Team Members: Starr Corbin
In the era of big data, integrating multiple data sources, including text and images, presents a significant challenge due to the diversity in data modalities and the complexity of underlying relationships. Knowledge graphs, with their ability to represent complex interrelations in a structured form, have the potential to integrate and associate relationships between multi-modal data, thereby facilitating a more coherent understanding of multiple, large datasets.
This research delves into state-of-the-art approaches for integrating textual and visual data within KGs, including entity recognition, linking strategies, and the use of semantic technologies for enhancing data interoperability and fusion effectiveness. Challenges such as scalability, data quality, and dynamic updates in KGs are also addressed, alongside emerging trends like the use of artificial intelligence for automating and optimizing knowledge graph construction and multi-modal data fusion processes.
Through this comprehensive synthesis, this research aims to provide a deep understanding of the current landscape, challenges, and future prospects of using knowledge graphs for multi-modal data fusion within efforts to combat human trafficking.