Generative AI refers to a class of artificial intelligence systems that can learn from existing data and generate new data, thereby achieving functions similar to human creativity. Unlike traditional AI systems, generative AI systems can create new content on their own rather than merely processing input data. It can be realized through various technologies such as deep learning, GAN (Generative Adversarial Networks), etc., by training on large-scale datasets to learn the essential patterns of abstract data and using models to generate new data.
This issue focuses on “Generative AI” technology, which has been widely applied in various fields such as music generation, image generation, text generation, etc. These applications allow people to quickly generate a large amount of creative content, bringing new opportunities and challenges to the creative industry.
Publication trends in the field of Generative AI by IEEE over the past 10 years. (Click on “Read the Original” at the end of the article to download the full report and access the publication data for previous years.)
Data Source: IEEE Xplore, June 2023
Key technical terms in the field of Generative AI by IEEE.
Data Source: IEEE Xplore, June 2023
Global research situation in the field of Generative AI. (Click on “Read the Original” at the end of the article to download the full report for research situations in some countries.)
Data Source: IEEE Xplore, June 2023
IEEE Transactions on Pattern Analysis and Machine Intelligence
About this Journal: A monthly journal focusing on research related to computer vision and image understanding, pattern analysis and recognition, and machine intelligence, with a particular emphasis on machine learning used for pattern analysis. Additionally, this journal also focuses on specialized hardware or software architectures related to technologies involving visual search, document and handwriting analysis, medical image analysis, video and image sequence analysis, content-based image and video retrieval, facial and gesture recognition.
Recommended articles related to “Generative AI” in this journal:
-
GLEAN: Generative Latent Bank for Image Super-Resolution and Beyond
-
RankSRGAN: Super Resolution Generative Adversarial Networks With Learning to Rank
-
A Systematic Survey on Deep Generative Models for Graph Generation
The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023
CVPR 2023 will be held from June 18 to 22, 2023, in Vancouver, Canada. As a premier annual event in the field of computer vision, it attracts many organizations in the technology sector. The conference focuses on research related to computer vision and pattern recognition, mainly including learning, artificial intelligence, image and video processing and analysis, etc.
Recommended articles related to “Generative AI” at this conference:
-
Generative Dual Adversarial Network for Generalized Zero-Shot Learning
-
End-to-end Generative Pretraining for Multimodal Video Captioning
-
Non-Adversarial Image Synthesis With Generative Latent Nearest Neighbors
How to Grow a Robot: Developing Human-Friendly, Social AI
Introduction to the E-Book: The development of deep learning is considered the foundation of future artificial intelligence. The author points out that people need more insightful, responsive, and human-like artificial intelligence that is more social, interactive, and interesting than machines. He believes that the way to achieve this goal is to “nurture” robots to learn from experience. In this book, the author also describes his experiments with the iCub humanoid AI and explains how iCub learns from its own experiences. The aim of artificial intelligence is to treat humans as objects while learning empathy and developing robots with an internal “self” model to better interact with humans.
P3129/D3, Aug 2022 – IEEE Approved Draft Standard for Robustness Testing and Evaluation of Artificial Intelligence (AI)-based Image Recognition Service
Standard Introduction: This standard provides a set of testing specifications for common damage and adversarial attack metrics that can be used to evaluate the robustness of AI-based image recognition services. The standard specifies robustness requirements and establishes an evaluation framework to assess the robustness of AI-based image recognition services in various settings. The purpose of this standard is to guide individuals or organizations developing/using AI-based image recognition services in testing/evaluating these services and improving the robustness of the aforementioned services. It is also applicable to guide third-party evaluation laboratories to score individual algorithm implementations to test and evaluate the robustness of these services through standardized testing.
Copywriting | IEEE Xplore
Editor | Mao Jingjing
Editor-in-Chief | Zhang Yanhua
Reviewer | Zhang Yuanyuan
Read the Original