Scientific Programming for Multimodal Big Data 2021
1Dalian University of Technology, Dalian, China
2Montclair State University, Montclair, USA
3St. Francis Xavier University, Antigonish, Canada
4China University of Mining and Technology, Xuzhou, China
Scientific Programming for Multimodal Big Data 2021
Description
In this era of big data, there is an increase of data collection and description measures. Multimodal data contains a wide array of data in various formats or modalities. It can be collected far more easily than ever before. It is important to discover the features and knowledge hidden in the data through comprehensive understanding and scientific programming. The data can provide benefits across many different applications, from scientific and engineering computing to intelligent decisions and predictive services.
In multimodal data, different modalities represent data samples from different perspectives. It usually provides complementary information to each other. Exploiting complementary characteristics can lead to a more comprehensive description of data samples. However, integrating knowledge across modalities and thereby unlocking the huge value of the data is still a significant problem in big data research. This is the major difference between learning tasks in big data and traditional data. Scientific programming plays a significant role in providing solutions and mechanisms to issues surrounding multimodal big data, such as optimizing the processing of large volumes or high dimensions of low-quality multimodal data and accelerating the analysis of real-time multimodal data. It also helps integrate and fuse the features of heterogeneous multimodal data.
The aim of this Special Issue is to attract high-quality papers from academics and industry researchers in big data and data fusion. We hope that this Special Issue gathers the most recent advanced methods and applications for effective fusion of multimodal big data with scientific programming. We welcome both original research and review articles.
Potential topics include but are not limited to the following:
- Scientific programming methods and tools for multimodal data
- Multimodal data fusion and analysis
- Multimodal feature learning
- Low-quality multimodal data fusion
- Incremental and online multimodal data fusion
- Domain adaptation for multimodal data
- Cross-modal learning for multimodal data
- Knowledge reasoning for multimodal data
- Multimodal feature fusion for medical data
- Multimodal data programming and industry applications
- Multimodal data programming in other fields