1. IEEE Transactions on Computational Intelligence and AI in Games
-----------------------
全文截稿：2017-05-15
期刊：IEEE Transactions on Computational Intelligence and AI in Games
专刊：Special Issue on Deep/Reinforcement Learning and Games
领域：人工智能
难度：★★★
CCF分类：C类
影响因子：1
网址：http://cis.ieee.org/ieee-transactions-on-computational-intelligence-and-ai-in-games.html
-----------------------
Deep Learning (DL) and Reinforcement Learning (RL) have been applied with great success to many games, including Go and Atari 2600 games. Monte Carlo Tree Search (MCTS), developed in 2006, can be viewed as a kind of online RL. This technique has greatly improved the level of Go-playing programs. MCTS has since become the state of the art for many other games including Hex, Havannah, and General Game Playing, and has found much success in applications as diverse as scheduling, unit commitment problems, and probabilistic planning.
Deep learning has transformed fields such as image and video recognition and speech understanding. In computer games, DL started making its mark in 2014, when teams from University of Edinburgh and Google DeepMind independently applied Deep Convolutional Neural Networks (DCNNs) to the problem of expert move prediction in Go. Clark and Storkey's DCNN achieved a move prediction rate of 44%, exceeding all previously published results. DeepMind's publication followed soon after, with a DCNN that reached 55%.
The combination of DL and RL led to great advances in Atari 2600 game playing, and to the ultimate breakthrough in computer Go. What is the larger impact of these new techniques? For which games do they succeed or fail? How can they be extended to new applications? How can they be combined with other approaches? The purpose of this special issue is to publish high quality papers reporting the latest research covering the theory and practice of DL/RL/DRL methods applied to games. Topics include but are not limited to:
- MCTS and reinforcement learning
- Deep/reinforcement learning for all kinds of games, including board games, card games, video games, general game playing, etc.
- Deep/reinforcement learning for procedural content generation (PCG)
- Deep/reinforcement learning for modeling players/designers
- Deep/reinforcement learning for game analytics
- Deep learning neural net architectures
- Online and offline deep reinforcement learning methods
- Training and testing issues for deep learning, such as transfer learning, dropout, regularization to avoid overfitting, adaptive learning rates, momentum, selection of training data sets, etc.
- Approximation methods for deep learning
- Hybrid deep learning approaches
- Real world applications
- DL-based knowledge representation models for games
2. Image and Vision Computing
-----------------------
全文截稿：2017-05-15
期刊：Image and Vision Computing
专刊：Special Issue on Reliable Automatic Facial Coding
领域：人工智能
难度：★★★
CCF分类：C类
影响因子：1.766
网址：http://www.journals.elsevier.com/image-and-vision-computing/
-----------------------
Automatic Facial Action Coding, in particular FACS Action Unit coding, has continued to see steady progress since the first challenge in automatic facial expression recognition was held (FERA 2011). Two more FACS challenges have been organised since then (FERA 2015 and 2017), which opened benchmarking to interactive scenarios using the SEMAINE database, and to spontaneous emotions and non-frontal head-poses using the BP4D database. Other benchmarking databases have also been widely used, e.g. the DISFA or UNBC-McMaster shoulder-pain expression archive database.
We are calling for papers in the broad area of facial action coding, with a stated interest in and focus on fair comparison on aspects of occurrence and intensity estimation accuracy, computational complexity, robustness to the prevailing challenging conditions, and reproducibility of results. All submissions *must* report on the three FERA testsets (2011, 2015, and 2017), in addition to any other data sets authors wish to report on. Results on the FERA testsets will be included in a summary of the special issue.
Papers are invited addressing any of the following themes:
- Action Unit Occurrence detection
- Action Unit intensity estimation
- FACS analysis for human behaviour interpretation
- FACS analysis under challenging conditions
- Deep Learning for Automatic Facial Coding
- Multimodal and multi-cue behaviour analysis using FACS
3. International Journal of Approximate Reasoning
-----------------------
全文截稿：2017-05-31
期刊：International Journal of Approximate Reasoning
专刊：Special Issue on Uncertainty Management in Machine Learning Applications
领域：人工智能
难度：★★★★
CCF分类：B类
影响因子：2.696
网址：http://www.journals.elsevier.com/international-journal-of-approximate-reasoning/
-----------------------
The International Symposium on Integrated Uncertainty in Knowledge Modelling and Decision Making (IUKM) is an open international forum for exchanges of research results, ideas for and experience of application among researchers and practitioners involved with all aspects of uncertainty management and application. IUKM 2016 is the fth edition of the Conference, which was successfully held in Da-Nang, Vietnam, during 30 November-2 December, 2016.
In Machine Learning applications the uncertainty lies in the noisy data (ambiguous, imprecise, contradictory, missing data) and the unknown (or partly known) model parameters. Such different types of uncertainty come from different sources and require different approaches to handle. This special issue follows IUKM 2016 and solicits contributions dealing with any aspects of uncertainty management in Machine Learning applications. However, it is also open to other relevant contributions that were not presented in IUKM 2016.
Topics include but are not limited to:
Methodology:
- Uncertainty formalisms: Bayesian probabilities, Dempster-Shafer theory, fuzzy measures, random sets, rough sets, fuzzy sets and their hybrids
- Uncertainty modeling and management in big-data environments
- Learning and reasoning with uncertainty
Application:
- Natural language processing
- Bioinformatics / Computational biology
- Medical information systems
- Ranking and recommendation systems
- Opinion mining and sentiment analysis
- Fequent pattern mining
- Social media analytics
- Anomaly detection, etc.
4. Image and Vision Computing
-----------------------
全文截稿：2017-06-30
期刊：Image and Vision Computing
专刊：Special Issue on Biometrics in the Wild
领域：人工智能
难度：★★★
CCF分类：C类
影响因子：1.766
网址：http://www.journals.elsevier.com/image-and-vision-computing/
-----------------------
Biometric recognition from data captured in unconstrained settings, commonly referred to as biometric recognition in the wild, represents a challenging and highly active area of research. The interest in this area is fueled by the numerous application domains that deal with unconstrained data acquisition conditions such as forensics, surveillance, social media, consumer electronics or border control. While the existing biometric technology has matured to a point, where excellent performance can be achieved for various tasks in ideal laboratory-like settings, many problems related to in-the-wild scenarios still require further research and novel ideas. The goal of this special issue is to present the most advanced work related to biometric recognition in unconstrained settings and introduce novel solutions to open biometrics-related problems. Submitted papers should make a significant contribution in terms of theoretical findings or empirical observations, demonstrate improvements over the existing state-of-the-art and use the most challenging datasets available.
The special issue builds on the Biometrics-in-the-Wild (BWild) workshop series organized as part of IEEE FG 2015 and IEEE FG 2017. The special issue is open to all, but submissions from past BWild participants are especially welcome.
We invite original high-quality papers on topics related to biometric recognition in the wild, including, but not limited to:
- Region of interest detection (alignment, landmarking) in the wild,
- Soft biometrics in the wild,
- Context-aware techniques for biometric detection and recognition,
- Novel normalization techniques,
- Multi-modal biometrics in the wild,
- Biometric recognition in the wild,
- Biometrics from facial behavior (e.g., eye movement, facial expressions, micro-expressions),
- Biometrics based on facial dynamics,
- Novel databases and performance benchmarks,
- Ethical issues, privacy protection and de-identification,
- Spoofing and countermeasures,
- Deep learning approaches for unconstrained biometric recognition,
- Related applications, especially mobile.
5. IEEE Transactions on Neural Networks and learning systems
-----------------------
全文截稿：2017-07-15
期刊：IEEE Transactions on Neural Networks and learning systems
专刊：Special Issue on Discriminative Learning for Model Optimization and Statistical Inference
领域：人工智能
难度：★★★★
CCF分类：B类
影响因子：4.854
网址：http://cis.ieee.org/ieee-transactions-on-neural-networks-and-learning-systems.html
-----------------------
Model optimization and statistical inference have played a central role in various applications of computational intelligence, data analytics, and computer vision. Traditional model-centric learning approaches require properly crafted optimization and inference algorithms, as well as carefully tuned parameters. Recently, the discriminative learning technique has demonstrated its power for process-centric learning. The resulting solutions are closely related to a variety of statistical and optimization models such as sparse representation, structured regression, and conditional random fields, and are empowered by effective computational techniques such as bi-level optimization and partial differential equations (PDEs). Moreover, many deep learning models has been shown to be closely tied with discriminative learning models. For example, a problem-specific deep architecture can be formed by unfolding the model inference as an iterative process, whose parameters can be jointly learned from training data with a discriminative loss. Such a viewpoint motivates the incorporation of domain expertise and problem structures into designing deep architectures, and helps the interpretation and performance improvement of deep models.
This special issue aims at promoting first-class research along this direction, and offers a timely collection of information to benefit the researchers and practitioners. We welcome high-quality original submissions addressing both novel theoretical and modeling progress, and real-world applications that benefit discriminative learning for model optimization and statistical inference. Topics of interests include, but are not limited to:
- Task-driven learning for model optimization and/or statistical inference.
- Novel architectures and algorithms for bi-level optimization and/or PDEs .
- Problem-specific deep architectures for solving model optimization and statistical inference.
- Integration of optimization-based, statistical learning, and inference models with deep learning models.
- Sparse representation motivated deep architectures.
- Structured regression motivated deep architectures.
- Conditional random forest motivated recurrent neural networks.
- Novel interpretative frameworks on the working mechanism of representative deep learning models.
- Theoretical analysis of deep learning models and algorithms: convergence, optimality, generalization, stability, and sensitivity analysis.
- Applications based on the above described models and algorithms: (1) image enhancement, restoration and synthesis; (2) optical flow, stereo matching, camera localization, and normal estimation; (3) visual recognition, detection, and segmentation, and scene understanding; (4) pattern classification, clustering and dimensionality reduction; (5) medical image analysis and other novel application domains
6. International Journal on Document Analysis and Recognition
-----------------------
全文截稿：2017-08-31
期刊：International Journal on Document Analysis and Recognition
专刊：Special Issue on Deep Learning for Document Analysis and Recognition
领域：人工智能
难度：★★★
CCF分类：C类
影响因子：0.885
网址：http://www.springer.com/journal/10032/about
-----------------------
Deep learning is a new field of machine learning research, to design models and learning algorithms for deep neural networks. Due to the ability of learning from big data and the superior representation and prediction performance, deep learning has gained great successes in various applications of pattern recognition and artificial intelligence, including character and text recognition, image segmentation, object detection and recognition, face recognition, traffic sign recognition, speech recognition, machine translation, to name a few. Intensive attention has been drawn to the exploration of new deep learning models and algorithms, and the extension to more application areas. The combination of deep learning and traditional methods in pattern recognition and artificial intelligence has also demonstrated benefits.
The technology of document analysis and recognition (DAR) is to analyze the structure and textual contents of document images and handwriting. It faces numerous application needs such as digitization of books and forms, pen-based text input, information extraction from Web document images. It has been under study as a field of pattern recognition since 1960s. In recent years, the introduction of deep learning to DAR has led to significant improvement of performance in many branches, particularly in the cases when large sets of labeled data are available for supervised learning, such as handwritten character and text recognition. Among the most successful deep learning models are the convolutional neural network (CNN) and the recurrent neural network with long short-term memory (LSTM). The application of deep learning is now extended to scene text detection and recognition, document image segmentation and layout analysis, writer identification, document retrieval, and so on.
This special issue is aimed to report the new advances in DAR using deep learning methods. Articles presenting reviews, perspectives, new methods and applications in DAR are cordially invited. The topics of interest include, but are not limited to
- Deep learning for document image processing and segmentation
- Deep learning for layout analysis
- Deep learning for character and text recognition
- Deep learning for scene text detection and recognition
- Deep learning for writer identification and signature analysis
- Deep learning for document retrieval
- Deep learning for context modeling
- Deep learning for graphics and symbol recognition
- Deep learning for other DAR tasks
7. IEEE Transactions on Neural Networks and learning systems
-----------------------
全文截稿：2017-11-15
期刊：IEEE Transactions on Neural Networks and learning systems
专刊：Special Issue on Intelligent Control through Neural Learning and Optimization for Human Machine Hybrid Systems
领域：人工智能
难度：★★★★
CCF分类：B类
影响因子：4.854
网址：http://cis.ieee.org/ieee-transactions-on-neural-networks-and-learning-systems.html
-----------------------
During the recent decades, there are a vast number of learning methods for designing intelligent controllers for human machine hybrid systems. However, a further consideration not only is guaranteeing the control stability, but is optimality based on a predefined cost function to determine the performance of the human machine hybrid systems. Therefore, we are faced with a need for improved control schemes, which not only achieve the stability of the human machine hybrid systems, but also keep the cost of the systems as small as possible. The special issue addresses a broad spectrum of topics ranging from deterministic and stochastic intelligent control design for various human machine hybrid systems such as unmanned aerial vehicles, intelligent quadruped robots, industrial robots, robotic exoskeletons, biped robots, wheeled balance transporters, to the optimization of the learning algorithm. Special attention should be given to how to optimize controller design, achieve the high accurate performance for the human machine interactions, and handle nonlinearities and the unknown system dynamics. This includes modeling, learning control, neural network adaptations, iterative learning, deep learning, reinforcement learning, dynamic programming and testing the effectiveness of the controllers. The special issue publishes original papers of innovative ideas and concepts, new discoveries and improvements, and novel applications to the field of intelligent control for human machine hybrid systems. Topics explored in this special issue include, but are not limited to:
- Learning and Optimizations for the intelligent control;
- Adaptive dynamic programming for human machine hybrid systems and their applications;
- Iterative learning control for human machine hybrid systems and their applications;
- Deep Learning for human machine interactions;
- Reinforcement learning to handle nonlinearities for human machine hybrid systems;
- Learning control design for intelligent robots;
- High accurate tracking control via learning for multi-robot systems and applications;
- Modeling and learning control for humanoid robots and applications;
- Identification and learning control design for quadruped robots;
- System design and learning control for industrial robots;
- Learning control and optimizations for exoskeletons;
- Learning control and balance analysis for wheeled balance transporters;
- Learning control and optimizations for aerial vehicles;
- Learning control and stability analysis for humanoid robots or quadruped robots;
- Modeling, identification and optimizations via learning;
- Neural network control and practical applications in model-free environment;
- New applications of learning control for human machine hybrid systems.
-----------------------
全文截稿：2017-12-31
期刊：IET Computer Vision
专刊：Special Issue on Computer Vision in Cancer Data Analysis
领域：人工智能
难度：★★★
CCF分类：C类
影响因子：0.573
网址：http://digital-library.theiet.org/content/journals/iet-cvi
-----------------------
This Special Issue will present state-of-the-art computer vision methods in cancer data analysis. Recent progress in imaging hardware, acquisition techniques, and algorithmic processing of data has led to advances in detection, diagnosis, staging, treatment, and follow-up in cancer-related clinical workflows, as well as fundamental understanding of cancer modelling and dynamics. Cancer imaging includes varied modalities, and numerous scales including nano, micro, and macro. The Special Issue will be dedicated to technical advances that have potential for clinical relevance, and seeks to bring together a collection of recently developed approaches in this domain. We hope the methods presented will inspire future research both from theoretical and practical viewpoints to spur further advances in the field.
Topics include, but are not limited to:
- Segmentation in cancer imaging: from nano to macro
- Tracking of cells in metastasis and migration processes
- Registration of cancer images
- Histopathology image analysis
- Modelling of cancer cells, vasculature and cancerous processes
- Image-based interventional techniques for cancer treatment
- Tissue characterisation from images
- Machine learning in medical imaging for detection, diagnosis, and cancer staging
Call4Papers App上线啦！下载Call4Papers App，获取更多详细内容！欢迎各位用户多提宝贵建议！
注意：请点开图片后，提取二维码，进入下载页面。
