报告1： - 题目：Recent Progress in Discriminative Point Cloud Parsing http://valser.org/webinar/slide/slides/20150114/Point+Cloud+Parsing_JRR.ppt
- 主讲人：纪荣嵘 厦门大学教授
- 时间：2015年01月14日 20:30
- 相关论文：Yan Wang, Rongrong Ji, and Shih-Fu Chang. Label Propagation from ImageNet to 3D Point Clouds. IEEE International Conference on Computer Vision and Patten Recognition (CVPR).
- 主持人：孟德宇
- 摘要：In this talk, I will review some of our recent progress in 3D scene parsing. More specially, I will focus on the issue of semantic inference and segmentation of 3D point cloud data. This problem differs significantly from the traditional research on image-based semantic segmentation in three-fold, i.e., (1) the lack of sufficient training instances manually or collaboratively collected (such as LabelMe or ImageNet-Seg), (2) the lack of robust nearest neighborhood search technique for finding similar superverxels in the feature space, and (3) the lack of efficient and accurate inference model. In this talk, we will analyze and discuss some preliminary results on our solution to the above three challenges.
- 报告人简介：纪荣嵘博士是厦门大学信息学院智能科学系教授，智能多媒体信息处理实验室主任。1983年1月生，2010年至2013工作于美国哥伦比亚大学电子工程系数字视频与多媒体实验室，担任博士后研究员，（导师：Shih-Fu Chang教授，哥伦比亚大学工学院副院长），研究方向为移动视觉搜索与社交媒体舆情分析； 2010年工作于北京大学视频编码国家工程实验室，担任研究助理（导师：高文院士），致力于MPEGCDVS（CompactDescriptorforVisualSearch）标准工作; 2007年至2008年工作于微软亚洲研究院，担任访问学生（导师：谢幸主任研究员），开发Photo2Search移动视觉搜索系统； 2011年获得哈尔滨工业大学博士学位（计算机科学与技术专业），2007年获哈尔滨工业大学硕士学位（计算机科学与技术专业），2005年获得哈尔滨工程大学本科学位（计算机科学与技术专业）。目前为IEEE高级会员、中国计算机学会多媒体技术专业委员会委员、中国计算机学会计算机视觉专业组委员、中国计算机学会青年工作委员会厦门分论坛副主席、福建省人工智能协会常务理事。
报告2： - 题目：Sparse Representation Based Image Interpolation with Nonlocal Autoregressive Modeling http://valser.org/webinar/slide/slides/20150114/VALSE_0114_DWS.pptx
- 主讲人：董伟生 西安电子科技大学副教授
- 时间： 2015年1月14日 21:10
- 主持人：彭玺
- 摘要：Sparse representation has proven to be a promising approach to image super-resolution, where the low resolution (LR) image is usually modeled as the down-sampled version of its high resolution (HR) counterpart after blurring. When the blurring kernel is the Dirac delta function, i.e., the LR image is directly down-sampled from its HR counterpart without blurring, the super-resolution problem becomes an image interpolation problem. In such case, however, the conventional sparse representation models (SRM) become less effective because the data fidelity term will fail to constrain the image local structures. In natural images, fortunately, the many nonlocal similar patches to a given patch could provide nonlocal constraint to the local structure. In this paper we incorporate the image nonlocal self-similarity into SRM for image interpolation. More specifically, a nonlocal autoregressive model (NARM) is proposed and taken as the data fidelity term in SRM. We show that the NARM induced sampling matrix is less coherent with the representation dictionary, and consequently makes SRM more effective for image interpolation. Our extensive experimental results demonstrated that the proposed NARM based image interpolation method can effectively reconstruct the edge structures and suppress the jaggy/ringing artifacts, achieving the best image interpolation results so far in term of PSNR as well as perceptual quality metrics such as SSIM and FSIM.
- 相关论文：W. Dong, L. Zhang, R. Lukac, and G. Shi, "Sparse Representation Based Image Interpolation with Nonlocal Autoregressive Modeling", IEEE Trans. on Image Processing, vol. 22, no. 4, Apr. 2013.
- 报告人简介：董伟生，男，西安电子科技大学副教授，曾获陕西省青年科技新星称号。2004年本科毕业于华中科技大学，2010年博士毕业于西安电子科技大学，2009.1-2010.6在香港理工大学进行合作研究。主要研究方向为图像稀疏和低秩表示，图像处理逆问题等。在包括IEEE Trans. Image Processing、CVPR等图像信号处理领域的权威国际期刊和会议上发表论文30余篇，论文被引用980余次。曾获IEEE VCIP国际会议最佳论文奖，陕西省科学技术一等奖。具体详见个人主页：http://see.xidian.edu.cn/faculty/wsdong.
|
