|
Murdoch University的Hamid Laga教授和王冠博士生于2018年1月31日VALSE Webinar 成功举办.
Hamid Laga: Dr.Hamid received the M.Sc (2003) and PhD (2006) degrees in Computer Science from Tokyo Institute of Technology in the area of 3D shape analysis and retrieval. Prior to Joining Murdoch University, He worked as a senior research fellow at the Phenomics and Bioinformatics (PBRC) of the University of South Australia. He has also served as the deputy director of the PBRC. Prior to that he was Associate Professor at the Institut Telecom, Telecom Lille1 in France (2010-2012), Assistant Professor at Tokyo Institute of Technology (2006-2010), and as a fellow of the Japan Society for the Promotion of Science (JSPS) at Nara Institute of Science and Technology (2006). His research interests span various fields of computer vision, computer graphics, and image-based cereal plant phenotyping. 个人主页： http://profiles.murdoch.edu.au/myprofile/hamid-laga/
Guan Wang: Guan Wang is a third year Ph.D. student at Tongji University, majoring in software engineering. He is currently a visiting Ph.D student at Murdoch University, Australia, under the supervision of Associate Professor Hamid Laga. He is working on the project of tree modelling using statistical models. He has received Ph.D National Scholarship in 2015 and 2017 respectively.
Hamid教授和王冠博士生的Webinar的题目为：Statistical Modelling in Tree-Shape Space.
报告中提出了：An algorithm is proposed for generating novel 3D tree model variations from existing ones via geometric and structural blending. The approach is to treat botanical trees as elements of a tree-shape space equipped with a proper metric that quantifies geometric and structural deformations. Geodesics, or shortest paths under the metric, between two points in the tree-shape space correspond to optimal deformations that align one tree onto another, including the possibility of growing, adding or removing branches and parts. Central to the approach is a mechanism for computing correspondences between trees that have different structures and different number of branches. The ability to compute geodesics and their lengths enables us to compute continuous blending between botanical trees, which in turn facilitates statistical analysis such as the computation of averages of tree structures. We show a variety of 3D tree models generated with the proposed approach from 3D trees exhibiting complex geometric and structural differences. We also demonstrate the application of the framework in reflection symmetry analysis and symmetrization of botanical trees.
问答部分：
问题1：树木映射到高维空间是怎么映射的，能具体介绍一下这个过程吗？ 回答：对于每个树木模型，首先提取骨架信息，骨架上每个点用（x, y, z, r）表示，然后将每条边的信息依次写入一个向量中，这个高维向量对应高维空间中的一个点，从而完成了高维映射的过程。
问题2：什么是高维向量？ 回答：这里的高维向量指的是一个1*n的矩阵，三维空间中的点是1*3的向量，当n>>3时，就指的高维向量。
问题3：请问你们使用的特征维度有多大？ 回答：这里准确的说我们没用特征，每个（树木）模型会对应一个高维的向量，不同树木对应的高维向量的维度是不一样的。
问题4：如果用深度学习来做的话，将树木用深度模型提取特征，然后进行插值，再映射回树空间效果会不会更好，你有做过这方面的工作么？
回答：我们之前没有做过相关方面的工作，不过我们认为基于深度模型进行树木模型的插值这个思路挺好，我们以后工作中会考虑，谢谢您的建议。
问题5：如果用深度学习来做的话，将树木用深度模型提取特征，然后进行插值，再映射回树空间效果会不会更好，你有做过这方面的工作么？ 回答：同问题4。
录像视频在线观看地址： http://www.iqiyi.com/u/2289191062
特别鸣谢本次Webinar主要组织者： VOOC责任委员：谢宁（电子科技大学） VODB协调理事：王琦（西北工业大学）
活动参与方式： 1、VALSE Webinar活动依托在线直播平台进行，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，并通过聊天功能与讲者交互； 2、为参加活动，请关注VALSE微信公众号：valse_wechat 或加入VALSE QQ群（目前A、B、C、D、E、F群已满，除讲者等嘉宾外，只能申请加入VALSE G群，群号：669280237），直播链接会在报告当天（每周三）在VALSE微信公众号和VALSE QQ群发布； *注：申请加入VALSE QQ群时需验证姓名、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、在活动开始前10分钟左右，讲者会开启直播，听众点击直播链接即可参加活动，支持安装Windows系统的电脑、MAC电脑、手机等设备； 4、活动过程中，请勿送花、打赏等，也不要说无关话语，以免影响活动正常进行； 5、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； 6、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； 7、VALSE微信公众号会在每周一推送上一周Webinar报告的总结及视频（经讲者允许后），每周四发布下一周Webinar报告的通知。
| 
发表于 2018-3-27 11:15:07