Conferences
27–30 June 2022, Newark, NJ, USA
The Third Workshop on Intelligent Cross-Data Analytics and Retrieval (ICDAR 2022)
Data play a critical role in human life. In the digital era, where data can be collected almost anywhere, at any time, and by anything, people can own a vast volume of real-time data reflecting their living environment in various granularities. From these data, people can extract the necessary information to gain knowledge towards becoming informed. As data do not come from a sole source, they only reflect a small part of the massive puzzle of life. Hence, the more pieces of data that can be collected and filled into the canvas, the faster the puzzle can be solved. If we consider a puzzle piece to be single-modal data, the puzzle becomes a multimodal data analytic problem. If we consider a group of puzzle pieces assembled as a segment of the puzzle to be one domain (e.g., a mountain, house, or animal), the puzzle game becomes a multi-domain problem. If we consider a 3D puzzle game, it becomes a multi-platform problem. Finally, bidirectional mapping between puzzle pieces and the frame (e.g., a sample picture of a puzzle) during the game can be considered as a cross-data/domain/platform problem. In other words, we can use a set of data (i.e., multimodal data) from certain domains with analytic models built on one platform to infer (e.g., predict, interpolate, or query) data from another domain(s) and vice versa. We have witnessed the rise of cross-data against multimodal data problems recently. The cross-modal retrieval system uses a textual query to look for images; some examples of this research direction include: the air quality index can be predicted using lifelogging images; congestion can be predicted using weather and tweets data; daily exercises and meals can help to predict sleeping quality. Although vast investigations focusing on multimodal data analytics have been developed, few cross-data (e.g., cross-modal data, cross-domain, or cross-platform) research has been carried out. In order to promote intelligent cross-data analytics and retrieval research and to bring about a smart, sustainable society for human beings, this specific article collection on "Intelligent Cross-Data Analysis and Retrieval" is introduced. This research topic welcomes those who come from diverse research domains and disciplines such as well-being, disaster prevention and mitigation, mobility, climate change, tourism, healthcare, and food computing.
Example topics of interest include, but are not limited to the following:
- Event-based cross-data retrieval data mining and AI technology.
- Complex event processing to link sensor data from individuals and regions to broad areas dynamically.
- Transfer learning and transformers.
- Hypotheses development of the associations within heterogeneous data.
- The realization of a prosperous and independent region in which people and nature coexist.
- Applications leverage intelligent cross-data analysis for a particular domain.
- Cross-datasets for repeatable experimentation.
- Federated analytics and federated learning for cross-data.
- Privacy–public data collaboration.
- Integration of diverse multimodal data.
