设为首页收藏本站

VALSE

VALSE 首页 活动通知 好文作者面授招 查看内容

20180627-18 王鑫超:Tracking Multiple Objects in Image Sequences

2018-6-21 18:44| 发布者: 程一-计算所| 查看: 831| 评论: 0

摘要: 报告嘉宾:王鑫超(Stevens Institute of Technology)报告时间:2018年06月27日(星期三)早上10:00(北京时间)报告题目:Tracking Multiple Objects in Image Sequences主持人:樊彬(中科院自动化所)报告人简介 ...

报告嘉宾:王鑫超Stevens Institute of Technology

报告时间:2018年06月27日(星期三)早上10:00(北京时间)

报告题目:Tracking Multiple Objects in Image Sequences

主持人:樊彬(中科院自动化所)


报告人简介:

Xinchao Wang is currently a tenure-track assistant professor in the Department of Computer Science, Stevens Institute of Technology. His main research interests include Computer Vision, Applied Machine Learning, Multimedia, and Big Data Analytics. Before joining Stevens, he was a Postdoc at the Image Formation and Professing (IFP) group at Beckman Institute, University of Illinois Urbana-Champaign  (UIUC). He received a Ph.D. from the Computer Vision Lab, École polytechnique fédérale de Lausanne (EPFL) in 2015, and a first-class honorable B.Sc. in Department of Computing, the Hong Kong Polytechnic University (HKPU) in 2010.


个人主页:


https://sites.google.com/site/sitexinchaowang/


报告摘要:

Multi-object tracking (MOT) is a crucial task in computer vision, for which the goal is to follow the states of objects over time while preserving their identities. In this talk, we will discuss several major challenges of MOT and our models to handle them. We will show a wide domain of application scenarios ranging from video surveillance through sports analytics to medical image analysis.


参考文献:

[1] Interacting Tracklets for Multi-object Tracking 

L Lan, X Wang, S Zhang, D Tao, W Gao, TS Huang 

IEEE Transactions on Image Processing (TIP), 2018.

 

[2] Greedy Batch-based Minimum-cost Flows for Tracking Multiple Objects X Wang, B Fan, S Chang, Z Wang, X Liu, D Tao, TS Huang

IEEE Transactions on Image Processing (TIP), 2017.

 

[3] Non-Markovian Globally Consistent Multi-Object Tracking A Maksai, X Wang, F Fleuret, P Fua  International Conference on Computer Vision (ICCV), 2017.

 

[4] Tracking Interacting Objects Using Intertwined Flows X Wang, E Türetken, F Fleuret, P Fua IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2016.


18-18期VALSE在线学术报告参与方式:


长按或扫描下方二维码,关注”VALSE“微信公众号(valse_wechat),后台回复”18期“,获取直播地址。



特别鸣谢本次Webinar主要组织者:

VOOC责任委员:樊彬(中科院自动化所

VODB协调理事:彭玺(四川大学



活动参与方式:

1、VALSE Webinar活动依托在线直播平台进行,活动时讲者会上传PPT或共享屏幕,听众可以看到Slides,听到讲者的语音,并通过聊天功能与讲者交互;

2、为参加活动,请关注VALSE微信公众号:valse_wechat 或加入VALSE QQ群(目前A、B、C、D、E、F、G群已满,除讲者等嘉宾外,只能申请加入VALSE H群,群号:701662399);

*注:申请加入VALSE QQ群时需验证姓名、单位和身份,缺一不可。入群后,请实名,姓名身份单位。身份:学校及科研单位人员T;企业研发I;博士D;硕士M。

3、在活动开始前5分钟左右,讲者会开启直播,听众点击直播链接即可参加活动,支持安装Windows系统的电脑、MAC电脑、手机等设备;

4、活动过程中,请不要说无关话语,以免影响活动正常进行;

5、活动过程中,如出现听不到或看不到视频等问题,建议退出再重新进入,一般都能解决问题;

6、建议务必在速度较快的网络上参加活动,优先采用有线网络连接;

7、VALSE微信公众号会在每周一推送上一周Webinar报告的总结及视频(经讲者允许后),每周四发布下一周Webinar报告的通知及直播链接。


[slides]

最新评论

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

GMT+8, 2018-9-23 11:13 , Processed in 0.043371 second(s), 19 queries .

Powered by Discuz! X3.2

© 2001-2013 Comsenz Inc.

返回顶部