Journal Information
Multimedia Tools and Applications
Impact Factor:

Call For Papers
Multimedia Tools and Applications publishes original research articles on multimedia development and system support tools, and case studies of multimedia applications. Experimental and survey articles are appropriate for the journal. The journal is intended for academics, practitioners, scientists and engineers who are involved in multimedia system research, design and applications. All papers are peer reviewed.

Specific areas of interest include (but are not limited to):

Multimedia Tools:
Multimedia application enabling software
System software support for multimedia
Performance measurement tools for multimedia
Multimedia authoring tools
System hardware support for multimedia
Multimedia databases and retrieval
Web tools and applications
Multimedia Applications:
Prototype multimedia systems and platforms
Multimedia on information superhighways

Video on-demand
Interactive TV
Home shopping
Remote home care
Electronic album
Personalized electronic journals
Last updated by Dou Sun in 2017-04-13
Special Issues
Special Issue on Few-shot Learning for Multimedia Content Understanding
Submission Date: 2017-08-31

The multimedia analysis and machine learning communities have long attempted to build models for understanding real-world applications. Driven by the innovations in the architectures of deep convolutional neural network (CNN), tremendous improvements on object recognition and visual understanding have been witnessed in the past few years. However, it should be noticed that the success of current systems relies heavily on a lot of manually labeled noise-free training data, typically several thousand examples for each object class to be learned, like ImageNet. Although it is feasible to build learning systems this way for common categories, recognizing objects 'in the wild' is still very challenging. In reality, many objects follow a long-tailed distribution: they do not occur frequently enough to collect and label a large set of representative exemplars in contrast to common objects. For example, in some real-world applications, such as anomalous object detection in a video surveillance scenario, it is difficult to collect sufficient positive samples because they are 'anomalous' as defined, and fine-grained object recognition, annotating fine-grained labels requires expertise such that the labeling expense is prohibitively costly. The expensive labeling cost motivates the researchers to develop learning techniques that utilize only a few noise-free labeled data for model training. Recently, some few-shot learning, including the most challenging task zero-shot learning, approaches have been proposed to reduce the number of necessary labeled samples by transferring knowledge from related data sources. In the view of the promising results reported by these works, it is fully believed that the few-shot learning has strong potential to achieve comparable performance with the sufficient-shot learning techniques and significantly save the labeling efforts. There still remains some important problems. For example, a general theoretical framework for few-shot learning is not established, the generalized few-shot learning which recognizes common and uncommon objects simultaneously is not well investigated, and how to perform online few-shot learning is also an open issue. The primary goal of this special issue is to invite original contributions reporting the latest advances in fewshot learning for multimedia (e.g., text, video and audio) content understanding towards addressing these challenges, and to provide the opportunity for researchers and product developers to discuss the state-of-theart and trends of few-shot learning for building intelligent systems. The topics of interest include, but are not limited to: - Few-shot/zero-shot learning theory; - Novel machine learning techniques for few-shot/zero-shot learning; - Generalized few-shot/zero-shot learning; - Online few-shot/zero-shot learning; - Few-shot/zero-shot learning with deep CNN; - Few-shot/zero-shot learning with transfer learning; - Few-shot/zero-shot learning with noisy data; - Few-shot learning with actively data annotation (active learning); - Few-shot/zero-shot learning for fine-grained object recognition; - Few-shot/zero-shot learning for anomaly detection; - Few-shot/zero-shot learning for visual feature extraction; - Weakly supervised learning and its applications; - Attribute learning and its applications; - Leaning to hash and its applications; - Applications in object recognition and visual understanding with few-shot learning;
Last updated by Dou Sun in 2017-05-23
Special Issue on Advances in Computational Intelligence for Multimodal Biomedical Imaging (ATSIP 2017)
Submission Date: 2017-09-15

Nowadays, many modalities such as CT, X-ray scanners, MRI/fMRI, PET scan, etc. generate complex images with a large amount of data that are becoming extremely difficult to handle. This growing mass of data requires new strategies for the diagnosis of diseases and new therapies. In recent years, particular attention has been paid to computational intelligence methods in multimodal biomedical imaging applications. Inspired by artificial intelligence, mathematics, biology and other fields, these methods can find relationships between different categories of this complex data and provide a set of tools for the diagnosis and monitoring of the disease. The topics of this special issue include the following computational intelligence based methods for multimodal biomedical imaging systems and applications, but are not limited to: - Bio-inspired methods and neural modelling - Learning theory for biomedical image processing - Machine, deep and manifold learning for biomedical imaging systems - Pattern recognition and big data in medical imaging systems methodologies - Compressive sensing and time series analysis - Evolutionary algorithms and metaheuristics optimization for medical imaging - Neural networks and genetic algorithms for biomedical imaging systems - Applications (diagnosis, classification, denoising, registration, segmentation, security, augmented reality-aided surgery, brain-computer interface etc ...) - Modalities (X-ray, CT, MRI, fMRI, PET scan etc ...)
Last updated by Dou Sun in 2017-06-03
Special Issue on Soft Computing Techniques and Applications on Multimedia Data Analyzing Systems
Submission Date: 2017-09-20

In computer science and engineering research, soft computing is the use of inexact solutions to computationally hard tasks such as the solution of NP-complete problems, for which there is no known algorithm that can compute an exact solution in polynomial time. Soft computing differs from conventional computing in that, unlike hard computing, it is tolerant of imprecision, uncertainty, partial truth, and approximation. In effect, the role model for soft computing is the human mind. The three major components of soft computing are fuzzy logic, neural network, and probabilistic reasoning, which complement each other. Fuzzy logic is used for error analysis and neural network for knowledge learning. Probabilistic reasoning is used to solve uncertainties and chestnut problems. It is concluded that fuzzy logic can simulate the function of human processing language, and neural network and probability inference model imitate human process data, knowledge learning and reasoning process, so it can deal with multivariable and nonlinear system problem with soft computing theory. The integration of soft computing and multimedia systems is the trend especially when the deep learning arises. The aim of this special issue is to provide a premier international platform for wide range of professions including scholars, researchers, academicians and industry researchers to discuss and present the different types of cutting-edge soft computing techniques toward multimedia data analyzing systems. The special issue is open to submit novel and high quality research contributions. We target the researchers from both the industry and academia and anticipate that this special issue will open new entrance for further research and technology improvements in this important area. Preferred topics in this issue include (but are not limited to): - Online multimedia stream classification - On-line single-pass active learning from multimedia data streams - Multimedia big data mining, advanced analytics and visualization - Operating systems and real-time processing for multimedia data-intensive applications - Reliability in multimedia model predictions and parameters - Dynamic dimension reduction and feature selection in multimedia streams - User activities recognition for multimedia systems - Semi-supervised learning from multimedia data streams - Interplay between multimedia components for novel big data applications - Soft computing model for multimedia assisted prediction - Performance characterization, evaluation, optimization and design trade-offs - MapReduce and parallel models for multimedia big data processing - Web applications for multimedia systems - Compiler support for multimedia data-intensive in high performance systems - Multimedia information retrieval and feature extraction - Remote sensing multimedia system model and platform - Multimedia data stream modelling and identification - Robotics, intelligent system and advanced manufacturing with multimedia - Deep learning model and the applications in multimedia systems
Last updated by Dou Sun in 2017-06-03
Special Issue on Large-Scale Heterogeneous Multimedia Data Computing and Understanding
Submission Date: 2017-09-27

We are living in the era of large-scale multimedia data in a heterogeneous space. This era not only provides new opportunities to jointly represent objects from distinct aspects, but also brings great challenges in data understanding and analysis. Apart from the traditional audios, images, and videos, data in this era exhibit unprecedented modalities, such as user connections, user behaviors, and geographical annotations. To gain insightful understanding and analysis into the data, recent years have witnessed the wave of a variety of machine learning algorithms and frameworks, ranging from deep learning to quantum learning models. It therefore becomes vital to report the very recent progress in advanced machine learning methodologies and state-of-the-arts for handling large-scale heterogeneous multimedia data. We are targeting at inviting original research outputs in this field, including new theories, applications, benchmark datasets, and new industrial deployments on the topic. The list of possible topics includes, but not limited to: 1. Large-scale heterogeneous media data computing - Multimodal media data acquisition - Image/video feature extraction - Heterogeneous data feature learning - Deep learning methods for media computing 2. Large-scale heterogeneous media data management - Multimodal data indexing - Hash methods with multimodal data - Search with multimodal data - Cross-view or cross-modal Search 3. Large-scale heterogeneous media understanding - Retrieval, classification and recognition with multimodal data - Multi-View or Multimodal data fusion technique - Multimodal dictionary learning technique - Human-Computer-Interaction with multimodal data - Learning methods using multimodal data - Deep learning methods for heterogeneous feature fusion
Last updated by Dou Sun in 2017-06-03
Special Issue on Content Based Multimedia Indexing
Submission Date: 2017-10-15

Multimedia indexing systems aim at providing user-friendly, fast and accurate access to large multimedia repositories. Various tools and techniques from different fields such as data indexing, machine learning, pattern recognition, and human computer interaction have contributed to the success of multimedia systems. In spite of significant progress in the field, content-based multimedia indexing systems still show limits in accuracy, generality and scalability. The goal of this special issue is to bring forward recent advancements in content-based multimedia indexing. In addition to multimedia and social media search and retrieval, we wish to highlight related and equally important issues that build on content-based indexing, such as multimedia content management, user interaction and visualization, media analytics, etc. The special issue will also feature contributions on application domains, e.g., deep learning for multimedia indexing, sparse data learning, cultural heritage and synergetic media production.
Last updated by Dou Sun in 2017-04-13
Special Issue on Spatial-Temporal Feature Learning for Unconstrained Video Analysis
Submission Date: 2017-12-15

With the development of mobile Internet and personal devices, we are witnessing an explosive growth of video data on the Web. This has encouraged the research of video analysis. Compared to the trimmed videos in the open benchmark datasets, most of the real-world videos are unconstrained. Firstly, as captured under different conditions, unconstrained videos usually have large intra-class differences. Secondly, as captured by different devices and people, unconstrained videos may own more variants in quality. The success of hand-crafted descriptors lies in the simultaneously incorporating spatial description of each frame and temporal consistency of successive frames. Recently, researchers have tried to learn video representations from deep ConvNets, where the promising progresses were obtained owing to the breakthrough in the appropriately pooling or encoding of temporal information of video sequences in the deep neural networks. As the visual content and temporal consistency of unconstrained videos are more complex, there are still challenges in video analysis and practical applications. This special issue serves as a forum for researchers all over the world to discuss their works and recent advances in video feature learning and its applications in real world applications. Both state-of-the-art works, as well as benchmark datasets and literature reviews, are welcome for submission. This special issue seeks to present and highlight the latest developments on practical methods of unconstrained video analysis. Papers addressing interesting real-world applications are especially encouraged. Topics of interest include, but are not limited to, - Feature learning by multi-cue fusion for unconstrained video analysis - Pooling the spatial-temporal layers in deep ConvNets - End-to-end integration of RNN and CNN for video feature learning - Effective feature learning for video captioning - Ad hoc feature learning for video event detection - Adapt un-labeled videos for robust feature learning - Transfer feature learning for video analysis - Spatial-temporal hashing and indexing for large-scale video retrieval - Unconstrained video benchmark for the evaluation of future learning - Real-world applications of unconstrained video analysis with future learning, e.g., event detection, action recognition, retrieval, summarization, synthesis, and video-to-language captioning.
Last updated by Dou Sun in 2017-06-14
Related Publications
Related Conferences
CCFCOREQUALISShortFull NameSubmissionNotificationConference
ICTCInternational Conference on ICT Convergence2017-07-312017-08-252017-10-18
PHMPrognostics and System Health Management Conference2017-04-152017-05-152017-07-09
BigDataServiceInternational Conference on Big Data Computing Service and Applications2016-12-012016-12-222017-04-06
CIAInternational Conference on Computer, Information and Application2016-03-302016-04-152016-05-19
AEEInternational Conference on Advances in Electrical Engineering2016-07-162016-07-252016-07-30
bTrustBusInternational Conference on Trust, Privacy, and Security in Digital Business2016-04-042016-06-062016-09-05
ICCAAEInternational Conference on Computer Applications and Applied Electronics2016-08-262016-08-312016-09-10
DCAInternational Conference on Digital Contents and Applications2015-10-152015-11-102015-12-16
ICCTIMInternational Conference on Computing Technology and Information Management2015-04-052015-04-102015-04-21