加载中…
正文 字体大小:

【16-40期VALSEWebinar活动】

(2016-12-07 17:03:49)
标签:

it

【16-40期VALSEWebinar活动】
报告嘉宾1:施柏鑫(AIST)
报告时间:2016年12月14日(星期三)晚20:00(北京时间)
报告题目:面向非朗伯和非标定光度立体视觉的标准评测数据集
主持人:徐轶超(香港城市大学)

报告摘要:
光度立体视觉技术通过分析变化光照的图像序列来估计每一个像素的法线方向,是一种可以得到高精度几何信息的三维重建方法。传统的方法在物体表面的反射模型上有过于理想的假设,并需要事先对光源方向进行标定。近些年提出的光度立体视觉算法多关注非朗伯反射的复杂材质和非标定的技术,从而推进这一技术的实用化。由于数据拍摄的繁琐和标定要求的严格,面向非朗伯和非标定光度立体视觉的标准评测数据集一直是该领域的研究空白。本次报告首先回顾近些年非朗伯和非标定光度立体视觉的代表算法,然后介绍最新发布的标准评测数据集,并利用该数据集对近些年的主流方法进行统一量化的对比分析。

参考文献:
[1] Boxin Shi, Zhe Wu, Zhipeng Mo, DinglongDuan, Sai-Kit Yeung, and Ping Tan, “A benchmarkdataset and evaluation for non-Lambertian and uncalibrated photometric stereo”, In Proc.IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016
[2] Boxin Shi, Ping Tan, Yasuyuki Matsushita, and Katsushi Ikeuchi, “Bi-polynomial modeling of low-frequency reflectances”, In IEEE Transactions on Pattern Analysis and Machine Intelligence(TPAMI), Volume 36, Number 6, Pages 1078-1091, 2014.
[3] Boxin Shi, Ping Tan, Yasuyuki Matsushita, and Katsushi Ikeuchi, “Elevation angle fromreflectance monotonicity: Photometric stereo for general isotropic reflectances”, In Proc. European Conference on Computer Vision (ECCV), 2012.
[4] Boxin Shi, Ping Tan, Yasuyuki Matsushita, and Katsushi Ikeuchi, “A biquadratic reflectancemodel for radiometric image analysis”, In Proc. IEEE Conference on Computer Vision andPattern Recognition (CVPR), 2012.
[5] Boxin Shi, Yasuyuki Matsushita, Yichen Wei, Chao Xu, and Ping Tan,“Self-calibrating photometric stereo”, In Proc. IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2010.
[6] LunWu, Arvind Ganesh, Boxin Shi, Yasuyuki Matsushita, YongtianWang, and Yi Ma,“Robustphotometric stereo via low-rank matrix completion and recovery”, In Proc. Asian Conferenceon Computer Vision (ACCV), 2010.

报告人简介:
施柏鑫,2013年从日本东京大学取得博士学位(师从KatsushiIkeuchi教授)。2014年在麻省理工学院媒体实验室从事博士后研究(合作导师RameshRaskar副教授)。2015年分别在新加坡科技设计大学和南洋理工大学(合作导师Alex Kot教授)做博士后。2016年加入日本国立产业技术综合研究所(AIST)人工智能研究中心任研究员。曾在微软亚洲研究院(合作研究员Yasuyuki Matsushita教授)和新加坡国立大学(合作导师谭平副教授)实习。研究兴趣为计算摄像学和基于物理的计算机视觉。曾获国际计算摄像学大会(ICCP15)第二最佳论文。担任MVA17领域主席,CVPR、ICCV等会议程序委员会委员,和TPAMI、IJCV等期刊审稿人。

【16-40期VALSEWebinar活动】
报告嘉宾2:梁小丹(CMU)
报告时间:2016年12月14日(星期三)晚21:00(北京时间)
报告题目:Deep Variation-structured Reinforcement Learning for Visual Relationship and Attribute Detection
主持人:左旺孟(哈尔滨工业大学)

报告摘要:
Despite progress in visual perception tasks such as image classification and detection, computers still struggle to understand the interdependency of objects in the scene as a whole, e.g., relations between objects or their attributes. Existing methods often ignore global context cues capturing the interactions among different object instances, and can only recognize a handful of types by exhaustively training individual detectors for all possible relationships. To capture such global interdependency, we propose a deep Variation-structured Reinforcement Learning (VRL) framework to sequentially discover object relationships and attributes in the whole image. First, a directed semantic action graph is built using language priors to provide a richand compact representation of semantic correlations between object categories, predicates, and attributes. Next,we use a variation-structured traversal over the action graph to construct a small, adaptive action set for each step based on the current state and historical actions. In particular, an ambiguity-aware object mining scheme is used to resolve semantic ambiguity among object categories that the object detector fails to distinguish. We then make sequential predictions using a deep RL framework, incorporating global context cues and semantic embedding of previously extracted phrases in the state vector. Our experiments on the Visual Relationship Detection (VRD) dataset and the large-scale Visual Genome dataset validate the superiority of VRL, which can achieve significantly better detection results on datasets involving thousands of relationship and attribute types.

报告人简介:
Xiaodan Liang is currently a postdoctoral research fellow at the Machine Learning Department, Carnegie Mellon University, working with Prof. Eric P. Xing.She obtained my Ph.D. degree in the School of Data and Computer Science at Sun Yat-sen University in June 2016, advised by Prof. Liang Lin. She was a visiting scholar from March, 2014 to March, 2016 in the Department of EECS of the National University of Singapore, working with Prof. Shuicheng Yan. She have closely collaborated with Dr. Xiaohui Shen in Adobe Research and Dr. Jianchao Yang in Snapchat Research from 2014 to 2016. 

特别鸣谢本次Webinar主要组织者:
VOOC责任委员:邓伟洪(北京邮电大学)
VODB协调理事:林倞(中山大学),郑伟诗(中山大学)


活动参与方式:
1、VALSE Webinar活动全部网上依托VALSE QQ群的“群视频”功能在线进行,活动时讲者会上传PPT或共享屏幕,听众可以看到Slides,听到讲者的语音,并通过文字或语音与讲者交互;
2、为参加活动,需加入VALSE QQ群,目前A、B、C、D群已满,除讲者等嘉宾外,只能申请加入VALSE E群,群号:279398311 。申请加入时需验证姓名、单位和身份,缺一不可。入群后,请实名,姓名身份单位。身份:学校及科研单位人员T;企业研发I;博士D;硕士M
3、为参加活动,请下载安装Windows QQ最新版,群视频不支持非Windows的系统,如Mac,Linux等,手机QQ可以听语音,但不能看视频slides;
4、在活动开始前10分钟左右,主持人会开启群视频,并发送邀请各群群友加入的链接,参加者直接点击进入即可;
5、活动过程中,请勿送花、棒棒糖等道具,也不要说无关话语,以免影响活动正常进行;
6、活动过程中,如出现听不到或看不到视频等问题,建议退出再重新进入,一般都能解决问题;
7、建议务必在速度较快的网络上参加活动,优先采用有线网络连接。

0

阅读 评论 收藏 禁止转载 喜欢 打印举报
已投稿到:
  • 评论加载中,请稍候...
发评论

       

    发评论

    以上网友发言只代表其个人观点,不代表新浪网的观点或立场。

      

    新浪BLOG意见反馈留言板 不良信息反馈 电话:4006900000 提示音后按1键(按当地市话标准计费) 欢迎批评指正

    新浪简介 | About Sina | 广告服务 | 联系我们 | 招聘信息 | 网站律师 | SINA English | 会员注册 | 产品答疑

    新浪公司 版权所有