Multimodal Machine Learning: Techniques and Applications explains recent advances in multimodal machine learning, providing a coherent set of fundamentals for designing efficient multimodal learning algorithms for different applications. The book addresses the main challenges in multimodal machine learning based computing paradigms, including multimodal representation learning, translation and mapping, modality alignment, multimodal fusion and co-learning. The book also explores the important texture feature descriptors based on recognition and transform techniques. It is ideal for senior undergraduates, graduate students, and researchers in data science, engineering, computer science and statistics.