• 学术动态

9月18日澳大利亚阿德莱德大学张臻学术报告预告
作者:cwj 发布日期:2019-09-12 浏览次数:

报告题目:深度图特征学习在匹配问题中的应用

Deep Graphical Feature Learning for the Feature Matching Problem

报告时间: 918(周三) 下午2:30

报告地点:计算机学院四楼会议室A411

报  告 人:张臻,阿德莱德大学博士后研究员

    张臻博士即将加入阿德莱德大学任博士后研究员,主要研究方向为概率图模型与图网络学习。此前,张臻2010年与西北工业大学计算机学院取得学士学位,于2017年于西北工业大学计算机学院取得博士学位(导师:张艳宁教授),并于20177月到20198月在新加坡国立大学担任博士后研究员(导师:Lee Wee Sun教授),在201211月到201412月,在澳大利亚阿德莱德大学联合培养(导师:史勤锋副教授 与 Anton ven den Hengel教授)。截至目前,张臻博士已经在CVPRICCVAAAI IJCAIIEEE TIP, IEEE TMM等重要会议和期刊上发表论文十余篇,并为CVRPICCVNIPSICMLICLRIEEE TGRS等重要会议和期刊担任审稿人。

报告摘要:

The feature matching problem is a fundamental problem in various areas of computer vision including image registration, tracking and motion analysis. Rich local representation is a key part of efficient feature matching methods.  However, when the local features are limited to the coordinate of key points, it becomes challenging to extract rich local representations. Traditional approaches use pairwise or higher order handcrafted geometric features to get robust matching; this requires solving NP-hard assignment problems. In this paper, we address this problem by proposing a graph neural network model to transform coordinates of feature points into local features. With our local features, the traditional NP-hard assignment problems are replaced with a simple assignment problem which can be solved efficiently. Promising results on both synthetic and real datasets demonstrate the effectiveness of the proposed method.