Manuscript Topics

With the rapid development of deep learning technology, AI generative tasks have become a popular research area in the fields of multimedia signal processing, computer vision, machine learning, etc., with many potential applications, such as dialog box generation, text-to-speech conversion, image generation, video generation, and cross-modal generation between audio, video and text. As a typical representative of generative models, Generative Adversarial Networks (GANs) have attracted great attention in recent years. GANs are widely used in many fields, such as meteorology, healthcare, architecture, art, etc., due to their powerful generative capabilities and ease of use. In addition, GANs can improve accessibility and inclusion in content creation, making it easier for people with disabilities to access and use content. It is undeniable that GANs is gradually changing our lives.

However, the quality of GANs still needs to be improved and has not reached the same level as humans in several areas such as video generation. And as the depth of neural networks increases, the possible arrangements of network architectures and parameters explode, and the design of network architectures becomes a thorny issue. Applying evolutionary computation to complex neural networks helps to solve the network architecture design problem, especially when designing unstable network architectures such as GANs.

The purpose of this special issue is to explore the significance of evolutionary generative adversarial networks in different industries and applications. We welcome submissions of review articles examining evolutionary generative adversarial networks. We also encourage exploring the potential of evolutionary generative adversarial networks in improving accessibility and inclusiveness of content creation.

Potential topics include but are not limited to:
• Technical advances in evolutionary generative adversarial networks, including image generation, video generation, text generation and other algorithms.
• Evolutionary generative adversarial networks for neural architecture search.
• Applications of evolutionary generative adversarial networks in various industries and applications, such as multimedia marketing, advertising, journalism, entertainment and transportation.
• The forgery detection and quality evaluation of evolutionary generative adversarial networks, such as fake facial image detection and deepfake video detection.
• The potential of evolutionary generative adversarial networks for improving accessibility and inclusivity in image, video, and multimedia content creation.
• The technical challenges and opportunities of evolutionary generative adversarial networks.
• The future of evolutionary generative adversarial networks and its potential impact on society.

Instructions for authors
https://www.aimspress.com/era/news/solo-detail/instructionsforauthors
Please submit your manuscript to online submission system
https://aimspress.jams.pub/