好文作者面授招–20151008

【15-31期VALSE Webinar活动】

报告嘉宾金鑫(北京电子科技学院 )
报告时间:2015年10月8日(星期四)晚20:00(北京时间)
报告题目:Artistic Illumination Assessment & Manipulation for Portraits [Slides]
主持人王瑞平(中科院计算所)
报告摘要: Good lighting is the key to good portraits. Professional photographers and Artists can assess portrait lighting and produce beautiful illumination effects for portraits. This talk is about three questions. Q1: Can computers assess portrait lighting automatically? Q2: Can we transfer good illumination to a normal lighting face? Q3: How about artistic illumination from Masterpieces? We have proposed a method to learn templates for artistic portrait lighting analysis and methods for face illumination manipulation using a single reference image by adaptive layer decomposition. Plenty of synthesis results will be shown in the presentation. (This work was done when the reporter in Beihang University)
参考文献
[1] Xiaowu Chen, Xin Jin, Hongyu Wu and Jinping Zhao. Learning Templates for Artistic Portrait Lighting Analysis. IEEE Transactions on Image Processing (TIP),Vol. 24, No. 2, pp. 608-618, Feb. 2015.
[2] Xiaowu Chen, Hongyu Wu, Xin Jin* and Jinping Zhao. Face Illumination Manipulation using a Single Reference Image by Adaptive Layer Decomposition. IEEE Transactions on Image Processing (TIP),Vol. 22, No. 11, pp. 4249 – 4259, Nov. 2013.
[3] Xiaowu Chen, Mengmeing Chen, Xin Jin* and Qinping Zhao. Face Illumination Transfer through Edge-preserving Filters. Computer Vision and Pattern Recognition (CVPR), Colorado Springs, June 20-25, pp.281-287, 2011.
[4] Xiaowu Chen, Xin Jin*, Jinping Zhao and Hongyu Wu. Artistic Illumination Transfer for Portraits. Eurographics Symposium on Rendering (EGSR), Paris France June 27-29, 2012. Published in Computer Graphics Forum (CGF), Vol. 31, No. 4, pp.1425-1434, 2012.
[5] Xin Jin, Mingtian Zhao, Xiaowu Chen, Jinping Zhao, and Song-Chun Zhu. Learning Artistic Lighting Template from Portrait Photographs. European Conference on Computer Vision (ECCV), Heraklion, Crete, Greece, September 5-11, pp.101-114, 2010.
报告人简介:金鑫,博士,2006年~2013年就读于北京航空航天大学,计算机学院计算机应用技术专业,虚拟现实技术与系统国家重点实验室,师从赵沁平院士与陈小武教授,获工学博士学位。现于北京电子科技学院计算机系、中共中央办公厅信息安全重点实验室、北京电子科技学院可视计算与安全研究组从事科研与教学工作,主要从事计算机视觉、可视媒体安全、混合现实等方面的研究与开发。已发表或录用学术论文近30篇,根据Google Scholar的统计,累计被引用近80次,其中包含TIP、CVPR、CGF、ECCV等,获国家发明专利授权7项。担任IEEE TIP、Eurographics、Pacific Graphics等期刊或会议的审稿人,作为项目负责人主持国家自然科学基金项目、国家档案局科技计划等项目,作为主要技术人员负责国家图像及音视频类电子文件标准制定。

报告嘉宾马述高(波士顿大学)
报告时间:2015年10月8日(星期四)晚20:45(北京时间)
报告题目:Space-Time Tree Ensemble for Action Recognition [Slides]
主持人蓝振忠(卡耐基梅隆大学)
报告摘要:Human actions are, inherently, structured patterns of body movements. We explore ensembles of hierarchical spatio-temporal trees, discovered directly from training data, to model these structures for action recognition. The hierarchical spatio-temporal trees provide a robust midlevel representation for actions. However, discovery of frequent and discriminative tree structures is challenging due to the exponential search space, particularly if one allows partial matching. We address this by first building a concise action vocabulary via discriminative clustering. Using the action vocabulary we then utilize tree mining with subsequent tree clustering and ranking to select a compact set of highly discriminative tree patterns. We show that these tree patterns, alone, or in combination with shorter patterns (action words and pairwise patterns) achieve state-of-the-art performance on two challenging datasets: UCF Sports and HighFive. Moreover, trees learned on HighFive are used in recognizing two action classes in a different dataset, Hollywood3D, demonstrating the potential for cross-dataset generality of the trees our approach discovers.
参考文献:Ma, Shugao, Leonid Sigal, and Stan Sclaroff. “Space-time tree ensemble for action recognition.” Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR). 2015.
报告人简介:马述高现为波士顿大学计算机系博士生,波士顿大学图像与视频计算(Image and Video Computing)实验室组员,在教授Stan Sclaroff指导下研究计算机视觉和机器学习,其主要研究课题为视频中的人类行为自动识别。他在顶级计算机视觉会议上发表多篇文章,包括CVPR,ICCV,ECCV和BMVC,并在多家公司如迪斯尼研究院,谷歌,微软和思爱普从事过计算机视觉及人工智能项目的实习。 马述高本科毕业于复旦大学,并从中科院取得硕士学位。

(Visited 388 times, 1 visits today)