预告 | 投稿倒计时7天:第十届国际图象图形学学术会议(ICIG 2019)征稿进行中

2019 年 5 月 13 日 AI科技评论

AI 科技评论消息,第十届国际图象图形学学术会议(ICIG 2019)将于 2019 年 8 月 23-25 日在北京友谊宾馆召开,主题为「人工智能时代的图像图形前沿研究」。国际图象图形学学术会议(ICIG)是中国图象图形学学会主办的最高级别的系列国际会议,创建于 2000 年,每两年举办一届,迄今已经成功举办九届。

会议征文将于 5 月 20 日截止,现面向广大科技工作者公开征集学术论文(英文),会议论文集将由 Springer 出版社出版,并被 EI 和 CPCI 检索。优秀的论文经扩展后将推荐到国内外高质量期刊的特刊(Pattern Recognition Letters、Cognitive Computation、Pattern Recognition 等)。

投稿系统网址:

http://cmt3.research.microsoft.com/ICIG2019

今年大会共计 3 个特邀报告、5 个热点前沿论坛、1 个顶会顶刊论坛、1 个博士生论坛、2 个技术竞赛、多场创新成果展。大会将为图像图形领域的专家学者和产业界同仁提供展示创新成果、探讨未来发展的平台,大会详情如下。

大会主题

人工智能时代的图像图形前沿研究

征文范围

  • Color and Multispectral Processing

  • Multi-View and Stereoscopic Processing

  • Biological and Medical Image Processing

  • Compression, Transmission, Retrieval

  • Computer Vision and Pattern Recognition

  • Computer Graphics and Visualization

  • Computational Imaging

  • Virtual Reality

  • Game and Animation

  • Artificial Intelligence

  • Surveillance and Remote Sensing

  • Security 

重要日期

  • 投稿截止日期:2019 年 5 月 20 日

  • 录用通知日期:2019 年 6 月 20 日

  • 终稿提交日期:2019 年 6 月 30 日

  • 开始注册日期:2019 年 6 月 20 日

特邀报告

Marc Alexa

Electronics & Information

Technical University of Berlin

Title: The Shape of Deformations

Abstract:

Let us say that a frame is given by three ‘sticks’ (of equal lengths) meeting in one common point. We are interested in representing the orientation and the ‘shape’ of the frame. Orientation is the rotation relative to a reference frame; and ‘shape’ is the deformation relative to a reference frame. It turns out that any frame can be turned into any other frame by a Möbius transformation. This viewpoint reveals that rotations are points on a 3-sphere, the so-called unit quaternions. Unit quaternions are well-known and quite useful as a representation for rotations in space — they are continuous in the variables, minimal in the sense that at least four coordinates are necessary for a continuous representation, and they come with a natural metric that allows us to measure the ‘amount’ of rotation, i.e. the angle. The viewpoint of Möbius transformations also reveals, and this is the new aspect of this work, that deformations are points on a hyperboloid. So ‘shape’ can be described as a point in hyperbolic space. This is a representation that, just like unit quaternions, is continuous, small, and comes with a natural metric that allows measuring the amount of deformation.

Biography:

Marc Alexa is a Professor in the Faculty of Electrical Engineering and Computer Science at the Technical University of Berlin and heads the Computer Graphics group. He is interested in creating, processing, and manufacturing shapes, as well as intuitive interfaces for these tasks. He holds a masters and PhD degree in Computer Science from Darmstadt University of Technology. He has been Technical Papers Chair for SIGGRAPH 2013, and has chaired several other committees and boards. He received an ERC Starting Grant, the Heinz Maier-Leibnitz prize, as well as other cross-disciplinary grants and awards. He is currently the editor in chief of ACM Transactions on Graphics.

Shmuel Peleg

School of Computer Science and Engineering

The Hebrew University of Jerusalem

Title: Improved Scene Understanding by Combining Sight and Sound

Abstract:

In traditional computer vision research, we were careful to strip and ignore the soundtrack. In the same manner, audio analysis traditionally ignored the available visual information in a video. I will describe how better scene understanding can be gained by using both sight and sound in video. One example will show how speech can be enhanced when using a video showing the face of the speaker. Also, video surveillance cases will be shown where the sound can enhance the understanding of scene activity.

Biography:

Shmuel Peleg received his Ph.D. in Computer Science from the University of Maryland in 1979, and since 1981 he is a professor at the Hebrew University of Jerusalem. Shmuel published over 150 technical papers in computer vision and image processing, and holds 23 US patents. He founded several startup companies, and his latest company, Briefcam, was acquired by Canon on 2018. Shmuel served as a committee member of numerous conferences, e.g. general co-chair of ICPR 1994, CVPR 2011, ICCP 2013, and CVPR 2018.

Jie Zhou

Department of Automation

Tsinghua University

Title: Low quality fingerprint recognition

Abstract:

Fingerprint recognition is one of the most widely used biometric technologies. Despite its wide applications, the recognition rate of low quality fingerprints, such as fingerprints of elderly people, latent fingerprints from crime scenes, and fingerprints of very dry or wet fingers, is still far from satisfactory. This talk will provide an introduction of our recent progress for low quality fingerprint recognition, including fingerprint enhancement, skin distortion rectification, and dense registration.

Biography:

Dr. Jie Zhou received the PhD degree from the Institute of Pattern Recognition and Artificial Intelligence, Huazhong University of Science and Technology (HUST), Wuhan, China, in 1995. He joined in the Department of Automation, Tsinghua University in 1997. Since 2003, he has been a full professor in the Department of Automation, Tsinghua University. From 2015 to 2018, he was the Chair of Department of Automation, Tsinghua University. From 2018 to now, he is the Dean of Graduate School, Tsinghua University. His research interests include pattern recognition, computer vision, and image processing. In recent years, he has authored more than 300 papers in peer-reviewed journals and conferences. Among them, more than 50 papers have been published in top journals and conferences (IEEE T-PAMI, T-IP, CVPR and ICCV). He received the National Outstanding Youth Foundation of China Award in 2012. He is a fellow of IAPR and Associate Editor of IEEE T-PAMI.

会议邮箱

icig@csig.org.cn

会议网址

http://icig2019.csig.org.cn

点击阅读原文,加入比赛交流小组和同行切磋交流

登录查看更多
4

相关内容

模式识别是一个成熟的、令人兴奋的、快速发展的领域,它支撑着计算机视觉、图像处理、文本和文档分析以及神经网络等相关领域的发展。它与机器学习非常相似,在生物识别、生物信息学、多媒体数据分析和最新的数据科学等新兴领域也有应用。模式识别(Pattern Recognition)杂志成立于大约50年前,当时该领域刚刚出现计算机科学的早期。在这期间,它已大大扩大。只要这些论文的背景得到了清晰的解释并以模式识别文献为基础,该杂志接受那些对模式识别理论、方法和在任何领域的应用做出原创贡献的论文。 官网地址:http://dblp.uni-trier.de/db/conf/par/
 第八届中国科技大学《计算机图形学》暑期课程课件
专知会员服务
56+阅读 · 2020年3月4日
【深度学习视频分析/多模态学习资源大列表】
专知会员服务
91+阅读 · 2019年10月16日
中国多媒体大会(ChinaMM 2020) 征文通知
专知
16+阅读 · 2020年3月27日
CCF推荐 | 国际会议信息6条
Call4Papers
9+阅读 · 2019年8月13日
计算机 | IUI 2020等国际会议信息4条
Call4Papers
6+阅读 · 2019年6月17日
CCF推荐 | 国际会议信息10条
Call4Papers
8+阅读 · 2019年5月27日
计算机类 | 低难度国际会议信息6条
Call4Papers
6+阅读 · 2019年4月28日
CCF A类 | 顶级会议RTSS 2019诚邀稿件
Call4Papers
10+阅读 · 2019年4月17日
学会征文|第三届亚洲人工智能技术大会征文通知
中国人工智能学会
3+阅读 · 2019年3月12日
人工智能 | 国际会议截稿信息9条
Call4Papers
4+阅读 · 2018年3月13日
会议征文|第一届中国模式识别与计算机视觉学术会议
中国人工智能学会
5+阅读 · 2017年12月6日
【今日新增】计算机领域国际会议截稿信息
Call4Papers
9+阅读 · 2017年7月21日
Directions for Explainable Knowledge-Enabled Systems
Arxiv
26+阅读 · 2020年3月17日
Arxiv
6+阅读 · 2018年4月23日
Arxiv
4+阅读 · 2017年11月14日
VIP会员
相关VIP内容
 第八届中国科技大学《计算机图形学》暑期课程课件
专知会员服务
56+阅读 · 2020年3月4日
【深度学习视频分析/多模态学习资源大列表】
专知会员服务
91+阅读 · 2019年10月16日
相关资讯
中国多媒体大会(ChinaMM 2020) 征文通知
专知
16+阅读 · 2020年3月27日
CCF推荐 | 国际会议信息6条
Call4Papers
9+阅读 · 2019年8月13日
计算机 | IUI 2020等国际会议信息4条
Call4Papers
6+阅读 · 2019年6月17日
CCF推荐 | 国际会议信息10条
Call4Papers
8+阅读 · 2019年5月27日
计算机类 | 低难度国际会议信息6条
Call4Papers
6+阅读 · 2019年4月28日
CCF A类 | 顶级会议RTSS 2019诚邀稿件
Call4Papers
10+阅读 · 2019年4月17日
学会征文|第三届亚洲人工智能技术大会征文通知
中国人工智能学会
3+阅读 · 2019年3月12日
人工智能 | 国际会议截稿信息9条
Call4Papers
4+阅读 · 2018年3月13日
会议征文|第一届中国模式识别与计算机视觉学术会议
中国人工智能学会
5+阅读 · 2017年12月6日
【今日新增】计算机领域国际会议截稿信息
Call4Papers
9+阅读 · 2017年7月21日
Top
微信扫码咨询专知VIP会员