Pattern Recognition is the official journal of the Pattern Recognition Society. The Society was formed to fill a need for information exchange among research workers in the pattern recognition field. Up to now, we ''pattern-recognitionophiles'' have been tagging along in computer science, information theory, optical processing techniques, and other miscellaneous fields. Because this work in pattern recognition presently appears in widely spread articles and as isolated lectures in conferences in many diverse areas, the purpose of the journal Pattern Recognition is to give all of us an opportunity to get together in one place to publish our work. The journal will thereby expedite communication among research scientists interested in pattern recognition.

We consider pattern recognition in the broad sense, and we assume that the journal will be read by people with a common interest in pattern recognition but from many diverse backgrounds. These include biometrics, target recognition, biological taxonomy, meteorology, space science, classification methods, character recognition, image processing, industrial applications, neural computing, and many others.

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.

Special Issue on Graph-based Methods for Large Scale Financial and Business Data Analysis
Submission Date: 2020-06-30

Aims and Scope

Machine learning and pattern recognition techniques have had a significant impact on the analysis of large-scale datasets in the financial domain. However, to date most of the analysis techniques used have focused on the use of standard vectorial methods and time series data. Recently though, interest has turned to the use of relational and similarity-based representations of financial data. This is largely due to improvements in the maturity of the available methods, including graph embedding, graph kernels and deep graph convolutional networks. This has resulted in a number of impressive applications of graph-based methods for data analysis in the finance and business sectors. Because of the timeliness of this topic, this special issue will focus on the recent advances in graph-based pattern recognition approaches in the finance domain. Over the past decade or so, the effectiveness of graph-based methods has been repeatedly demonstrated for modeling the complex structural relationships that exist in high volume and high dimensional data. In the meantime, the size and dimension of data encountered in the finance and business sectors that need to be analyzed have grown dramatically. Despite their attractive features, graph-based pattern recognition methods are still far from being a panacea for extracting or mining relevant information from financial and business data. In addition, because financial data is often time-varying, high-dimensional, unstable, and often noisy or imbalanced, it brings with additional challenges for developing efficient and effective graph-based pattern recognition techniques. Provided these problems can be controlled, graph-based pattern recognition holds out the potential as a powerful tool for modelling complex structural data relationships, and also mining both useful information and temporal patterns which could be used for building powerful analytics for use by financial and commercial organizations. These approaches will thus significantly benefit financial market analysis, banking, and e-commerce, not only for predicting factors such as accurate financial behavior prediction and risk management, but also fraud and anomalous behavior detection.

Methods:

    Graph Kernel Methods
    Graph Embedding Methods
    Graph-based Deep Learning
    Graph-based Feature Selection
    Complex Networks
    Structural Time Series Analysis
    Graph Matching
    Graph-based Optimization
    Graph Neural Networks
    Representation Learning on Graph Structured Data
    Graph Classification and Vertex Classification
    Adversarial and Generative Graph Learning
    Transductive and Inductive Learning on Graphs
    Survey Papers Regarding the Topic of Learning with Graphs
    Other Graph-based Methods

Applications:

    Financial Market Simulation
    Trading Strategies
    Stock Price Forecasting
    Derivatives Modelling and Pricing
    Credit Scoring & Credit Rating
    Bankruptcy Prediction
    Fraud Detection
    Contagion Modelling and Analysis
    Analyzing Financial Crisis
    Systematic Risk Prediction
    Portfolio Optimization
    E-commerce Applications
    Block Chain Applications
    Other Important Aspects, Issues and Progress associated with Graph-based methods in Financial and Business Applications

Special Issue on Deep relational learning in visual recognition, understanding, and reasoning
Submission Date: 2020-07-01

The success of machine learning and in-depth explorations of deep neural networks have facilitated the advances in understanding the high-level semantic of visual contents. Deep relational learning aims to provide a fine-grained modelling of the relationships and interactions of visual content, including visual relationship detection, scene graph generation, and knowledge graph extraction. The progress of deep relational learning can also improve the down-stream tasks that requires fine-grained visual understanding—e.g., visual question answering, referring expression, and visual captioning.

This special issue aims to demonstrate on 1; 1) how machine learning algorithms and deep neural network models have contributed, and are contributing, to new theories, models, and datasets related to the topic of deep relational learning; and 2) how deep relational learning can facilitate other task like visual recognition, understanding, and reasoning. The editors hope to collect a group of research results to report the recent developments in the related research topics. In addition, researchers can exchange their innovative ideas on the topic of deep relational learning in visual recognition, understanding, and reasoning by submitting manuscripts to this special issue. To summarize, this special issue prefers a large scope of submissions, which develop and adopt new progress for these topics. We are especially interested in 1) theoretical advances and algorithm developments in deep relational learning; 2) useful applications and system creations of deep relational learning in visual recognition, understanding, and reasoning; and 3) new datasets and benchmarks for new progress. Topics of interest include, but are not limited to:

Supervised, weakly-supervised and unsupervised deep models for relational learning
Graph learning, adversarial learning and transfer learning for relation analysis
Multi-modal knowledge network representation and reasoning
Visual relationship detection and scene graph generation
Human action and human-object interactions recognition
Visual recognition, detection and segmentation with relational learning
Visual question answering, visual captioning and referring expression
Data-driven and knowledge-driven visual reasoning models
New datasets and benchmarks related to the aforementioned topics

Special Issue on Conformal and Probabilistic Prediction with Applications
Submission Date: 2020-07-30

This issue will be devoted to conformal prediction, a novel machine learning technique

that complements predictions of ML algorithms with reliable measures of confidence.

The methods developed based on this framework produce well-calibrated confidence measures for individual examples without assuming anything more than that the data are generated independently from the same probability distribution (the i.i.d. model). Topic includes:

Theoretical analysis of conformal prediction, including performance guarantees
Applications of conformal prediction in various fields, including bioinformatics, drug discovery, medicine, natural language processing, robotics and information security
Novel conformity measures
Conformal anomaly detection
Venn prediction and other methods of multiprobability prediction
Conformal predictive distributions
Probabilistic prediction
On-line compression modelling
Prediction in: Machine learning, Pattern recognition, Data mining, Transfer learning
Algorithmic information theory
Data visualization
Big data applications

Special Issue on Meta-learning for Image/Video Segmentation
Submission Date: 2020-11-15

Pattern recognition (PR) is in transition as the fast convergence of digital technologies and data science holds the promise to liberate consumer data and provide a faster and more cost-effective way of improving human initiatives. Particularly, deep learning, as one of the automatic discovery methods of regularities in data, is heavily influencing in the computer vision applications, including image segmentation, object tracking and recognition. The data driven-based deep learning algorithms have the potential to reshape the expectations of human’s actions, the way that companies’ stakeholders collaborate, and revamp business models in the various industries.

However, most of recent big data driven-based deep learning algorithms remain challenging to discover patterns in small data, which are insufficient to train deep networks.

To tackle these challenges, meta-learning is a recent technique to entail acquiring a prior over previous tasks and experiences, such that new tasks be learned from small amounts of data. It aims at using machine learning itself to automatically learn the most appropriate algorithms and parameters for deep learning algorithms. Particularly, meta-learning approaches that utilize neural network representations have made progress in few-shot image classification, reinforcement learning, and, more recently, image semantic segmentation, the training algorithms and model architectures have become increasingly specialized to the few-shot domain.

The objective of this special issue is to generate a comprehensive understanding of meta-learning in image/video segmentation for both theoretical and practical implications. This special issue is focused on the scope from responsible small data augmentation, meta-learning engine, to meta-learning applications. Authors are invited to submit outstanding and original unpublished research manuscripts focused on the latest findings in this field.

The following (but not limited to) topics are the particular interests of this special issue, including:

Novel theoretical insights on meta learning
Learning from model evaluations
Siamese networks
Meta data augmentation
Prototypical networks
Relation and matching networks
Memory-augmented neural networks
Model agnostic meta learning
Meta-SGD
Gradient agreement
Entropy maximization/reduction
Meta imitation learning
Meta learning in image/video segmentation
Meta learning in classification/tracking

Special Issue on Modeling and Learning for Matching: Models, Methods and Applications
Submission Date: 2020-12-30

The special issue will focus on the recent advance in modeling and learning to solve the matching problem in pattern recognition. The capability of finding correspondence among images, graphics, point sets and other structures has been a fundamental in many pattern recognition. The past decades have witnessed the rapid expansion of the frontier for automatic correspondence establishment among images/graphics, which is largely due to the advances in computational capacity, data availability and new algorithmic paradigms. Although the correspondence problem has been extensively studied in the context of multi-view geometry, its more generalized forms, along with underlying connections among different methods and settings, have not been fully explored. Meanwhile, the combination of big data and the deep learning paradigm has achieved significant success in many perceptual tasks; however, the existing paradigm is still far from a panacea to the matching problem, which often calls for more careful treatments on the local and global structures. Also, there are emerging methods for discovering latent graph structures that enrich the applicability for graph matching. In this special issue, we attempt to assemble recent advances in the matching problem, considering the explosions of big visual data applications and the deep learning algorithms.

This special issue will feature original research papers related to the models and algorithms for robust establishment of correspondence, together with applications to real-world problems.

Main Topics of Interest (but are not limited to):

Object matching: 1) Graph representation and modeling using image/graphics data; 2) Robust matching/registration for visual correspondences over two or multiple images/graphics/point sets; 3) Partial, one-to-many/many-to-many matching, in the presence of major noise and outliers; 4) Similarity between graphs/graphics and graph clustering/classification; 5) Cross-network matching, e.g. social networks and other forms e.g. protein network; 6) Incremental matching of a series of objects; 7) Shape matching.

Tracking and optical flow estimation: 1) Single/multiple object tracking and data association; 2) Robust and/or efficient optical flow methods; 3) Object co-detection; 4) Visual trajectory generation and modeling; 5) Person Re-ID; 6) Planar Object Tracking

Correspondence for 3-D vision: 1) Calibration, and pose estimation; 2) visual SLAM; 3) Depth estimation and 3-D reconstruction;

Learning for/by permutation and matching: 1) Learning graph structure and similarity from data with established or unestablished correspondences; 2) Learning image feature representation from established or loosely established correspondence; 3) Common/similar objects discovery and recognition from images; 4) Learning for matching and permutation.

Structure discovery from data: 1) structure inference from behavior data e.g. time series and event sequence; 2) latent structure matching based on behavior data

Applications: Application of matching technology to solve any real-world visual understanding problems including object detection/recognition among images/graphics, image stitching, 2-D/3-D recovery, robot vision, photogrammetry and remote sensing, industrial imaging, embed system etc.