设为首页收藏本站

VALSE

VALSE 首页 活动通知 专题侠客群论剑 查看内容

20150401-10 陈轲:Age and Crowd Density Estimation

2015-3-30 18:01| 发布者: 贾伟中科院合肥| 查看: 4050| 评论: 0

摘要: 专题侠客群论剑-20150401【15-10期VALSE Webinar活动】报告嘉宾2:陈轲(坦佩雷理工大学)主持人:张兆翔(北航)报告时间:2015年4月1日晚20:00(北京时间)报告题目: Cumulative Attribute Space for Age and Cro ...

专题侠客群论剑-20150401

【15-10期VALSE Webinar活动】

报告嘉宾2陈轲(坦佩雷理工大学)

主持人:张兆翔北航

报告时间:2015年4月1日晚20:00(北京时间)
报告题目: Cumulative Attribute Space for Age and Crowd Density Estimation http://valser.org/webinar/slide/slides/20150401/KeChen.pptx

文章信息
[1]  K Chen, S Gong, T Xiang, CC Loy, Cumulative Attribute Space for Age and Crowd Density Estimation, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 2467-2474, 2013.
报告摘要:A number of computer vision problems such as human age estimation, crowd density estimation and body/face pose (view angle) estimation can be formulated as a regression problem by learning a mapping function between a high dimensional vector-formed feature input and a scalar-valued output. Such a learning problem is made difficult due to sparse and imbalanced training data and large feature variations caused by both uncertain viewing conditions and intrinsic ambiguities between observable visual features and the scalar values to be estimated. Encouraged by the recent success in using attributes for solving classification problems with sparse training data, this paper introduces a novel cumulative attribute concept for learning a regression model when only sparse and imbalanced data are available. More precisely, low-level visual features extracted from sparse and imbalanced image samples are mapped onto a cumulative attribute space where each dimension has clearly defined semantic interpretation (a label) that captures how the scalar output value (e.g. age, people count) changes continuously and cumulatively. Extensive experiments show that our cumulative attribute framework gains notable advantage on accuracy for both age estimation and crowd counting when compared against conventional regression models, especially when the labelled training data is sparse with imbalanced sampling.
报告人简介:陈轲博士,目前在坦佩雷理工大学从事博士后工作,2013年毕业于伦敦大学玛丽皇后学院获得哲学博士学位 。主要研究方向是:计算机视觉,模式识别,神经动力学及其在机器人中的应用。共在国际学术期刊和国际会议发表论文40余篇。

最新评论

Archiver|手机版|小黑屋|Vision And Learning SEminar    

GMT+8, 2020-8-3 23:33 , Processed in 0.032387 second(s), 20 queries .

Powered by Discuz! X3.2

© 2001-2013 Comsenz Inc.

返回顶部