Pub Date : 2026-01-09DOI: 10.1109/JPROC.2025.3646388
{"title":"IEEE Membership","authors":"","doi":"10.1109/JPROC.2025.3646388","DOIUrl":"https://doi.org/10.1109/JPROC.2025.3646388","url":null,"abstract":"","PeriodicalId":20556,"journal":{"name":"Proceedings of the IEEE","volume":"113 8","pages":"C3-C3"},"PeriodicalIF":25.9,"publicationDate":"2026-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11345494","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145929642","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-23DOI: 10.1109/JPROC.2025.3640442
Summary form only: Abstracts of articles presented in this issue of the publication.
仅以摘要形式提供：本刊发表的文章摘要。
{"title":"Scanning the Issue","authors":"","doi":"10.1109/JPROC.2025.3640442","DOIUrl":"https://doi.org/10.1109/JPROC.2025.3640442","url":null,"abstract":"Summary form only: Abstracts of articles presented in this issue of the publication.","PeriodicalId":20556,"journal":{"name":"Proceedings of the IEEE","volume":"113 7","pages":"610-612"},"PeriodicalIF":25.9,"publicationDate":"2025-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11313232","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145808597","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-23DOI: 10.1109/JPROC.2025.3631180
{"title":"Proceedings of the IEEE: Stay Informed. Become Inspired.","authors":"","doi":"10.1109/JPROC.2025.3631180","DOIUrl":"https://doi.org/10.1109/JPROC.2025.3631180","url":null,"abstract":"","PeriodicalId":20556,"journal":{"name":"Proceedings of the IEEE","volume":"113 7","pages":"C4-C4"},"PeriodicalIF":25.9,"publicationDate":"2025-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11313229","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145808582","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-23DOI: 10.1109/JPROC.2025.3631176
{"title":"Future Special Issues/Special Sections of the Proceedings","authors":"","doi":"10.1109/JPROC.2025.3631176","DOIUrl":"https://doi.org/10.1109/JPROC.2025.3631176","url":null,"abstract":"","PeriodicalId":20556,"journal":{"name":"Proceedings of the IEEE","volume":"113 7","pages":"707-707"},"PeriodicalIF":25.9,"publicationDate":"2025-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11313345","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145808638","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-23DOI: 10.1109/JPROC.2025.3642445
{"title":"TechRxiv","authors":"","doi":"10.1109/JPROC.2025.3642445","DOIUrl":"https://doi.org/10.1109/JPROC.2025.3642445","url":null,"abstract":"","PeriodicalId":20556,"journal":{"name":"Proceedings of the IEEE","volume":"113 7","pages":"708-708"},"PeriodicalIF":25.9,"publicationDate":"2025-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11313230","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145808572","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-23DOI: 10.1109/JPROC.2025.3631172
{"title":"Proceedings of the IEEE Publication Information","authors":"","doi":"10.1109/JPROC.2025.3631172","DOIUrl":"https://doi.org/10.1109/JPROC.2025.3631172","url":null,"abstract":"","PeriodicalId":20556,"journal":{"name":"Proceedings of the IEEE","volume":"113 7","pages":"C2-C2"},"PeriodicalIF":25.9,"publicationDate":"2025-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11313231","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145808605","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-23DOI: 10.1109/JPROC.2025.3631178
{"title":"IEEE Membership","authors":"","doi":"10.1109/JPROC.2025.3631178","DOIUrl":"https://doi.org/10.1109/JPROC.2025.3631178","url":null,"abstract":"","PeriodicalId":20556,"journal":{"name":"Proceedings of the IEEE","volume":"113 7","pages":"C3-C3"},"PeriodicalIF":25.9,"publicationDate":"2025-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11313227","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145808587","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-22DOI: 10.1109/JPROC.2025.3642972
Luís Crespo;Nuno Neves;Pedro Tomás;Nuno Roma
In the past few years, there has been a renewed effort to advance general-purpose architectures. In particular, to deliver performance and energy efficiency advantages, several techniques have been applied based on new forms of specialization while maintaining usability. As a result, data movement and communication have become the primary bottlenecks in computer systems. To overcome this, one of the most recent breakthroughs has been the introduction of data streaming mechanisms, just like those used in accelerators, into modern general-purpose processors (GPPs). This article comprehensively reviews stream-based architectures, tracing their development from accelerator solutions to their recent adoption in GPPs. This survey starts by introducing the fundamental principles of stream specialization, followed by a taxonomy for memory accesses, and formal mathematical models to represent them as data streams. Then, it categorizes different topologies of data stream specialization and examines them from a compiler’s perspective. Some of the most representative architectures proposed in the past few years, including instruction set architecture (ISA) and streaming engines, are described, followed by a comparative analysis that highlights their key features and presents quantitative evaluations. Then, we discuss some open challenges and suggest directions for future research in stream-based architectures.
{"title":"A Survey on Stream-Based Architectures: From Accelerators to CPUs","authors":"Luís Crespo;Nuno Neves;Pedro Tomás;Nuno Roma","doi":"10.1109/JPROC.2025.3642972","DOIUrl":"10.1109/JPROC.2025.3642972","url":null,"abstract":"In the past few years, there has been a renewed effort to advance general-purpose architectures. In particular, to deliver performance and energy efficiency advantages, several techniques have been applied based on new forms of specialization while maintaining usability. As a result, data movement and communication have become the primary bottlenecks in computer systems. To overcome this, one of the most recent breakthroughs has been the introduction of data streaming mechanisms, just like those used in accelerators, into modern general-purpose processors (GPPs). This article comprehensively reviews stream-based architectures, tracing their development from accelerator solutions to their recent adoption in GPPs. This survey starts by introducing the fundamental principles of stream specialization, followed by a taxonomy for memory accesses, and formal mathematical models to represent them as data streams. Then, it categorizes different topologies of data stream specialization and examines them from a compiler’s perspective. Some of the most representative architectures proposed in the past few years, including instruction set architecture (ISA) and streaming engines, are described, followed by a comparative analysis that highlights their key features and presents quantitative evaluations. Then, we discuss some open challenges and suggest directions for future research in stream-based architectures.","PeriodicalId":20556,"journal":{"name":"Proceedings of the IEEE","volume":"113 8","pages":"713-751"},"PeriodicalIF":25.9,"publicationDate":"2025-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145807786","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}
Pub Date : 2025-12-12DOI: 10.1109/jproc.2025.3638871
Matthieu Muller, Daniele Picone, Begüm Demir, Gustau Camps-Valls, Mauro Dalla Mura, Magnús Örn Úlfarsson, Jón Atli Benediktsson
{"title":"Hybrid Deep Learning Models for Remote Sensing Image Processing","authors":"Matthieu Muller, Daniele Picone, Begüm Demir, Gustau Camps-Valls, Mauro Dalla Mura, Magnús Örn Úlfarsson, Jón Atli Benediktsson","doi":"10.1109/jproc.2025.3638871","DOIUrl":"https://doi.org/10.1109/jproc.2025.3638871","url":null,"abstract":"","PeriodicalId":20556,"journal":{"name":"Proceedings of the IEEE","volume":"149 1","pages":""},"PeriodicalIF":20.6,"publicationDate":"2025-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145731344","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}
Neural networks have achieved remarkable success across various fields. However, the lack of interpretability limits their practical use, particularly in critical decision-making scenarios. Posthoc interpretability, which provides explanations for pretrained models, is often at risk of fidelity and robustness. This has inspired a rising interest in self-interpretable neural networks (SINNs), which inherently reveal the prediction rationale through model structures. Despite this progress, existing research remains fragmented, relying on intuitive designs tailored to specific tasks. To bridge these efforts and foster a unified framework, we first collect and review existing works on SINNs and provide a structured summary of their methodologies from five key perspectives: attribution-based, function-based, concept-based, prototype-based, and rule-based self-interpretation. We also present concrete, visualized examples of model explanations and discuss their applicability across diverse scenarios, including image, text, graph data, and deep reinforcement learning (DRL). Additionally, we summarize existing evaluation metrics for self-interpretation and identify open challenges in this field, offering insights for future research. To support ongoing developments, we present a publicly accessible resource to track advancements in this domain: https://github.com/yangji721/Awesome-Self-Interpretable-Neural-Network
{"title":"A Comprehensive Survey on Self-Interpretable Neural Networks","authors":"Yang Ji;Ying Sun;Yuting Zhang;Zhigaoyuan Wang;Yuanxin Zhuang;Zheng Gong;Dazhong Shen;Chuan Qin;Hengshu Zhu;Hui Xiong","doi":"10.1109/JPROC.2025.3635153","DOIUrl":"10.1109/JPROC.2025.3635153","url":null,"abstract":"Neural networks have achieved remarkable success across various fields. However, the lack of interpretability limits their practical use, particularly in critical decision-making scenarios. Posthoc interpretability, which provides explanations for pretrained models, is often at risk of fidelity and robustness. This has inspired a rising interest in self-interpretable neural networks (SINNs), which inherently reveal the prediction rationale through model structures. Despite this progress, existing research remains fragmented, relying on intuitive designs tailored to specific tasks. To bridge these efforts and foster a unified framework, we first collect and review existing works on SINNs and provide a structured summary of their methodologies from five key perspectives: attribution-based, function-based, concept-based, prototype-based, and rule-based self-interpretation. We also present concrete, visualized examples of model explanations and discuss their applicability across diverse scenarios, including image, text, graph data, and deep reinforcement learning (DRL). Additionally, we summarize existing evaluation metrics for self-interpretation and identify open challenges in this field, offering insights for future research. To support ongoing developments, we present a publicly accessible resource to track advancements in this domain: <uri>https://github.com/yangji721/Awesome-Self-Interpretable-Neural-Network</uri>","PeriodicalId":20556,"journal":{"name":"Proceedings of the IEEE","volume":"113 8","pages":"783-813"},"PeriodicalIF":25.9,"publicationDate":"2025-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145664821","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：