计算机科学最新文献_第3页

Adapt or Wait: Quality Adaptation for Cache-aided Channels

IF 8.3 2区计算机科学

IEEE Transactions on Communications Pub Date : 2024-12-24 DOI: 10.1109/tcomm.2024.3522040

Eleftherios Lampiris, Giuseppe Caire

引用次数: 0

TactGen: Tactile Sensory Data Generation via Zero-Shot Sim-to-Real Transfer

IF 7.8 1区计算机科学

IEEE Transactions on Robotics Pub Date : 2024-12-24 DOI: 10.1109/tro.2024.3521967

Shaohong Zhong, Alessandro Albini, Perla Maiolino, Ingmar Posner

引用次数: 0

Task-Driven Detection of Distribution Shifts with Statistical Guarantees for Robot Learning

IF 7.8 1区计算机科学

IEEE Transactions on Robotics Pub Date : 2024-12-24 DOI: 10.1109/tro.2024.3521963

Alec Farid, Sushant Veer, Divyanshu Pachisia, Anirudha Majumdar

引用次数: 0

Hierarchical Banzhaf Interaction for General Video-Language Representation Learning

IF 23.6 1区计算机科学

IEEE Transactions on Pattern Analysis and Machine Intelligence Pub Date : 2024-12-24 DOI: 10.1109/tpami.2024.3522124

Peng Jin, Hao Li, Li Yuan, Shuicheng Yan, Jie Chen

引用次数: 0

Scheduling Phase Period Design for Sub-6 GHz Assisted Millimeter Wave Vehicle-to-Everything (V2X) Communication Scheduler

IF 6.8 2区计算机科学

IEEE Transactions on Vehicular Technology Pub Date : 2024-12-24 DOI: 10.1109/tvt.2024.3521941

Chenyuan He, Zhouyu Zhang, Yingfeng Cai, Hai Wang, Long Chen, Fenghua Huang

引用次数: 0

Neural Network-Based Nonlinear Stabilizing Control for 3-D Offshore Crane With Double-Pendulum Effect

IF 5.6 2区计算机科学

IEEE Transactions on Automation Science and Engineering Pub Date : 2024-12-24 DOI: 10.1109/tase.2024.3516873

Ling Yang, Gang Li, Xin Ma

引用次数: 0

RALACs: Action Recognition in Autonomous Vehicles Using Interaction Encoding and Optical Flow

IF 11.8 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2024-12-24 DOI: 10.1109/tcyb.2024.3515104

Eddy Zhou, Owen Leather, Alex Zhuang, Alikasim Budhwani, Rowan Dempster, Quanquan Li, Mohammad Al-Sharman, Derek Rayside, William Melek

引用次数: 0

Facebook vs Twitter: the differential relationship with mass attitudes about democracy in Latin Americas

IF 5.9 3区管理学

Internet Research Pub Date : 2024-12-24 DOI: 10.1108/intr-09-2023-0850

Richard Kornrumpf, Jason Gainous, Kevin M. Wagner, Tricia J. Gray

{"title":"Facebook vs Twitter: the differential relationship with mass attitudes about democracy in Latin Americas","authors":"Richard Kornrumpf, Jason Gainous, Kevin M. Wagner, Tricia J. Gray","doi":"10.1108/intr-09-2023-0850","DOIUrl":"https://doi.org/10.1108/intr-09-2023-0850","url":null,"abstract":"<h3>Purpose</h3>\u0000<p>We argue that the information flow on Twitter is largely driven by elite communication with a top-down flow, while Facebook’s bottom-up flow is driven by mass public communication. Both are crucial news sources for democratic processes in Latin America. We explore how exposure to these flows affects opinions on democracy across 18 countries with varying democratic conditions.</p>\u0000<h3>Design/methodology/approach</h3>\u0000<p>Using mixed-effects models, our analysis draws on survey data from the 2018 Latinobarómetro paired with democracy measures from the 2018 Varieties of Democracy.</p>\u0000<h3>Findings</h3>\u0000<p>The results indicate that Facebook’s bottom-up communication correlates with negative perceptions of democracy, whereas Twitter’s top-down model correlates with more favorable views, especially among mass consumers. However, these differences are inconsistent across demographic factors.</p>\u0000<h3>Research limitations/implications</h3>\u0000<p>Cross-sectional survey data limits causal claims. Longitudinal data could provide stronger insights into the mechanisms underlying the observed relationships.</p>\u0000<h3>Practical implications</h3>\u0000<p>Understanding how different platforms influence democratic attitudes can inform strategies for political communication and digital governance in Latin America. Policymakers should consider platform-specific interventions to promote democratic engagement.</p>\u0000<h3>Originality/value</h3>\u0000<p>This study adds to the limited research on platform differences in political public opinion, particularly in Latin America, and highlights the need to explore mechanisms of change across various social media platforms.</p>","PeriodicalId":54925,"journal":{"name":"Internet Research","volume":"1 1","pages":""},"PeriodicalIF":5.9,"publicationDate":"2024-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142869960","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Learning state-action correspondence across reinforcement learning control tasks via partially paired trajectories

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2024-12-24 DOI: 10.1007/s10489-024-06190-7

Javier García, Iñaki Rañó, J. Miguel Burés, Xosé R. Fdez-Vidal, Roberto Iglesias

{"title":"Learning state-action correspondence across reinforcement learning control tasks via partially paired trajectories","authors":"Javier García, Iñaki Rañó, J. Miguel Burés, Xosé R. Fdez-Vidal, Roberto Iglesias","doi":"10.1007/s10489-024-06190-7","DOIUrl":"10.1007/s10489-024-06190-7","url":null,"abstract":"<div><p>In many reinforcement learning (RL) tasks, the state-action space may be subject to changes over time (e.g., increased number of observable features, changes of representation of actions). Given these changes, the previously learnt policy will likely fail due to the mismatch of input and output features, and another policy must be trained from scratch, which is inefficient in terms of <i>sample complexity</i>. Recent works in transfer learning have succeeded in making RL algorithms more efficient by incorporating knowledge from previous tasks, thus partially alleviating this problem. However, such methods typically must provide an explicit state-action correspondence of one task into the other. An autonomous agent may not have access to such high-level information, but should be able to analyze its experience to identify similarities between tasks. In this paper, we propose a novel method for automatically learning a correspondence of states and actions from one task to another through an agent’s experience. In contrast to previous approaches, our method is based on two key insights: i) only the first state of the trajectories of the two tasks is <i>paired</i>, while the rest are <i>unpaired</i> and randomly collected, and ii) the transition model of the source task is used to predict the dynamics of the target task, thus aligning the <i>unpaired</i> states and actions. Additionally, this paper intentionally decouples the learning of the state-action corresponce from the transfer technique used, making it easy to combine with any transfer method. Our experiments demonstrate that our approach significantly accelerates transfer learning across a diverse set of problems, varying in state/action representation, physics parameters, and morphology, when compared to state-of-the-art algorithms that rely on cycle-consistency.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 3","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142875250","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A domain-aware model with multi-perspective contrastive learning for natural language understanding

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2024-12-24 DOI: 10.1007/s10489-024-06154-x

Di Wang, Qingjian Ni

{"title":"A domain-aware model with multi-perspective contrastive learning for natural language understanding","authors":"Di Wang, Qingjian Ni","doi":"10.1007/s10489-024-06154-x","DOIUrl":"10.1007/s10489-024-06154-x","url":null,"abstract":"<div><p>Intent detection and slot filling are core tasks in natural language understanding (NLU) for task-oriented dialogue systems. However, current models face challenges with numerous intent categories, slot types, and domain classifications, alongside a shortage of well-annotated datasets, particularly in Chinese. Therefore, we propose a domain-aware model with multi-perspective, multi-positive contrastive learning. First, we adopt a self-supervised contrastive learning with multiple perspectives and multiple positive instances, which is capable of spacing the vectors of positive and negative instances from the domain, intent, and slot perspectives, and fusing more positive instance information to increase the classification effectiveness of the model. Our proposed domain-aware model defines domain-level units at the decoding layer, allowing the model to predict intent and slot information based on domain features, which greatly reduces the search space for intent and slot. In addition, we design a dual-stage attention mechanism for capturing implicitly shared information between intents and slots. We propose a data augmentation method that adds noise to the embedding layer, applies fine-grained augmentation techniques, and filters biased samples based on a similarity threshold. Our model is applied to real task-oriented dialogue systems and compared with other NLU models. Experimental results demonstrate that our proposed model outperforms other models in terms of NLU performance.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 3","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142875296","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0