Tat-Seng Chua教授

简介：Dr Chua is the KITHCT Chair Professor at the School of Computing, National University of Singapore. He was the Acting and Founding Dean of the School from 1998-2000. Dr Chua’s main research interest is in multimedia information retrieval and social media analytics. In particular, his research focuses on the extraction, retrieval and question-answering (QA) of text and rich media arising from the Web and multiple social networks. He is the co-Director of NExT, a joint Center between NUS and Tsinghua University to develop technologies for real-time social media search. Dr Chua is the 2015 winner of the prestigious ACM SIGMM award for Outstanding Technical Contributions to Multimedia Computing, Communications and Applications. He is the Chair of steering committee of ACM International Conference on Multimedia Retrieval (ICMR) and Multimedia Modeling (MMM) conference series. Dr Chua is also the General Co-Chair of ACM Multimedia 2005, ACM CIVR (now ACM ICMR) 2005, ACM SIGIR 2008, and ACM Web Science 2015. He serves in the editorial boards of four international journals. Dr. Chua is the co-Founder of two technology startup companies in Singapore. He holds a PhD from the University of Leeds, UK.

报告题目：From Object Detection to Relation Inferencing in Videos

摘要：We are experiencing an unprecedented evolution of deep learning techniques in multimedia. As a holy grail of Artificial Intelligence, the task of connecting vision and language perhaps gains the most appreciable benefits in recent years. For example, today’s machines are able to outperform humans in a controlled large-scale visual recognition, and describe or answer questions about an image/video in natural language. This has made possible the industry deployment of a range of visual oriented applications such as fashion, home furnishing and product search. In this talk, I will first provide a brief retrospect of the progress of the connection in the pre- and current deep learning era. Then, I will outline some applications of visual technology in several vertical domains. Next, I will introduce our recent works in addressing what is missing in the state-of-the-art paradigm, including the groundings of open-vocabulary and deeper scene understanding such as object relations. Lastly, we will discuss recent work in video analytics and several interesting future research directions.

孙茂松教授

简介：孙茂松，清华大学计算机科学与技术系教授、党委书记。2007-2010年任该系系主任。主要研究领域为自然语言处理、互联网智能、机器学习、社会计算和计算教育学。国家重点基础研究发展计划（973计划）项目首席科学家，国家社会科学基金重大项目首席专家。在国际刊物、国际会议、国内核心刊物上发表论文160余篇，主持完成文本信息处理领域ISO国际标准2项。主要学术兼职包括：教育部在线教育研究中心副主任，清华大学大规模在线教育研究中心主任，清华大学-新加坡国立大学下一代搜索技术联合研究中心共同主任，国务院学位委员会第六届学科评议组计算机科学与技术组成员，国家自然科学基金委员会第十二、十三届专家评审组成员，中国科学技术协会第九届全国委员会委员，北京市语言文字工作委员会专家委员会副主任，中国中文信息学会第六、七届副理事长，《中文信息学报》主编，《大数据》杂志编委会副主任，全国计算机慕课联盟副理事长，多个教育部或省市级重点实验室学术委员会主任、副主任，国家语言文字工作委员会“两岸语言文字交流与合作协调小组”成员等。2007年获全国语言文字先进工作者，2016年获全国优秀科技工作者以及首都市民学习之星。

报告题目：运用之妙、存乎一心——从机器翻译到古诗生成摘要：本报告通过两个貌似几乎不相干的人工智能典型应用——机器翻译和古诗自动生成，揭示并彰显了隐身于其后的语言计算共性机制——深层神经网络的重要作用。一方面，试图从宏观角度对机器翻译的发展历程进行扼要的总结，着重于刻画各个时期在基本方法和核心技术上的主要特征，从而勾勒出机器翻译的全过程演进脉络。另一方面，对古诗自动生成的进展水平进行了具体而生动的评介。在上述讨论的基础上，本报告最后就人工智能近中期发展趋势给出了若干研判。

组织委员会

组委会: 聂礼强 (山东大学) 陈竹敏 (山东大学) 甘 甜 (山东大学) 宋雪萌 (山东大学) 刘 倩 (山东大学)

主办单位：山东大学
时间：2017年4月17日
地点：济南市舜华路1500号山东大学齐鲁软件学院校区 办公楼二层圆形报告厅