Arabic Multimodal Machine Learning: Datasets, Applications, Approaches, and Challenges
It provides a structured overview for researchers in Arabic MML, identifying critical gaps to guide future work, but is incremental as a survey paper.
This paper conducts a comprehensive survey of Arabic Multimodal Machine Learning, organizing existing research into a novel taxonomy covering datasets, applications, approaches, and challenges to highlight research gaps and opportunities.
Multimodal Machine Learning (MML) aims to integrate and analyze information from diverse modalities, such as text, audio, and visuals, enabling machines to address complex tasks like sentiment analysis, emotion recognition, and multimedia retrieval. Recently, Arabic MML has reached a certain level of maturity in its foundational development, making it time to conduct a comprehensive survey. This paper explores Arabic MML by categorizing efforts through a novel taxonomy and analyzing existing research. Our taxonomy organizes these efforts into four key topics: datasets, applications, approaches, and challenges. By providing a structured overview, this survey offers insights into the current state of Arabic MML, highlighting areas that have not been investigated and critical research gaps. Researchers will be empowered to build upon the identified opportunities and address challenges to advance the field.