中国计算机学会青年计算机科技论坛
CCF Young Computer Scientists & Engineers Forum
CCF YOCSEF
济南
于 2015 年 7 月 11 日(星期六)8:30-18:00
在山东大学举行
（济南市高新开发区舜华路 1500 号，山东大学软件园校区办公楼）
报告会主题
机器学习与机器视觉
程 序
执行主席：许信顺 张伟 杨成伟
机器学习与机器视觉研讨会
参加人员：IT 领域专业人士、研究生、媒体、其他有兴趣者
地点：山东大学计算机科学与技术学院办公楼圆形报告厅
上午：
8:30-9:00 签到
9:00-10:00 报告一
10:00-11:00 报告二
11:00-12:00 报告三
下午：
14:00-14:30 签到
14:30-15:30 报告四
15:30-16:30 报告五
16:30-17:30 报告六17:30-18:00 panel（主题为：强人工智能社会人与机器人的关系）
报告一：
报告题目：归类问题研究
特邀讲者：于剑
报告摘要：
在大数据时代，如何从数据中提取知识是一个亟待解决的问题。而概念是知识的
基本单位。 从数据中提取概念称为归类问题。 对于机器学习来说，归类通常包
括数据降维、密度估计、回归，聚类和分类等问题。目前，针对归类问题文献中
已经提出了众多的机器学习算法。这些算法的理论基础涉及面广， 彼此之间的
关系极其复杂。本次报告试图提出一个统一的归类表示方法， 其基本假设是：
归哪类，像哪类；像哪类，归哪类。据此，首次建立了归类公理化体系。该公理
化体可以推演出归类方法的三条设计原则，以统一的方式重新解释了数据降维、
密度估计、回归，聚类和分类等问题，而且与日常生活中的认知原则一致。
个人简介：
于剑，博士，教授，博士生导师。北京大学本科，硕士，博士。现任交通数据分
析与挖掘北京市重点实验室主任，北京交通大学计算机科学系主任, 中国计算机
学会人工智能与模式识别专委会副主任兼秘书长，中国人工智能学会机器学习专
委会副主任，《计算机学报》、《软件学报》、《计算机研究与发展》等多个学术期
刊编委，数字出版技术国家重点实验室学术委员会委员，主持多项国家自然科学
基金项目、教育部重点项目等。主要研究兴趣为模式识别，机器学习、数据挖掘
等。已经在国内外重要学术期刊发表相关学术论文多篇，包括 TPAMI, CVPR,
TIP,TFS,TNN, TSMCB 等。
报告二：
报告题目：
Self-paced Learning: Challenge and Opportunity
特邀讲者：孟德宇
报告摘要：
Self-paced learning (SPL) is a recently proposed learning regime inspired
by the learning process of humans and animals that gradually incorporates
easy to more complex samples into training. While several easy SPL
implementation strategies have been proposed, it is still short of a
general paradigm for guiding the construction of rational SPL learning
regimes targeting specific applications. To resolve this problem, weprovide an axiom for insightfully formulating the underlying principles
of self-paced learning. This axiomatic understanding not only involves
the previous SPL learning schemes as its special cases, but also can be
utilized to extend a series of new SPL implementation regimes based on
certain application aims. In the recent two years, we have constructed
several SPL realizations, including SPaR, SPLD, SPCL, SPMF, based on this
axiom, and achieved the best performance in several known benchmark
datasets, e.g., Web Query, Hollywood2, and Olympic Sports. Especially,
this paradigm has been integrated into the system developed by CMU
Informedia team, and achieved the leading performance in challenging
semantic query (SQ)/000Ex tasks of the TRECVID MED/MER competition
organized by NIST in 2014.
In this talk, I will introduce some of our main developments along this
line, and attempt to discuss several of the typical challenges and
possible opportunities for future SPL research.
个人简介：
孟德宇，西安交通大学数学与统计学院副教授。曾赴香港理工大学，Essex 大学
与卡内基梅隆大学进行学术访问与合作。共接收/发表论文 50 余篇，其中包括
TIP,TKDE,TNNLS,TSMCB,PR 等国际期刊与 ICML, NIPS, CVPR, ICCV, ECCV, AAAI,
ACM MM 等国际会议论文。担任 TPAMI,TIP,TNNLS 等期刊审稿人,ICCV,NIPS,
ICML,ACM MM 等会议程序委员会委员。曾获陕西省青年科技奖，陕西省优秀博士
论文奖，入选首批西安交通大学青年拔尖人才计划。CCF 会员, ACM 会员, IEEE 会
员。目前主要聚焦于机器学习、数据挖掘，计算机视觉与多媒体分析等方面的研
究。
报告三：
报告题目：
Multimodal Learning: From Image and Sentence Matching to Image Question
Answering
特邀讲者：马林
报告摘要：
Deep neural networks have been successfully applied on single modalities,
such as text, image, and audio. Nowadays, multiple modalities always
accompany with each other, such as image and language, video and audio.
Deep learning has been now studied for multiple modalities to study the
association and correlation properties between them. In this talk, we
discuss the multimodal learning, specifically the multimodalconvolutional neural network (m-CNN), for image and sentence matching and
image question answering. m-CNN provides an end-to-end framework with
convolutional architectures to exploit image representation, word
composition for sentence representation, and the matching relations
between the two modalities. As such, the matching properties between image
and sentence have been captured for the association between them. For
bidirectional image and sentence retrieval, m-CNN achieves the
state-of-the-art performances on Flickr8K, Flickr30K, and Microsoft COCO
databases. For image question answering, m-CNN can fuse the multimodal
input of the image and question to obtain the joint representation for
the classification in the space of candidate answer words. The efficacy
of m-CNN on DAQUAR and COCO-QA datasets is demonstrated, two datasets
recently created for the image question answering (QA), with performance
substantially outperforming the state-of-the-arts.
个人简介：
Lin Ma is now a Researcher at Huawei Noah's Ark Lab, Hong Kong. His current
research interests lie in the areas of deep learning and multimodal
learning, specifically for image and language. His Ph.D. research topics
are image/video processing and quality tuning. He received his Ph.D.
degree in Department of Electronic Engineering at the Chinese University
of Hong Kong (CUHK) in 2013. He received the B. E., and M. E. degrees from
Harbin Institute of Technology, Harbin, China, in 2006 and 2008,
respectively, both in computer science. He got the best paper award in
Pacific-Rim Conference on Multimedia (PCM) 2008. He was awarded the
Microsoft Research Asia fellowship in 2011. He was a finalist to HKIS young
scientist award in engineering science in 2012.
报告四：
报告题目：深度学习及其在人脸识别上的应用
特邀讲者：山世光
报告摘要：
深度学习在语音、图像识别领域的成功已迅速影响了计算机视觉的各个研究方
向。人脸分析和识别领域亦不例外。尽管简单照搬深度学习在其他视觉问题上的
已有成功模型即已初显深度学习对于人脸判别特征提取的优异效果，但简单应用
并不能解决所有问题。本报告将概述了近期我们在基于深度学习的人脸分析与识
别方面的相关实践，包括面向人脸识别和表情识别的卷积神经网络特征学习，由
粗到精的多阶段深度非线性人脸形状提取，以及姿态鲁棒的人脸特征渐进深度学
习等。最后，总结了较小规模人脸数据条件下应用深度学习模型的有关经验。个人简介：
山世光，中国科学院计算技术研究所研究员、博士生导师，中科院智能信息处理
重点实验室常务副主任。主要从事计算机视觉、模式识别、机器学习等相关研究
工作。已在国际/国内期刊、国际会议上发表/录用学术论文 200 余篇，其中 CCF
A 类国际会议和期刊论文 40 余篇。论文曾获 CCF A 类国际会议 CVPR2008 大会颁
发的 Best Student Poster Award Runner-up 奖。所发表论文被国内外同行引用
7000 余次（Google Scholar），领导课题组完成的人脸识别系统多次获得国内外
人脸识别竞赛第一名。应邀担任 CCF-A 类国际刊物 IEEE Trans. on Image
Processing 以及 Neurocomputing ，EURASIP Journal of Image and Video
Processing, Frontier of Computer Science, 《计算机研究与发展》等期刊的
编委(Associate Editor)，应邀担任过 ICCV2011, ICPR2012, ACCV2012, FG2013,
ICASSP2014 和 ICPR2014 等相关领域重要国际会议的 Area Chair（领域主席）。
所完成的人脸识别研究成果 2005 年度国家科技进步二等奖（第 3 完成人）。他是
2012 年度国家自然科学基金委员会首届“优青”获得者。
报告五：
报告题目: Saliency Object Detection: From Contrast-based methods to
Supervised-based Methods
特邀讲者：卢湖川
报告摘要:
Saliency object detection, which aims to identify the most important and
conspicuous object regions in an image, has received increasingly more
interest in recent years. Salient object detection methods can be
categorized as bottom-up stimuli-driven and top-down task-driven
approaches. Bottom-up methods are usually based on low-level visual
information and are more effective in detecting fine details. In contrast,
top-down saliency models are able to detect objects of certain sizes and
categories based on more representative features from training samples.
In this talk, I would like to introduce Bayesian saliency、
Manifold-ranking saliency and Markov-chain saliency which are all
Contrast-based methods from the Bottom-up perspective and Bootstrap
Learning saliency, Deep Learning saliency which are all Supervised-based
methods from the Top-down perspective.
个人简介：
Huchuan Lu received both the B. Eng. and M. Eng. degrees in Electronic
Engineering from the Department of Electronic Engineering, Dalian
University of Technology(DUT), China, in 1995 and 1998 respectively, and
the PhD degree in System Engineering, Dalian University ofTechnology(DUT), China, in 2008. He joined School of Electronic and
Information Engineering as faculty member at DUT in 1998, and He has been
a Vice Dean and a Professor since 2009 and 2012 respectively, with the
School of Information and Communication Engineering, DUT, China.
His major research interests include computer vision and pattern
recognition. He has obtained several honors and awards such as the Most
Remembered Poster (ICCV2011) , Best Student Paper Award Finalist
( ICIP2012) and Best Paper (IET Image Processing 2014). He is an
associate editor of IEEE Transactions on Systems, Man and Cybernetics –
Part B.
报告六：
报告题目：Markerless Motion Capture and 4D Reconstruction
特邀讲者：刘烨斌
报告摘要：
三维动态对象的无标记运动捕捉及时空 4D 重建仍是计算机视觉及计算机图形学
的热点和难题。本报告讲介绍基于多摄像机或深度传感设备的动态对象三维重建
及无标记运动捕捉，包括：动态对象运动捕捉和 4D 重建的基本方法、多动态对
象 4D 重建技术、基于多 Kinect 及单 Kinect 的动态对象 4D 重建。报告最后将介
绍未来无标记运动捕捉及 4D 重建技术的技术发展。
个人简介：
刘烨斌，清华大学自动化系副研究员。2002 年获北京邮电大学自动化学士学位，
2009 年获得清华大学自动化系博士学位；2009 在清华大学自动化系从事博士后
研究工作，2011 年出站后留校；2010 年在德国马普计算所进行访问研究。研究
兴趣包括基于图像的三维重建、运动捕捉、立体视频、计算摄像、计算光学等。
获得 2008 年国家技术发明二等奖及 2012 年国家技术发明一等奖（皆排名第三），
2013 年清华大学学术新人奖。
参加人员：IT 领域专业人士、研究生、媒体、其他有兴趣者
报名方式：杨成伟 Tel:131-7667-2101 Email: yangchengwei2006@163.com
许信顺 Tel:139-6900-3221 Email:xuxinshun@sdu.edu.cn
报告会地点：山东省济南市高新区舜华路 1500 号山东大学软件园校区办公楼
