CFP | Virtual Images for Visual Artificial Intelligence
近年来,深度学习已经成为机器视觉与人工智能领域的核心技术。深度学习依赖海量的带标注数据,例如面向视觉计算任务的ImageNet、MS COCO等。但是,实际图像数据存在获取和标注成本高、难以覆盖复杂自然环境、极端场景样本稀少等问题,单纯依靠实际数据设计的深度学习系统,在实际应用时面临着可靠性不足的风险。鉴于此,利用计算机图形学、虚拟现实、生成式模型等技术构建典型多样的虚拟图像数据,与深度学习技术相结合,越来越成为视觉人工智能的主流。在视觉计算模型的训练、测试、理解、优化等方面,虚实互动的平行视觉方法正发挥着越来越重要的作用。
Neurocomputing专刊“Virtual Images for Visual Artificial Intelligence”主要关注虚拟图像的生成技术及其在视觉人工智能中的应用,欢迎相关领域的专家学者踊跃投稿!
CALL FOR PAPERS
Special Issue on Virtual Images for Visual Artificial Intelligence
Summary and Scope
Recently, deep learning has become one of the core technologies of computer vision and artificial intelligence. Deep learning is a data-driven technology and its performance heavily relies on large-scale labeled data, e.g., ImageNet and MS COCO. Unfortunately, it is rather expensive to collect and annotate large-scale image data from the real world, the collected real images are limited in covering complex environmental conditions, and the real scenes are uncontrollable and unrepeatable. As a result, the performance of current deep learning systems is not satisfactory while working in complex scenarios, such as autonomous driving and intelligent monitoring scenarios.
In light of the disadvantages of collecting images from the real world, more and more researchers start to synthesize and use virtual images for computer vision research. A variety of advanced techniques including computer graphics simulation, image style transfer, and generative models have been used for virtual image generation. The virtual images are especially valuable to the training, testing, understanding and optimization of learning-based models in computer vision.
This special issue emphasizes the important role of virtual images in deep learning and computer vision research, and welcomes a broad range of submissions developing and using virtual images for visual artificial intelligence. The list of possible topics includes, but is not limited to:
● New image synthesis methods
● Computer graphics and virtual/augmented reality for scene simulation
● Graphics rendering techniques for generating photorealistic virtual images
● Image-to-image translation and video-to-video translation
● Image super-resolution
● Deep generative models related to virtual images (variational autoencoders, generative adversarial networks, etc.)
● Neural networks that learn from virtual images
● Domain adaptation methods for deep learning
● Understanding deep architectures using virtual images
● Intelligent visual computing with virtual images
● Virtual-real interactive parallel vision and parallel imaging
● Virtual images and artistic creation
● Applications of virtual images to intelligent systems (robots, autonomous vehicles, visual monitoring systems, medical devices, and so on)
Submission Guidelines
Authors should prepare their manuscripts according to the "Instructions for Authors" guidelines of “Neurocomputing” outlined at the journal website
https://www.elsevier.com/journals/neurocomputing/0925-2312/guide-for-authors.
All papers will be peer-reviewed following a regular reviewing procedure. Each submission should clearly demonstrate evidence of benefits to society or large communities. Originality and impact on society, in combination with a media-related focus and innovative technical aspects of the proposed solutions will be the major evaluation criteria.
Important Dates
Submission Deadline: April 15, 2018
First Review Decision: June 30, 2018
Revisions Due: July 31, 2018
Final Manuscript: September 30, 2018
Expected publication date: December 2018
Guest Editors
Kunfeng Wang (Institute of Automation, Chinese Academy of Sciences, China and Qingdao Academy of Intelligent Industries, China), Managing Guest Editor, with e-mail: kunfeng.wang@ia.ac.cn
Fei-Yue Wang (Institute of Automation, Chinese Academy of Sciences, China), with e-mail: feiyue.wang@ia.ac.cn
Visvanathan Ramesh (Goethe University, Frankfurt, Germany), with e-mail: ramesh@fias.uni-frankfurt.de
Ashish Shrivastava (Apple Inc., USA), with e-mail: ashish.umd@gmail.com
David Vázquez (Autonomous University of Barcelona (UAB), Spain), with e-mail: aklaway@gmail.com
Fuxin Li (Oregon State University, USA), with e-mail: lif@engr.orst.edu
📚往期文章推荐
🔗人工智能名人堂第55期 | BP算法之父: Paul J. Werbos
🔗中国工程院院士李正名谏言教育部长:科研评价过于注重论文篇数
🔗他引发了26亿美金无人车诉讼,现在正自我封神人工智能宗教领袖
德先生公众号 | 往期精选
在公众号会话位置回复以下关键词,查看德先生往期文章!
人工智能|机器崛起|区块链|名人堂
虚拟现实|无人驾驶|智能制造|无人机
科研创新|网络安全|数据时代|人机大战
……
更多精彩文章正在赶来,敬请期待!
点击“阅读原文”,移步求知书店,可查阅选购德先生推荐书籍。