期刊信息

Pattern Recognition (PR)

请登录查看期刊网址
免费注册：查看官网链接、跟踪截稿日期，并接收邮件提醒。
登录 注册

影响因子:
7.6
出版商:
Elsevier
ISSN:
0031-3203
浏览:
143680
关注:
148

征稿

Pattern Recognition (PR) is an academic journal published by Elsevier. (ISSN 0031-3203, impact factor 7.6, CCF B).

Pattern Recognition is a mature but exciting and fast developing field, which underpins developments in cognate fields such as computer vision, image processing, text and document analysis and neural networks. It is closely akin to machine learning, and also finds applications in fast emerging areas such as biometrics, bioinformatics, multimedia data analysis and most recently data science. The journal Pattern Recognition was established some 50 years ago, as the field emerged in the early years of computer science. Over the intervening years it has expanded considerably. The journal accepts papers making original contributions to the theory, methodology and application of pattern recognition in any area, provided that the context of the work is both clearly explained and grounded in the pattern recognition literature. Papers whos primary concern falls outside the pattern recognition domain and which report routine applications of it using existing or well known methods, should be directed elsewhere. The publication policy is to publish (1) new original articles that have been appropriately reviewed by competent scientific people, (2) reviews of developments in the field, and (3) pedagogical papers covering specific areas of interest in pattern recognition. Various special issues will be organized from time to time on current topics of interest to Pattern Recognition. Submitted papers should be single column, double spaced, no less than 20 and no more than 35 (40 for a review) pages long, with numbered pages.
由 Dou Sun 最后更新于

Special Issues

Special Issue on Multimodal Agent AI for Video-Centric Understanding, Generation, and Embodied Intelligence 截稿日期: 2026-07-31 This special issue centers on multimodal agent-based artificial intelligence, which integrates visual, textual, auditory, and embodied signals to enable intelligent perception, reasoning, and action. By unifying advances in multimodal understanding, generative modeling, and agentic decision-making, the issue highlights how such systems leverage rich sensory streams, including video-centric interaction, embodied environments, and human in the loop feedback, to support robust, adaptive intelligence. Vision–language systems, and agentic AI, intelligent agents are increasingly capable of perceiving, reasoning, and acting across multiple modalities in dynamic environments. At the same time, agent-based multimodal systems are emerging as a powerful paradigm for human-centric perception, embodied intelligence, decision-making, interactive human–agent collaboration in both physical and simulated environments due to the capability of planning, memory, tool use, long-horizon reasoning, and interaction (that can be guided, corrected, or co steered by humans when necessary). This special issue aims to bring together cutting-edge research that bridges multimodal understanding, agent intelligence, and embodied AI, with a particular emphasis on human-centric video content, perception–action loops, and real-world deployment. Guest editors: Dr. Lin Yuanbo Wu (Executive Guest Editor), University of Warwick, Coventry, United Kingdom; Email: [email protected] Dr. Zhi Liu, The University of Electro-Communications, Tokyo, Japan; Email: [email protected] Prof. Mohammed Bennamoun, The University of Western Australia, Crawley, Australia; Email: [email protected] Prof. Jian Zhang, University of Technology, Sydney, Australia; Email: [email protected] Prof. Chen Chen, University of Central Florida, Florida, United States; Email: [email protected] Special issue information: Relevant topics include (but are not limited to): Multimodal Video Generation and Editing • Text, image and audio-driven video generation • Diffusion and transformer-based video foundation models • Multimodal controllable and personalized video synthesis • Video editing with spatial–temporal and semantic consistency • Multi-view, 3D-aware, and embodied video generation • Ethical considerations and forensic detection for generated video content Human-Centric Multimodal Understanding • Video–language representation learning • Human pose estimation, tracking, and action recognition in video • Human–object–scene interaction understanding • Egocentric and first-person multimodal perception • Human intention, affect, and behavior modeling • Human-in-the-loop multimodal perception and adaptive model refinement • Interactive human–agent video annotation and collaborative interpretation • Social interaction and crowd behavior analysis • Long-term and memory-driven video understanding and summarization • Responsible, fair, and trustworthy human-centric AI Multimodal Agent and Embodied AI • Agent-based multimodal perception and reasoning • Vision–language–action models and decision-making agents • Embodied AI in simulated and real-world environments • Perception–action loops and interactive learning • Human–agent collaborative decision-making and interactive task execution • Multi-agent collaboration and coordination • Tool-augmented and memory-enabled multimodal agents Systems, Benchmarks, and Applications • New datasets and benchmarks for multimodal video and agent tasks • Efficient and scalable multimodal model deployment • Explainable and robust multimodal AI systems • Benchmarks for evaluating human–agent collaboration and human-in-the-loop adaptation • Applications in robotics, AR/VR, healthcare, surveillance, smart cities, and creative industries • AI for sustainability, energy systems, and industrial monitoring Manuscript submission information: Open for Submission: from 24-Apr-2026 to 31-Jul-2026 Submission Site: Editorial Manager® Article Type Name: "VSI: Multimodal Agent AI" - please select this item when you submit manuscripts online All manuscripts will be peer-reviewed. Submissions will be evaluated based on originality, significance, technical quality, and clarity. Once accepted, articles will be posted online immediately and published in a journal regular issue within weeks. Articles will also be simultaneously collected in the online special issue. For any inquiries about the appropriateness of contribution topics, welcome to contact the Guest Editor team. Guide for Authors will be helpful for your future contributions, read more: Guide for authors - Pattern Recognition - ISSN 0031-3203 | ScienceDirect.com by Elsevier For more information about our Journal, please visit our ScienceDirect Page: Pattern Recognition | Journal | ScienceDirect.com by Elsevier Keywords: multimodal learning, agent-based AI, embodied intelligence https://www.sciencedirect.com/special-issue/332957/multimodal-agent-ai-for-video-centric-understanding-generation-and-embodied-intelligence
由 Admin Agent 最后更新于
Special Issue on New Trend of Multimodal Intelligence: Perception, Computing, Understanding, and Generation via Large AI models 截稿日期: 2026-08-25 From the breakthroughs of the Transformer architecture to the rise of large generative models and foundation models, multimodal intelligence is reshaping the new era of artificial intelligence. Multimodal intelligence focuses on modeling and learning from multiple data modalities, such as vision, language, audio and other sensor data by integrating cross-modal heterogeneous signals to perform challenging and complex tasks. The new trend of large AI models, increasingly larger parameter amounts, from Vision Transformer to Diffusion Models, CLIP, GPT, LLaMA, Qwen, and Claude have demonstrated stronger capabilities of perception, computing, understanding, and generation. This new trend greatly promotes multimodal intelligence in fields of multimodal alignment, semantic understanding, vision language action, embodied agents, and cognitive reasoning. Therefore, multimodal intelligence empowered by large AI models enables to unlock new frontiers in both research and industry. By highlighting foundational advances and emerging real-world applications, this special issue strengthens the scientific understanding and interpretation of multimodal intelligence. This special issue aims to explore the foundational theories and emerging applications of multimodal intelligence. It particularly emphasizes the integration of large AI models and complex tasks involving perception, understanding, generation, and reasoning across multiple modalities. It will provide a timely platform for presenting state-of-the-art research on the foundations, models, and applications of multimodal intelligence in large AI model era. We welcome high-quality submissions on topics including, but not limited to: Multimodal large AI models for multimodal perception and understanding, e.g., CLIP, GPT, LLaMA, LLaVA, Qwen across signal, text, image, audio, and video. Multimodal pre-training, alignment, and fusion techniques for robust cross-modal representation learning. Generative AI models for Multimodal intelligence, e.g., GANs, VGGT, and Diffusion Models in multimodal data processing. Multimodal intelligence for decision-making, e.g., Vision language action, embodied agents. Cross-modal generation and reasoning, e.g., image-to-text, video-to-audio, text-to-animation, text-to-3D. Multimedia computing for perception enhancement, e.g., image restoration, video analytics, human-object interaction, and interactive agents. Efficient adaptation, distillation, and compression of large AI models for edge devices. Novel datasets and benchmarks for Multimodal Intelligence. Guest editors: Prof. Chengtao Cai Affiliation: Harbin Engineering University, Harbin, China Prof. Bihan Wen Affiliation: Nanyang Technological University, Singapore City, Singapore Prof. Jiwen Lu Affiliation: Tsinghua University, Beijing, China Prof. Weishi Zheng Affiliation: Sun Yat-sen University, Guangzhou, China Prof. Liang Wang Affiliation: University of Chinese Academy of Sciences, Beijing, China Manuscript submission information: Open for Submission: from 25-Mar-2026 to 25-Aug-2026 Submission Site: Editorial Manager® Article Type Name: "VSI: PR_New Trend of Multimodal Intelligence" - please select this item when you submit manuscripts online All manuscripts will be peer-reviewed. Submissions will be evaluated based on originality, significance, technical quality, and clarity. Once accepted, articles will be posted online immediately and published in a journal regular issue within weeks. Articles will also be simultaneously collected in the online special issue. For any inquiries about the appropriateness of contribution topics, welcome to contact Leading Guest Editor (Prof. Chengtao Cai). Guide for Authors will be helpful for your future contributions, read more: Guide for authors - Pattern Recognition - ISSN 0031-3203 | ScienceDirect.com by Elsevier For more information about our Journal, please visit our ScienceDirect Page: Pattern Recognition | Journal | ScienceDirect.com by Elsevier Keywords: Multimodal Intelligence; Multimodal Large Language Models; Cross-modal Learning; Generative Models; Generative Artificial Intelligence https://www.sciencedirect.com/special-issue/331523/new-trend-of-multimodal-intelligence-perception-computing-understanding-and-generation-via-large-ai-models
由 Admin Agent 最后更新于
Special Issue on Multimodal Pattern Recognition for Biomedical Data: Theories, Algorithms and Applications 截稿日期: 2026-08-31 The rapid advancement of medical technologies has led to an explosion of multimodal medical data, including genomic sequences, electronic health records (EHRs), medical imaging (MRI, CT, PET), wearable sensor data, and multi-omics profiles. Integrating and interpreting these diverse data types presents both unprecedented opportunities and significant challenges in precision medicine, disease diagnosis, and personalized treatment. The integration of multimodal medical data has the potential to revolutionize healthcare by enabling more accurate diagnoses, personalized treatment strategies, and improved patient outcomes. However, effectively combining these diverse data types-each with distinct formats, dimensionalities, and temporal resolutions, requires novel computational approaches. Traditional single-modal analysis methods often fail to capture the complex interactions between different data modalities, necessitating the development of advanced AI techniques that can extract synergistic information across modalities. This special issue aims to serve as a comprehensive resource for researchers, clinicians, and industry professionals working at the intersection of AI and multimodal medical data. With the increasing adoption of AI in healthcare, there is a pressing need for robust, generalizable, and interpretable models that can handle the complexity of real-world medical data. By bringing together diverse perspectives, i.e., from computational innovation to clinical implementation. This issue will facilitate cross-disciplinary collaboration and accelerate the translation of AI research into tangible solutions for the area of medicine. Guest editors: Prof. Xinwang Liu National University of Defense Technology, Changsha, China Assoc. Prof. Chang Tang Huazhong University of Science and Technology, Wuhan, China Dr. Siwei Wang Academy of Military Sciences, Beijing, China Prof. Lei Wang University of Wollongong, Wollongong, Australia Assoc. Prof. Junbo Ma Hangzhou Dianzi University, Hangzhou, China Manuscript submission information: Open for Submission: from 01-Feb-2026 to 31-Aug-2026 Submission Site: Editorial Manager® Article Type Name: "VSI: PR_Biomedical Data" - please select this item when you submit manuscripts online All manuscripts will be peer-reviewed. Submissions will be evaluated based on originality, significance, technical quality, and clarity. Once accepted, articles will be posted online immediately and published in a journal regular issue within weeks. Articles will also be simultaneously collected in the online special issue. For any inquiries about the appropriateness of contribution topics, welcome to contact Leading Guest Editor Prof. Xinwang Liu. Guide for Authors will be helpful for your future contributions, read more: Guide for authors - Pattern Recognition - ISSN 0031-3203 | ScienceDirect.com by Elsevier. For more information about our Journal, please visit our ScienceDirect Page: Pattern Recognition | Journal | ScienceDirect.com by Elsevier. Keywords: Multimodal learning Medical data processing Multi-omics Multimodal generative models https://www.sciencedirect.com/special-issue/329765/multimodal-pattern-recognition-for-biomedical-data-theories-algorithms-and-applications
由 Dou Sun 最后更新于
Special Issue on Generative Models for Computer Vision 截稿日期: 2026-09-28 Generative modeling has become a transformative paradigm in computer vision, enabling rapid advances in image, video, 3D/4D generation, neural rendering, synthetic data creation, and controllable visual synthesis. Beyond generating realistic visual content, modern generative models are increasingly being integrated with recognition, reconstruction, reasoning, simulation, robotics, and embodied AI systems, where they can provide structured priors, predictive world models, and new mechanisms for understanding dynamic environments. This Special Issue on Generative Models for Computer Vision aims to provide a focused venue for research that connects generative modeling with core pattern recognition problems. It welcomes high-quality contributions on diffusion and score-based models, autoregressive and transformer-based models, generative world models, 3D/4D generation, neural rendering, representation learning, analysis-by-synthesis, embodied perception, robotic planning, simulation, sim-to-real transfer, and responsible AI. The issue seeks to highlight both methodological advances and practical applications that demonstrate how generative models can help visual systems understand, reconstruct, predict, and interact with complex real-world environments. Guest editors: Dr. Fangneng Zhan, The Hong Kong University of Science and Technology, Hong Kong, China; Email: [email protected] Dr. Adam Kortylewski, Helmholtz Center for Information Security, Saarbrücken, Germany; Email: [email protected] Dr. Kaichen Zhou, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA; Email: [email protected] Dr. Wenhan Luo, The Hong Kong University of Science and Technology, Hong Kong, China; Email: [email protected] Dr. Mengyu Wang, Harvard University, Cambridge, Massachusetts, USA; Email: [email protected] Special issue information: Topics of interest include, but are not limited to: Diffusion and score-based models Autoregressive and transformer-based models Generative world models and simulation 3D/4D generation and neural rendering Representation learning with generative models Analysis-by-synthesis approaches Controllable and conditional generation Embodied perception and active vision Generative models for robotic planning and control Simulation and sim-to-real transfer for robotics Synthetic data for training and evaluation Ethical and responsible AI Manuscript submission information: Open for Submission: from 2-Jun-2026 to 28-Sep-2026 Submission Site: Editorial Manager® Article Type Name: "VSI: PR_GCV" - please select this item when you submit manuscripts online All manuscripts will be peer-reviewed. Submissions will be evaluated based on originality, significance, technical quality, and clarity. Once accepted, articles will be posted online immediately and published in a journal regular issue within weeks. Articles will also be simultaneously collected in the online special issue. For any inquiries about the appropriateness of contribution topics, welcome to contact the Guest Editor team. Guide for Authors will be helpful for your future contributions, read more: Guide for authors - Pattern Recognition - ISSN 0031-3203 | ScienceDirect.com by Elsevier For more information about our Journal, please visit our ScienceDirect Page: Pattern Recognition | Journal | ScienceDirect.com by Elsevier Keywords: Diffusion Models; Video Generation; 3D/4D Modeling; World Models; Controllable Synthesis https://www.sciencedirect.com/special-issue/334131/generative-models-for-computer-vision
由 Admin Agent 最后更新于
Special Issue on Advancements in Multi-Source Heterogeneous Data Fusion for Pattern Recognition 截稿日期: 2026-09-30 The exponential growth of heterogeneous data sources—images, video, audio, sensor signals, time-series, graphs, and IoT streams—has created an urgent demand for effective multi-source data fusion. Researchers and practitioners now face the challenge of integrating disparate modalities that are often asynchronous, noisy, and incomplete. Traditional approaches remain insufficient for such heterogeneity. More advanced, scalable, and trustworthy methods are needed to ensure robustness, adaptability, and interpretability in real-world systems, including healthcare, autonomous driving, robotics, smart cities, and environmental monitoring. At the same time, large foundation models (LLMs, VLMs, MLLMs) are opening unprecedented opportunities for multimodal representation learning and cross-domain transfer. Yet, their application to heterogeneous fusion still requires solving issues of modality alignment, temporal/spatial synchronization, schema mismatches, and uncertainty management. This special issue will highlight the latest advances in multi-source fusion, spanning theoretical foundations, algorithms, architectures, and practical deployments. It will provide a venue for showcasing robust, efficient, and explainable solutions that can transform pattern recognition research and industry. Topics of Interest include, but are not limited to: Fusion algorithms for multi-source heterogeneous data Efficient and scalable fusion architectures Handling data heterogeneity, incompleteness, and misalignment Uncertainty, causality, and interpretability in data fusion Trustworthy, fair, and responsible fusion systems Multimodal learning with foundation models Evaluation metrics, datasets, and benchmarking protocols Applications in healthcare, robotics, transportation, and smart cities Emerging trends in cross-domain and multimodal data fusion Guest editors: Dr. Xiaohan Yu Macquarie University, Sydney, Australia Prof. Dr. Xiao Bai Beihang University, Beijing, China Dr. Imad Rida BMBI - Biomecanique et Bioingenierie, Compiegne, France Prof. Amir Hussain Edinburgh Napier University, Edinburgh, United Kingdom Manuscript submission information: Open for Submission: from 1-Mar-2026 to 30-Sep-2026 Submission Site: Editorial Manager® Article Type Name: "VSI: PR_Heterogeneous Data Fusion" - please select this item when you submit manuscripts online All manuscripts will be peer-reviewed. Submissions will be evaluated based on originality, significance, technical quality, and clarity. Once accepted, articles will be posted online immediately and published in a journal regular issue within weeks. Articles will also be simultaneously collected in the online special issue. For any inquiries about the appropriateness of contribution topics, welcome to contact Leading Guest Editor (Dr. Xiaohan Yu). Guide for Authors will be helpful for your future contributions, read more: Guide for authors - Pattern Recognition - ISSN 0031-3203 | ScienceDirect.com by Elsevier For more information about our Journal, please visit our ScienceDirect Page: Pattern Recognition | Journal | ScienceDirect.com by Elsevier Keywords: multi-source heterogeneous data cross-domain and multimodal multimodal learning
由 Dou Sun 最后更新于
Special Issue on Evolving Multi-View Learning: From Theory to High-Impact Applications 截稿日期: 2026-10-31 With the proliferation of data from diverse sources and the rapid advancements in computational capabilities, the field of multi-view learning has become increasingly vital. This domain focuses on developing sophisticated models to harness the rich, complementary information present across different data modalities or "views", aiming to achieve more robust and comprehensive data representations. In recent years, deep learning and Large Language Model (LLM) techniques have unlocked new potential, enabling the capture of complex, non-linear relationships and leading to breakthroughs in a wide array of applications. This special issue invites cutting-edge research and innovative contributions that advance the theoretical foundations, methodological developments, and real-world applications of multi-view learning. We welcome submissions that explore new frontiers, including but not limited to, advanced representation alignment, novel deep architectures, and scalable algorithms on multi-view learning area. We particularly encourage papers that demonstrate the practical utility of these models in high-impact areas such as bioinformatics, intelligent systems, medical diagnostics, and beyond. This special issue will focus on: Heterogeneous Data Fusion: Effectively fusing and aligning information from different views. Low quality multi-view learning: incomplete multi-view learning, partially aligned multi-view learning, and noisy multi-view learning. Cross-modal Retrieval: Enabling precise information retrieval across views. Scalable Multi-view Algorithm. Explainability and Robustness. Multimodal Generative Models: Using models for cross-view content generation. Multimodal Representation Learning: Learning unified or correlated representations for different views. Deep Multimodal Architectures: Applying deep learning to capture complex, non-linear relationships in multi-view data. Few-shot and Zero-shot Learning: Generalizing to new tasks with limited or no labeled multi-view data. Multimodal for Applications: Applying multimodal learning to tasks like disease diagnosis, industrial vision and others. Evaluation Metrics and Benchmarks: Establishing new standards for evaluating multimodal/multi-view learning performance. Guest editors: Dr. Jie Wen Harbin Institute of Technology, Shenzhen, China Dr. Shizhe Hu Zhengzhou University, Zhengzhou, China Dr. Lusi Li Old Dominion University, Norfolk, United States
由 Dou Sun 最后更新于
Special Issue on Adaptive and Scalable Vision Models in Dynamic and Resource-Constrained Environments 截稿日期: 2026-11-30 In today’s rapidly evolving world, vision models are playing an increasingly crucial role in a variety of applications, including robotics, autonomous driving, healthcare, industrial automation, and environmental monitoring. However, these models often face challenges in dynamic, complex, and resource-constrained environments where data is noisy, incomplete, or continuously evolving. Traditional deep learning models typically rely on vast amounts of labeled data and significant computational resources, making them less feasible in real-world settings. As the demand for more adaptable and scalable systems grows, the integration of advanced learning techniques such as few-shot learning (FSL), zero-shot learning (ZSL), incremental learning (IL), and continual learning (CL) has emerged as a promising approach to overcome these limitations. These techniques allow vision systems to operate effectively even with limited data and evolving tasks, making them ideal for dynamic and resource-constrained environments. This special issue aims to gather cutting-edge research on adaptive and scalable visual models that can work efficiently in dynamic and resource limited environments. We welcome contributions from theoretical and applied research to address major challenges such as data scarcity, computational limitations, and task development. The paper should explore new algorithms, models, and frameworks to push the limits of visual system possibilities while ensuring practical applications in real-world scenarios. Few-Shot and Zero-Shot Learning for Vision Systems Incremental and Continual Learning for Vision Efficient Vision Systems for Real-World Applications Cross-Domain and Cross-Modal Vision Systems Adaptability in Dynamic and Unstructured Environments Few-Shot and Zero-Shot Learning in Robotics and Autonomous Systems Long-Term and Lifelong Vision Learning Scalable Vision Architectures for Large-Scale Data Vision-Based Healthcare Systems Robust Vision Systems in Adverse Conditions 3D Vision Systems and Applications Transfer Learning and Knowledge Sharing Across Tasks and Domains Guest editors: Prof. Xin Ning Affiliation: Institute of Semiconductors, Chinese Academy of Sciences, Beijing, China Prof. Prayag Tiwari Affiliation: Halmstad University, Halmstad, Sweden Prof. Qiuhong Ke Affiliation: Monash University, Melbourne, Australia Prof. Sahraoui Dhelim Affiliation: Dublin City University, Dublin, Ireland Prof. Wenbin Zhang Affiliation: Florida International University, Miami, USA Manuscript submission information: Open for Submission: from 01-Jan-2026 to 30-Nov-2026 Submission Site: Editorial Manager® Article Type Name: "VSI: PR_Adaptive and Scalable Vision Models" - please select this item when you submit manuscripts online All manuscripts will be peer-reviewed. Submissions will be evaluated based on originality, significance, technical quality, and clarity. Once accepted, articles will be posted online immediately and published in a journal regular issue within weeks. Articles will also be simultaneously collected in the online special issue. For any inquiries about the appropriateness of contribution topics, welcome to contact Leading Guest Editor Prof. Xin Ning. Guide for Authors will be helpful for your future contributions, read more: Guide for authors - Pattern Recognition - ISSN 0031-3203 | ScienceDirect.com by Elsevier For more information about our Journal, please visit our ScienceDirect Page: Pattern Recognition | Journal | ScienceDirect.com by Elsevier Keywords: Vision Models; Resource-constrained Environments; Few-Shot Learning; Incremental and Continual Learning; 3D Vision Systems
由 Dou Sun 最后更新于
Special Issue on Agentic AI for Pattern Recognition 截稿日期: 2027-03-31 Agentic AI has achieved remarkable success by combining the deep semantic understanding and generative capabilities of foundation models with autonomous agency, tool integration, and environmental interaction. This agentic paradigm is now catalyzing a parallel transformation in pattern recognition (PR), shifting the field beyond traditional static classification toward dynamic, interactive systems capable of autonomous decision-making. Contemporary Large Language Model (LLM) agents operate through sophisticated perception–reasoning–action loops that enable them to perceive multimodal environmental inputs, reason over complex patterns through chain-of-thought mechanisms, and execute contextually appropriate actions. This paradigm shift demands a critical re-examination of how pattern recognition systems are designed, moving from isolated task-specific models to generalist agents that can adaptively handle diverse recognition tasks through unified architectures. To this end, this special issue seeks to capture the transformative potential of PR Agent frameworks, where perception modules extract meaningful representations from raw sensory data, reasoning systems formulate adaptive strategies for pattern interpretation, and action mechanisms enable iterative refinement through environmental feedback. This special issue is founded on the premise that LLM agents and other agentic AI approaches for PR should be understood not only as a powerful set of methods, but as an emerging scientific and technical paradigm for the field. In alignment with the mission of pattern recognition research, we seek contributions that move beyond narrow performance gains to engage with the deeper disciplinary questions opened by this transition: how perception–reasoning–action loops reshape pattern perception, reasoning, recognition, interaction, and decision-making; how they alter the relationship between static feature extraction and dynamic, context-aware interpretation; and how they demand new pattern recognition frameworks for trust, robustness, interpretability, and responsible deployment. This special issue aims not merely to document an emerging trend, but to help define the next intellectual horizon of pattern recognition as a field where recognition and action are inseparably coupled through continuous perception–reasoning–action cycles, and where pattern understanding emerges from active, goal-directed engagement with dynamically changing environments. Guest editors: Assoc. Prof. Yifan Zhu (Executive Guest Editor) School of Computer Science, Beijing University of Posts and Telecommunications (BUPT), Beijing, China Email: [email protected] Assist. Prof. Kaize Shi School of Science, Engineering and Digital Technologies, University of Southern Queensland, Queensland, Australia Email: [email protected] Dr. Qika Lin National University of Singapore, Singapore Email: [email protected] Dr. Bin Pu The Hong Kong University of Science and Technology, Hong Kong, China Email: [email protected] Dr. Wenguan Wang Zhejiang University, Hangzhou, China Email: [email protected] Special issue information: We invite high-quality submissions presenting original research articles, research surveys, methods papers, and critical application studies in areas including, but not limited to: Foundations of Agentic AI for Pattern Recognition: Novel architectures and​frameworks for agent-based perception; chain-of-thought reasoning for visual andsignal analysis; tool-learning and API-usage for integrating classical PR algorithms with LLM agents and other agentic AI approaches. Unified 2D and 3D Scene Understanding Agents: Agents capable of bridging the gap between 2D image data and 3D point clouds/meshes; open-vocabulary object detection, segmentation, and grounding in complex 3D environments using language-guided reasoning. Revitalizing Classical PR Tasks with Agentic Workflows: Application of agents to traditional domains such as Optical Character Recognition (OCR), document analysis, biometrics, and handwriting recognition, specifically focusing on handling unstructured or noisy data through iterative reasoning. Spatiotemporal and Video Pattern Recognition Agents: Agents designed for temporal reasoning, action recognition, and video understanding; systems that cananswer complex queries about long-form video content by actively retrieving and analyzing frames. Embodied Agents and Active Perception: Integration of pattern recognition agents into robotic systems; active vision where agents dynamically adjust sensors or viewpoints to improve recognition confidence; navigation and manipulation based on visual reasoning. Neurosymbolic and Knowledge-Aware Agents: Hybrid systems combining neural pattern recognition with symbolic logic and knowledge graphs; agents that leverage external knowledge bases to recognize rare, zero-shot, or fine-grained categories. Multi-Agent Systems for Collaborative Recognition: Swarm intelligence and multiagent frameworks where specialized agents collaborate to solve complex, multi-modal recognition problems. Human-in-the-loop and Interactive Recognition Agents: Frameworks for collaborative pattern recognition where agents solicit human feedback to resolve ambiguity; interactive segmentation and annotation tools powered by conversational agents. Generative Data and Synthetic Training for Agents: Utilizing LLM to create synthetic 2D/3D training data or counterfactual scenarios to robustify pattern recognition agents; self-improving agents that generate their own training signals. Trustworthiness, Explainability, and Safety in Agentic PR: Methods for interpreting the decision-making process of black-box agents; ensuring robustness against adversarial attacks in agent-based recognition; ethical considerations in autonomous surveillance and biometric agents. Domain-Specific Agent Applications: Specialized agents for high-stakes pattern recognition in medical imaging (e.g., radiology report generation), remote sensing (satellite imagery analysis), industrial inspection, and bioinformatics. Manuscript submission information: Open for Submission: from 31-May-2026 to 31-Mar-2027 Submission Site: Editorial Manager® Article Type Name: "VSI: Agentic AI for PR" - please select this item when you submit manuscripts online All manuscripts will be peer-reviewed. Submissions will be evaluated based on originality, significance, technical quality, and clarity. Once accepted, articles will be posted online immediately and published in a journal regular issue within weeks. Articles will also be simultaneously collected in the online special issue. For any inquiries about the appropriateness of contribution topics, welcome to contact the Guest Editor team. Guide for Authors will be helpful for your future contributions, read more: Guide for authors - Pattern Recognition - ISSN 0031-3203 | ScienceDirect.com by Elsevier For more information about our Journal, please visit our ScienceDirect Page: Pattern Recognition | Journal | ScienceDirect.com by Elsevier Keywords: Agentic AI, LLM Agent, Perception–Reasoning–Action https://www.sciencedirect.com/special-issue/334009/agentic-ai-for-pattern-recognition
由 Admin Agent 最后更新于
Special Issue on Multimodal Representation Learning Based on Vision Foundation Models 截稿日期: 2027-03-31 Recent years have witnessed remarkable progress in foundation models-large-scale neural networks pre-trained on vast amounts of data-that exhibit strong generalization and transfer capabilities across diverse tasks and domains. In the visual domain, vision foundation models (VFMs) such as CLIP, DINOv2 and Segment Anything Model (SAM), have demonstrated unprecedented performance in zero-shot recognition, segmentation, captioning, and cross-modal alignment. These models serve as powerful backbones for multimodal understanding, enabling rich, joint representations that bridge vision with language, audio, depth, motion, and other sensory signals. However, despite rapid advancements, fundamental challenges remain in how to effectively leverage VFMs for robust, efficient, and interpretable multimodal representation learning. Key open questions include: How can we align heterogeneous modalities in a unified semantic space? How do we adapt frozen or partially trainable VFMs to downstream multimodal tasks with limited labeled data? What architectural and training paradigms best support compositional reasoning, temporal modeling, or 3D scene understanding using VFMs as priors? This special issue aims to bring together cutting-edge research that explores the intersection of vision foundation models and multimodal representation learning, fostering interdisciplinary dialogue among computer vision, natural language processing, machine learning, and cognitive science communities. Guest editors: Xin Tan (Executive Guest Editor), Research Professor, East China Normal University& Shanghai AI Laboratory, Shanghai, China; Email: [email protected] Xingchen Zhang, Senior Lecturer, University of Exeter, Exeter, UK; Email: [email protected] Yadan Luo, Senior Lecturer, The University of Queensland, Brisbane, Australia; Email: [email protected] Pantea Keikhosrokiani, Adjunct Professor, University of Oulu, Oulu, Finland; Email: [email protected] Piotr Koniusz, Associate Professor, University of New South Wales, Sydney, Australia; Email: [email protected] Special issue information: This special issue will provide a timely and comprehensive forum for disseminating high-impact research at the forefront of multimodal AI. By focusing on vision foundation models as a unifying substrate, it will catalyze innovations that move beyond task-specific pipelines toward general-purpose, perception-capable AI systems. The issue is expected to attract submissions from leading academic labs and industry research groups, thereby shaping future directions in foundation model research and multimodal intelligence. Topics of interest include, but are not limited to: Architectures & Frameworks: Novel multimodal fusion strategies leveraging VFMs (e.g., late/early/hybrid fusion, cross-attention mechanisms, adapter modules). Training Paradigms: Self-supervised, contrastive, generative, or instruction-tuning approaches for aligning vision with other modalities using foundation models. Efficiency & Adaptation: Parameter-efficient fine-tuning (PEFT), distillation, quantization, or continual learning techniques for VFM-based multimodal systems. Reasoning & Compositionality: Using VFMs to support symbolic, causal, or hierarchical reasoning across modalities.3D & Embodied Multimodal Learning: Integrating VFMs with depth, LiDAR, robotics, or egocentric vision for spatial and interactive understanding. Evaluation & Benchmarks: New datasets, metrics, or evaluation protocols for assessing multimodal generalization, robustness, and fairness. Applications: Multimodal retrieval, video-language understanding, assistive technologies, medical imaging with reports, autonomous systems, etc. Ethics & Societal Impact: Bias mitigation, interpretability, privacy, and responsible deployment of VFM-powered multimodal systems. Manuscript submission information: Open for Submission: from 15-Apr-2026 to 31-Mar-2027 Submission Site: Editorial Manager® Article Type Name: "VSI: Vision Foundation Models" - please select this item when you submit manuscripts online All manuscripts will be peer-reviewed. Submissions will be evaluated based on originality, significance, technical quality, and clarity. Once accepted, articles will be posted online immediately and published in a journal regular issue within weeks. Articles will also be simultaneously collected in the online special issue. For any inquiries about the appropriateness of contribution topics, welcome to contact the Guest Editor team. Guide for Authors will be helpful for your future contributions, read more: Guide for authors - Pattern Recognition - ISSN 0031-3203 | ScienceDirect.com by Elsevier For more information about our Journal, please visit our ScienceDirect Page: Pattern Recognition | Journal | ScienceDirect.com by Elsevier Keywords: Vision Foundation Models; Representation Learning; 3D scene understanding; Embodied Multimodal Learning https://www.sciencedirect.com/special-issue/332578/multimodal-representation-learning-based-on-vision-foundation-models
由 Admin Agent 最后更新于

看过这个的人也在看

CCF全称影响因子出版商ISSN
BInformation Sciences6.0Elsevier0020-0255
CNeurocomputing6.5Elsevier0925-2312
CIEEE Transactions on Computational Social Systems4.9IEEE2373-7476
CEngineering Applications of Artificial Intelligence9.0Elsevier0952-1976
BInformation Processing & Management6.9Elsevier0306-4573
BInformation Systems3.4Elsevier0306-4379
CDiscover ComputingSpringer2948-2992
AIEEE Transactions on Computers3.8IEEE0018-9340
CFuture Generation Computer Systems6.1Elsevier0167-739X
BAdvanced Engineering Informatics9.9Elsevier1474-0346

相关期刊

CCF全称影响因子出版商ISSN
International Journal of Pattern Recognition & Artificial IntelligenceWorld Scientific0218-0014
Engineering11.6Elsevier2095-8099
CPattern Recognition Letters3.9Elsevier0167-8655
BSoftware & Systems Modeling3.2Springer1619-1366
BIEEE Transactions on Neural Networks and Learning Systems8.9IEEE1045-9227
BInformation Sciences6.0Elsevier0020-0255
BComputer Networks4.6Elsevier1389-1286
BComputers & Security5.4Elsevier0167-4048
BIEEE Transactions on Intelligent Transportation Systems8.4IEEE1524-9050
BJournal of Systems and Software4.1Elsevier0164-1212

相关会议

CCFICORE简称全称截稿日期通知日期会议日期
AA*AAAIAAAI Conference on Artificial Intelligence2026-07-212026-11-302027-02-16
CBPRICAIPacific Rim International Conference on Artificial Intelligence2026-06-272026-08-082026-11-17
BA*ICDMInternational Conference on Data Mining2026-06-062026-08-162026-11-12
AA*KDDACM SIGKDD Conference on Knowledge Discovery and Data Mining2026-07-192026-11-142027-08-09
BSOCCACM Symposium on Cloud Computing2026-07-072026-09-262026-11-18
CIDTInternational Conference on Communication, Information and Digital Technologies2026-07-152026-08-152026-09-11
NLCAInternational Conference on Natural Language Computing Advances2026-07-182026-08-252026-10-24
CSENInternational Conference on Computer Science and Engineering2026-07-182026-07-252026-08-22
BMLIInternational Conference on Big Data, Machine Learning and IoT2026-07-182026-07-312026-09-26
CSTFMInternational Conference on Smart Transportation and Future Mobility2026-06-122026-06-262026-07-10

评论 0

暂无评论。

请登录后发表评论