Presentation mode and information richness are constantly improving with the development of human living environments and working styles, and multimedia computing will play an increasingly important role.

Multimedia computing concerns the computational methods for efficient and effective processing of multimedia data. In multimedia computing, the heterogeneous representations and inconsistent distributions of multimedia data of different modalities, e.g. text, audio, and image, make it challenging to correlate the data and perform analysis. Generative adversarial networks (GAN) have been attracting extensive attention from both academia and industry because GAN can perfectly generate new data with the same statistics as the training set. It is natural to ask whether GAN can be used to model the common distribution of multi-modal multimedia data, learn the discriminative representation to close the heterogeneity gap, and facilitate multimedia applications.

This Special Issue aims to report high-quality research on the recent advances of generative adversarial networks for multi-modal multimedia computing; more specifically the state-of-the-art algorithms, models, methodologies, and systems based on generative adversarial networks to analyze multi-modal multimedia data. It is anticipated that sufficient progress can be achieved to mitigate the long-standing heterogeneity issue in multimedia computing. Original research and review articles are welcome.

Potential topics include but are not limited to the following:

• Generative and discriminative models for multi-modal multimedia computing
• Generative adversarial networks for representation learning of multi-modal multimedia data
• Generative adversarial networks for feature extraction of multi-modal multimedia data
• Novel applications of multimedia computing based on generative adversarial networks
• Machine learning algorithms, models, and frameworks for efficient and effective processing of multi-modal multimedia data
• Theory of generative adversarial networks for multi-modal multimedia computing