Urban computing is a process of acquisition, integration, analysis, and understanding of the urban data generated from various sources (e.g., sensors, devices, and social media) for various applications (e.g., tackling air pollution and monitoring urban activities). Multimedia computing plays a vital role in urban computing due to the huge presence of multimodal sensors, heterogeneous multimedia data (e.g., check-ins, location, images, videos, and text) from social media, and multimedia interaction between human and cities. Recently, benefiting from both the easy availability of urban multimedia big data and the rapid development of deep learning technologies, some novel methods in multimedia computing have emerged as a promising tool for solving new urban computing tasks, such as quantifying urban perception and estimating the demographic makeup of neighborhoods. Meanwhile, these advances have led to new research directions, such as geographical or urban multimedia computing, at the intersection between multimedia computing and urban computing. However, it also brings new challenges:
Urban multimedia data has its own characteristics, such as biased and spatial-temporal properties. Without considering their distinctiveness, directly utilizing existing multimedia computing methods hardly fits the requirements.
Urban multimedia data analysis involves the interaction between humans and cities, such as the perception of the urban environment. There are limitations to existing methods because of the subjective annotations for the perceptions of urban physical appearance.
Urban multimedia computing is an interdisciplinary field where multimedia computing meet geo-computation and conventional city-related fields, like urban sociology and urban economics. In order to effectively utilize multimedia computing methods for modeling urban multimedia data, we should consider relevant theories from other fields. Therefore, there is a growing demand for developing and designing new multimedia computing methods for urban data analysis and applications, especially in the current deep learning and multimedia big data era.
The goal of this special issue is to provide a premier forum for researchers to present their recent studies on emerging methods in multimedia computing for urban multimedia computing. The topics of interest for this special issue include, but are not limited to:
Multi-source, multi-modality urban data fusing
Cross-device, cross-domain urban multimedia data correlation
Spatial-temporal urban multimedia data modeling
Urban, multimodal data mining from social media
Visual urban perception
High-level urban attributes (e.g., the crime rate, safety, and education) learning from urban multimodal data
Large-scale visual geo-localization and multi-modal geo-localization
Deep neural networks for urban data representation
Multimedia computing systems for urban data analysis, retrieval, and recommendation
Urban multimedia data interaction and visualization
Urban multimedia data collections, benchmarking, and performance evaluation
Other methods in multimedia computing for novel applications in urban computing
Only submissions that describe previously unpublished, original, state-of-the-art research and that are not currently under review by a conference or journal will be considered. Extended versions of conference papers must be at least 30 percent different from the original conference works. Articles submitted to IEEE MultiMedia should not exceed 6,500 words, including all text, the abstract, keywords, bibliography, biographies, and table text. The word count should include 200 words for each table and figure. There is a maximum of 20 references for final manuscripts. Authors should be aware that IEEE MultiMedia cannot accept or process papers that exceed this word limit. Articles should be understandable by a broad audience of computer science and engineering professionals, avoiding a focus on theory, mathematics, jargon, and abstract concepts. All manuscripts must be submitted to ScholarOne Manuscripts by the deadline in order to be considered for publication. Submissions are subject to peer review on both technical merit and relevance to IEEE MultiMedia readership. Accepted papers must be well written and understandable, as the level of editing will be a light copyedit. For accepted papers, authors will be required to provide electronic files for each figure according to the following guidelines: for graphs and charts, authors must submit them in their original editable source format (PDF, Visio, Excel, Word, PowerPoint, etc.); for screenshots or photographs, authors must submit high-resolution files (300 dpi or higher at the largest possible dimensions) in JPEG or TIFF formats.