【15-14期VALSE Webinar活动】 报告嘉宾1：樊鑫（大连理工大学）
主持人：郑伟诗（中山大学）
报告题目：Characteristic number regression for fiducial facial feature extraction http://valser.org/webinar/slide/slides/20150513/Fudicial_extraction_Invariant_XinFan.pdf 文章信息：
[1] Xin Fan*, Hao Wang, Zhongxuan Luo, Yuntao Li, Wenyu Hu, and Daiyun Luo, "Fiducial facial point extraction using a novel projective invariant", IEEE Transactions on Image Processing, 24(3):1164-1177, 2015.
[2] Yuntao Li, Xin Fan*, Risheng Liu, Yuyao Feng, Zhongxuan Luo, and Zezhou Li, “Characteristic number regression for facial feature extraction”, IEEE International Conference on Multimedia and Expo (ICME), 2015. (Oral, Best student paper candidate)
报告时间：2015年5月13日晚20:00（北京时间）
报告摘要: Facial feature extraction plays an important role in many multimedia and computer vision applications. Recent regression methods for extraction lack the explicit shape constraints for faces, and require a large number of facial images covering great appearance variations. We introduces a novel projective invariant, named characteristic number (CN), to explicitly characterize the intrinsic geometries of facial points shared by human faces, which is inherently invariant to pose changes. By further developing a shape-to-gradient regression framework, we provide a robust and efficient feature extractor for facial images in the wild. The computation of our model can be successfully addressed by learning the descent directions using point-CN pairs without the need of large collections for appearance training. We validate our approach on challenging benchmark data sets compared with state-of-the-art approaches.
报告人简介: 樊鑫，分别于1998年和2005年于西安交通大学通信与信息工程专业获工学学士和博士学位。从2006年5月至2009年6月分别在美国俄克拉荷马州立大学和得州大学西南医学研究中心进行博士后研究，2009年11月起在大连理工大学软件学院任副教授，现任数字媒体系主任，辽宁省泛在网络与服务软件重点实验室副主任。入选2011年度教育部“新世纪优秀人才支持计划”，辽宁省“百千万人才工程”千人层次，获得省部级科技进步奖1项、申请国家发明专利12项。一直致力于计算机视觉及医学影像处理的研究，已发表论文五十余篇，其中包括Nature旗下期刊Neuropsychopharmacology（SCI IF: 8.678，封面文章）、国际重要期刊IEEE Trans. on Image Processing, Pattern Recognition和知名会议ICCV、CVPR等。 | 