15
2022-04
12:00 - 12:00
MICCAI2022多模态腹部分割国际挑战赛(AMOS22)
国际顶级医学图像和计算机辅助介入大会MICCAI2022将于9月在新加坡召开。深圳大数据研究院,香港中文大学(深圳),香港大学,中山大学等多家研究机构将联合深圳市龙岗区人民医院,深圳市龙岗区中心医院举办MICCAI2022多模态腹部分割国际挑战赛(AMOS22),旨在通过开放数据集和挑战赛促进相应医疗分割算法的发展。
挑战赛背景
腹部多器官分割一直是医学图像分析领域最活跃的研究领域之一,其做为一项基础技术,在支持支持疾病诊断,治疗规划等计算机辅助技术发挥着重要作用。 近年来,基于深度学习的方法在该领域中获得了巨大成功,却也暴露出了一个迫切问题: 当前社区缺乏一个大规模的,多样性的,符合真正临床场景的综合基准数据集来开发/评估对应的算法。虽然目前已有几个腹部器官分割数据集,它们的标注器官和标注例子数目却相对有限的, 仍然限制了现代深度模型的力量,也难以对提出的不同方法进行全面和公平的评估。
为了解决上述问题,进一步促进医疗图像分割技术的发展,深圳大数据研究院,香港中文大学(深圳),香港大学,中山大学等机构联合深圳市龙岗区人民医院,深圳市龙岗区中心医院提出了多模态腹部分割数据集(AMOS),一个大规模,多样性的,收集自真实临床场景下的腹部多器官分割基准数据。AMOS 总计提供了500个CT与100个MRI扫描,每个扫描附带了15个腹部器官的体素级标注, 是目前已知最全面的腹…
更多
29
2022-04
08:40 - 17:40
Zoom Meeting ID: 778 472 0808 Passcode: 202204
Workshop on recent advances in image processing
In recent years, deep learning has achieved great success and many advances in image processing. This workshop aims to discuss the progress, challenges and opportunities of both traditional mathematical model-based and deep learning-based methods in image processing, and seek further integration and development.
For more information please visit: http://www.sribd.cn/WorkshopImage/index.html
更多
07
2022-04
10:00 - 11:30
哔哩哔哩,腾讯研究院视频号同步线上直播
“AI安全与隐私” 系列论坛第十二期:Trustworthy AI: to Be Robust or to Be Fair
“AI安全与隐私”系列论坛第十二期将于4月7日下周四上午10点-11点半举行,此次我们荣幸邀请到了密歇根州立大学汤继良教授分享关于“可信人工智能中的鲁棒性和公平性可以兼得吗?“的主题报告。汤教授是国际知名的学者,在可信人工智能和图神经网络方面做出了颇多开创性的工作。鲁棒性和公平性是深度学习中核心问题之一,汤教授将为大家带来深入的分析。
本次论坛由中科院自动化所梁坚教授担任主持人,由中国图像图形学学会视觉大数据专委会承办,由香港中文大学(深圳)广东省大数据计算基础理论与方法重点实验室和腾讯研究院联合协办,论坛将在Bilibili账号"AI安全与隐私"和腾讯研究院视频号同时直播,欢迎大家届时观看!
欢迎更多专家莅临本论坛分享您在AI安全与隐私方面的科研成果。
更多
24
2022-02
15:30 - 17:10
Room 103, Dao Yuan Building; Zoom
Design and Implementation of Some Effective Presolve Techniques for Linear Programming Solver
Abstract:
Presolve plays an important role in linear and mixed-integer programming optimization solvers. Effective presolvers can reduce model size significantly, detect infeasibility or unboundedness quickly, and tighten bounds of columns and rows. In this talk, design and implementation of some effective and practical presolve techniques for linear programming will be discussed.
Biography:
Longfei Wang is an engineer in Shenzhen Research Institute of Big Data. He has worked as an algorithm expert in AI department of Cainiao Network. He received master and bachelor degree from Peking Un…
更多
13
2022-01
15:30 - 17:10
Room 103, Dao Yuan Building; Zoom
Understanding the Capacity of Multi-Cell Non-orthogonal Multiple Access Systems
Abstract:
With the potential of enabling the massive device connection and enhancing the spectrum efficiency, non-orthogonal multiple access (NOMA) has been considered as a promising technology for the sixth generation (6G) wireless communication networks. The key idea of NOMA is to allow signals of different users to be superimposed on each other at the same time and on the same frequency. To extract intended messages, a receiver applies successive interference cancellation (SIC) to separate signals from different users. In this talk, we consider a fundamental problem for multi-cell NOMA sys…
更多
20
2022-01
15:30 - 17:10
Room 103, Dao Yuan Building; Zoom
Applications and Data Analysis on Campus Big Data
Abstract:
In Modern campus, smart devices such as cell phones are popular. The data generated by smart devices can help tackle some challenging issues such as preventing suicide and reducing dropout rates. In addition, campus data can help improving facility usage and university policy making. In this talk, I will discuss our Research and Development on applications based on campus big data.
Biography:
Dr. Jianjun Zhou received his Ph.D. degree in computing science from University of Alberta, his B.S. degree in computer science and technology from University of Science and Technology of…
更多
25
2021-11
00:00 - 12:00
ICASSP-SPGC-2022 通信网络智能运维大赛火热进行中
竞赛简介
5G新技术架构的引入和业务场景的多样性给智能化网络运维 (AIOps) 带来了新的挑战。无线网络故障根因定位是网络运维中的一个重要环节,通过快速且准确地判断出网络故障的根因,技术人员可以及时采取措施对网络进行修复。然而,现网经常受困于复杂的无线通信环境和网络部署结构,且存在网络故障样本数少、不同的场景下故障表征差异性大等问题。如何充分利用领域知识和一小部分标定数据,使用统计学习和因果推断技术,快速准确地定位故障的根因,是网络运维面临的巨大挑战。
为了加深学界对此类工业问题的理解,促进学界在此问题上的研究,香港中文大学(深圳)-深圳市大数据研究院-华为未来网络系统优化创新实验室联合在ICASSP 2022旗舰国际会议上组织举办本次竞赛。
本次竞赛使用业务场景数据集,包括领域专家提供的网络故障因果图。数据集中涵盖一系列工业应用实际难题,包括在少标签样本和有数据缺失的情况下进行高效时间序列分析和因果推断等,亟待具有不同专业背景的国内外学者和研究员共同解决!
ICASSP(International Conference on Acoustics, Speech and Signal Processing)是全世界最大的,也是最全面的融合信号处理、统计学习、及无线通信的综合性顶级会议。ICASSP-2022将于5月22日-27日在新加坡举行。…
更多
09
2021-09
10:00 - 11:00
Zoom会议室
Learning Theory of Deep Neural Networks
报告主题:
Learning Theory of Deep Neural Networks
报告嘉宾:
林绍波教授(西安交通大学)
报告时间:
9月9日(星期四)10:00-11:00
参与方式:
加入 Zoom 会议
https://cuhk-edu-cn.zoom.com.cn/j/99970274588?pwd=Tk0wUnlwSk1LWWlSWXo5UUQzWTRuQT09
会议号:999 7027 4588
密码:681114
报告简介:
Deep learning has attracted enormous research activities in the past decade. In this talk, we focus on theoretically demonstrating the power of depth, the role of massive data and the existence of a perfect global minima of ERM on deep ReLU nets. In particular, we derive optimal error bounds for running ERM on deep ReLU nets for numerous types of data. Our mai…
更多