exploits, and vulnerabilities. Studies that do look at vulnerabilities often focus on specific types. This lack of detailed data and breadth hampers the development of effective mitigation strategies and restricts insights into the inherent weaknesses of containers. To address these gaps, our study introduces a novel taxonomy integrating academic knowledge with industry insights and real-world vulnerabilities, creating a comprehensive and actionable framework for container security. We analyzed over 200 container-related vulnerabilities, categorizing them into 47 exploit types across 11 distinct attack vectors. This taxonomy not only advances theoretical understanding but also facilitates the identification of vulnerabilities and the implementation of effective mitigation strategies in containerized environments. Our approach enhances the resilience of these environments by mapping vulnerabilities to their corresponding exploits and mitigation strategies, especially in complex, multi-tenant cloud settings. By providing actionable insights, our taxonomy helps practitioners enhance container security. Our findings have identified critical areas for further investigation, thereby laying a comprehensive foundation for future research and improving container security in cloud environments.
{"title":"A Container Security Survey: Exploits, Attacks, and Defenses","authors":"Omar Jarkas, Ryan Ko, Naipeng Dong, Redowan Mahmud","doi":"10.1145/3715001","DOIUrl":"https://doi.org/10.1145/3715001","url":null,"abstract":"Containerization significantly boosts cloud computing efficiency by reducing resource consumption, enhancing scalability, and simplifying orchestration. Yet, these same features introduce notable security vulnerabilities due to the shared Linux kernel and reduced isolation compared to traditional virtual machines (VMs). This architecture, while resource-efficient, increases susceptibility to software vulnerabilities, exposing containers to potential breaches; a single kernel vulnerability could compromise all containers on the same host. Existing academic research on container security is often theoretical and lacks empirical data on the nature of attacks, exploits, and vulnerabilities. Studies that do look at vulnerabilities often focus on specific types. This lack of detailed data and breadth hampers the development of effective mitigation strategies and restricts insights into the inherent weaknesses of containers. To address these gaps, our study introduces a novel taxonomy integrating academic knowledge with industry insights and real-world vulnerabilities, creating a comprehensive and actionable framework for container security. We analyzed over 200 container-related vulnerabilities, categorizing them into 47 exploit types across 11 distinct attack vectors. This taxonomy not only advances theoretical understanding but also facilitates the identification of vulnerabilities and the implementation of effective mitigation strategies in containerized environments. Our approach enhances the resilience of these environments by mapping vulnerabilities to their corresponding exploits and mitigation strategies, especially in complex, multi-tenant cloud settings. By providing actionable insights, our taxonomy helps practitioners enhance container security. Our findings have identified critical areas for further investigation, thereby laying a comprehensive foundation for future research and improving container security in cloud environments.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"56 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143035153","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The availability of smart devices leads to an exponential increase in multimedia content. However, advancements in deep learning have also enabled the creation of highly sophisticated deepfake content, including speech Deepfakes, which pose a serious threat by generating realistic voices and spreading misinformation. To combat this, numerous challenges have been organized to advance speech Deepfake detection techniques. In this survey, we systematically analyze more than 200 papers published up to March 2024. We provide a comprehensive review of each component in the detection pipeline, including model architectures, optimization techniques, generalizability, evaluation metrics, performance comparisons, available datasets, and open-source availability. For each aspect, we assess recent progress and discuss ongoing challenges. In addition, we explore emerging topics such as partial Deepfake detection, cross-dataset evaluation, and defences against adversarial attacks, while suggesting promising research directions. This survey not only identifies the current state-of-the-art to establish strong baselines for future experiments but also offers clear guidance for researchers aiming to enhance speech Deepfake detection systems.
{"title":"A Survey on Speech Deepfake Detection","authors":"Menglu Li, Yasaman Ahmadiadli, Xiao-Ping Zhang","doi":"10.1145/3714458","DOIUrl":"https://doi.org/10.1145/3714458","url":null,"abstract":"The availability of smart devices leads to an exponential increase in multimedia content. However, advancements in deep learning have also enabled the creation of highly sophisticated deepfake content, including speech Deepfakes, which pose a serious threat by generating realistic voices and spreading misinformation. To combat this, numerous challenges have been organized to advance speech Deepfake detection techniques. In this survey, we systematically analyze more than 200 papers published up to March 2024. We provide a comprehensive review of each component in the detection pipeline, including model architectures, optimization techniques, generalizability, evaluation metrics, performance comparisons, available datasets, and open-source availability. For each aspect, we assess recent progress and discuss ongoing challenges. In addition, we explore emerging topics such as partial Deepfake detection, cross-dataset evaluation, and defences against adversarial attacks, while suggesting promising research directions. This survey not only identifies the current state-of-the-art to establish strong baselines for future experiments but also offers clear guidance for researchers aiming to enhance speech Deepfake detection systems.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"2 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143031012","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
visual reasoning (AVR) domain encompasses problems solving which requires the ability to reason about relations among entities present in a given scene. While humans, generally, solve AVR tasks in a “natural” way, even without prior experience, this type of problems has proven difficult for current machine learning systems. The paper summarises recent progress in applying deep learning methods to solving AVR problems, as a proxy for studying machine intelligence. We focus on the most common type of AVR tasks—the Raven’s Progressive Matrices (RPMs)—and provide a comprehensive review of the learning methods and deep neural models applied to solve RPMs, as well as present the RPM benchmark sets. Performance analysis of the state-of-the-art approaches to solving RPMs leads to formulation of certain insights and remarks on the current and future trends in this area. We also attempt to put RPM studies in a more general perspective and demonstrate how real-world problems from the outside of AVR area can benefit from the presented research.
{"title":"Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices","authors":"Mikołaj Małkiński, Jacek Mańdziuk","doi":"10.1145/3715093","DOIUrl":"https://doi.org/10.1145/3715093","url":null,"abstract":"visual reasoning (AVR) domain encompasses problems solving which requires the ability to reason about relations among entities present in a given scene. While humans, generally, solve AVR tasks in a “natural” way, even without prior experience, this type of problems has proven difficult for current machine learning systems. The paper summarises recent progress in applying deep learning methods to solving AVR problems, as a proxy for studying machine intelligence. We focus on the most common type of AVR tasks—the Raven’s Progressive Matrices (RPMs)—and provide a comprehensive review of the learning methods and deep neural models applied to solve RPMs, as well as present the RPM benchmark sets. Performance analysis of the state-of-the-art approaches to solving RPMs leads to formulation of certain insights and remarks on the current and future trends in this area. We also attempt to put RPM studies in a more general perspective and demonstrate how real-world problems from the outside of AVR area can benefit from the presented research.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"13 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143031006","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Public permissionless blockchains facilitate peer-to-peer digital transactions, yet face performance challenges, specifically minimizing transaction confirmation time to decrease energy and time consumption per transaction. Performance evaluation and prediction is crucial in achieving this objective, with performance modeling as a key solution despite the complexities involved in assessing these blockchains. This survey examines prior research concerning the systems used to model blockchain performance, specifically focusing on public permissionless blockchains. Initially, it provides foundational knowledge about these blockchains and the crucial performance parameters for their assessment. Additionally, the study delves into research on the performance modeling of public permissionless blockchains, predominantly considering these systems as bulk service queues. It also examines prior studies on workload and traffic modeling, characterization, and analysis within these blockchain networks. By analyzing existing research, our survey aims to provide insights and recommendations for researchers keen on enhancing the performance of public permissionless blockchains or devising novel mechanisms in this domain.
{"title":"Performance Modeling of Public Permissionless Blockchains: A Survey","authors":"Molud Esmaili, Ken Christensen","doi":"10.1145/3715094","DOIUrl":"https://doi.org/10.1145/3715094","url":null,"abstract":"Public permissionless blockchains facilitate peer-to-peer digital transactions, yet face performance challenges, specifically minimizing transaction confirmation time to decrease energy and time consumption per transaction. Performance evaluation and prediction is crucial in achieving this objective, with performance modeling as a key solution despite the complexities involved in assessing these blockchains. This survey examines prior research concerning the systems used to model blockchain performance, specifically focusing on public permissionless blockchains. Initially, it provides foundational knowledge about these blockchains and the crucial performance parameters for their assessment. Additionally, the study delves into research on the performance modeling of public permissionless blockchains, predominantly considering these systems as bulk service queues. It also examines prior studies on workload and traffic modeling, characterization, and analysis within these blockchain networks. By analyzing existing research, our survey aims to provide insights and recommendations for researchers keen on enhancing the performance of public permissionless blockchains or devising novel mechanisms in this domain.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"13 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143031005","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：