Learning Compact Hash Codes for Multimodal Representations Using Orthogonal Deep Structure


As large-scale multimodal data are ubiquitous in many real-world applications, learning multimodal representations for efficient retrieval is a fundamental problem. Most existing methods adopt shallow structures to perform multimodal representation learning. Due to a limitation of learning ability of shallow structures, they fail to capture the correlation… (More)
DOI: 10.1109/TMM.2015.2455415


10 Figures and Tables


Citations per Year

Citation Velocity: 39

Averaging 39 citations per year over the last 2 years.

Learn more about how we calculate this metric in our FAQ.

Slides referencing similar topics