好文作者面授招-20150128

【15-04期VALSE Webinar活动】

报告嘉宾1张利军(南京大学)
主持人董伟生(西安电子科技大学)
报告时间:2015年1月28日20:30(北京时间)
报告题目:Efficient Algorithms for Robust One-bit Compressive Sensing [Slides]
文章信息:Lijun Zhang, Jinfeng Yi, and Rong Jin. Efficient Algorithms for Robust One-bit Compressive Sensing, Proceedings of the 31st International Conference on Machine Learning (ICML), 2014.[PDFSupplementary]
报告摘要:In this paper, we study the vector recovery problem from noisy one-bit measurements, and develop two novel algorithms with formal theoretical guarantees. First, we propose a passive algorithm, which is very efficient in the sense it only needs to solve a convex optimization problem that has a closed-form solution. Despite the apparent simplicity, our theoretical analysis reveals that the proposed algorithm can recover both the exactly sparse and the approximately sparse vectors. In particular, for a sparse vector with $s$ nonzero elements, the sample complexity is $O(s \log n/\epsilon^2)$, where $n$ is the dimensionality and $\epsilon$ is the recovery error. This result improves significantly over the previously best known sample complexity in the noisy setting, which is $O(s \log n/\epsilon^4)$. Second, in the case that the noise model is known, we develop an adaptive algorithm based on the principle of active learning. The key idea is to solicit the sign information only when it cannot be inferred from the current estimator. Compared with the passive algorithm, the adaptive one has a lower sample complexity if a high-precision solution is desired.
报告人简介:张利军是南京大学计算机科学与技术系副教授。分别于2007年6月和2012年6月在浙江大学软件工程系和计算机科学与技术系获工学学士和工学博士学位;分别于2011年6月至12月、2012年8月至2014年4月,以访问学生、博士后身份在美国密歇根州立大学计算机科学与工程系访问研究。主要研究方向为大规模机器学习及优化,共在国际学术会议和期刊上发表论文30余篇,包括领域顶级会议和期刊ICML、NIPS、COLT、AAAI、ACM MM、AISTATS、TPAMI、TIP、TKDE。曾担任TPAMI、TKDE、NIPS等国际期刊和会议审稿人、曾担任AAAI、IJCAI、ACM MM等国际会议程序委员会委员。曾获浙江大学“竺可桢奖学金”、南京大学“登峰人才支持计划”、第26届AAAI人工智能国际会议“最佳论文”等荣誉。具体请详见http://cs.nju.edu.cn/zlj

报告嘉宾2张开华(南京信息工程大学)
主持人孟德宇(西安交通大学)
报告时间:2015年1月28日晚21:10(北京时间)
报告题目:Fast Compressive Tracking [Slides]
文章信息:Kaihua Zhang, Lei Zhang, and Ming-Hsuan Yang, Fast Compressive Tracking, IEEE Transactions on Pattern Analysis and Machine Intelligence,2014. [PDF, Codes]
报告摘要:It is a challenging task to develop effective and efficient appearance models for robust object tracking due to factors such as pose variation, illumination change, occlusion, and motion blur. Existing online tracking algorithms often update models with samples from observations in recent frames. Despite much success has been demonstrated, numerous issues remain to be addressed. First, while these adaptive appearance models are data-dependent, there does not exist sufficient amount of data for online algorithms to learn at the outset. Second, online tracking algorithms often encounter the drift problems. As a result of self-taught learning, misaligned samples are likely to be added and degrade the appearance models. In this paper, we propose a simple yet effective and efficient tracking algorithm with an appearance model based on features extracted from a multiscale image feature space with data-independent basis. The proposed appearance model employs non-adaptive random projections that preserve the structure of the image feature space of objects. A very sparse measurement matrix is constructed to efficiently extract the features for the appearance model. We compress sample images of the foreground target and the background using the same sparse measurement matrix. The tracking task is formulated as a binary classification via a naive Bayes classifier with online update in the compressed domain. A coarse-to-fine search strategy is adopted to further reduce the computational complexity in the detection procedure. The proposed compressive tracking algorithm runs in real-time and performs favorably against state-of-the-art methods on challenging sequences in terms of efficiency, accuracy and robustness.
报告人简介:张开华,男,南京信息工程大学教授。2006年本科毕业于中国海洋大学电子工程系,2009年硕士毕业于中国科学技术大学电子工程与信息科学系,2013年博士毕业于香港理工大学计算机系,导师为张磊教授。其中,2009年8月至2010年8月在香港理工大学计算机系从事研究工作,任研究助理。2013年12起在南京信息工程大学信息与控制学院任教。目前主要研究方向为基于水平集方法的图像分割与视觉目标跟踪。在国内外知名学术期刊和会议上发表论文20余篇,包含:IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), IEEE Trans. on Image Processing (TIP), IEEE trans. on Circuit System and Video Technology (TCSVT), IEEE Trans. on Geoscience and Remote Sensing (TGRS),Pattern Recognition (PR),Information Fusion (IF),Image and Vision Computing (IVC),ECCV等. 据Google Scholar统计,论文近5年来被引用1100余次,其中单篇他引超过200次论文3篇, 4篇论文被ESI评为近10年来高被引SCI论文。具体请详见http://web2.nuist.edu.cn/jszy/Professor.aspx?id=1991

(Visited 472 times, 1 visits today)