学术看板
科研动态
学院基金
成果展示
科研团队
相关政策
科研机构
学术看板
学术报告—— Online Visual Tracking via Deep Regression Networks
时间: 2017-12-12 10:25  来源: 计算机学院

 

报告题目:Online Visual Tracking via Deep Regression Networks

报告人:Dr. Chao Ma (Senior Research Associate, Australia Centre for Robotic Vision, The University of AdelaideAustralia)

报告时间:2016121815:30

报告地点:学院报告厅(望江校区基础教学大楼B302

 

报告内容:

Visual object tracking is challenging as target objects often undergo significant appearance changes. In this talk, I will present our recent work on how to best exploit deep regression networks to improve tracking accuracy and robustness. First, I will introduce our ICCV 2015 work, in which we adaptively learn correlation filters on hierarchical convolutional layers to precisely locate targets. Second, I will present our ICCV 2017 work, where we reformulate correlation filters by a one-layer neural network. We additionally exploit the spatial and temporal residual learning scheme to facilitate visual tracking. Last, I will report our recent work under review for CVPR 2018. In this work, we propose a novel shrinkage loss to train deep regression networks for visual tracking. Extensive experimental results on largescale benchmark datasets show that the proposed algorithms perform favourably against state-of-the-art methods.

 

报告人简介:

马超,阿德莱德大学高级研究员(Senior Research Associate),合作导师为沈春华(Chunhua Shen)教授和Ian Reid教授。于20166月获上海交通大学博士学位。20139月至20159月作为联合培养博士生,在加州大学默塞德分校Ming-Hsuan Yang教授计算视觉组学习。研究兴趣为计算机视觉,主要关注目标跟踪,图像超分辨以及图像检索。相关工作多次发表在计算机视觉顶级会议ICCVCVPRECCV上。发表于ICCV 2015的论文,首次提出利用多层级深度学习特征对运动目标进行跟踪的高效算法,在多个测试集上达到了国际领先的准确度。本论文被新媒体“新智元”评为影响深度学习的百篇经典论文之一,目前Google Scholar单篇引用量一年多时间为 220。曾受邀在视觉与学习青年研讨会上(VALSE)对本论文进行了汇报,被评为VALSE 2016-2017年度优秀Webinar讲者。

 

欢迎广大师生踊跃参加!

 

 

外事科

                                                    20171212






】 【打印本文】 【关闭窗口

 

 

地址:(望江校区)成都市一环路南一段24号基础教学楼B座三楼 邮编:610065 电话:86-028-85469688
   (江安校区)成都市双流县川大路第二基础教学楼B座五楼 邮编:610207 电话:86-028-85990972

万博娱乐彩票官网版权所有 © 2011

Produced By CMS 网站群内容管理系统 publishdate:2017/12/13 09:49:08