山东大学新闻网
山大邮箱 | 投稿系统 | 高级检索 | 旧版回顾
复杂检索

视点首页 > 学术预告 > 正文

Pattern Mining and Concept Discovery for Multimodal Content Analysis

发布日期:2018年09月10日 15:33 点击次数:

时间 9月12日(周三)10:00-11:00 地点 软件园校区行政楼办公楼202会议室
本站讯 讲座时间 2018-09-12 10:00:00

一、报告题目

Pattern Mining and Concept Discovery for Multimodal Content Analysis

二、主讲人

 Hongzhi Li

三、主持人

许信顺

四、主讲人简介

Dr. Hongzhi Li is a Senior Research SDE in Microsoft Research. His research interests are machine learning, multimodal content analysis and cloud based computing. His current research is focused on deep learning for visual intelligence and its applications on cloud computing platform.

Dr. Li received his PhD degree in Computer Science from Columbia University in 2016. Before that, he received his Bachelor and Master degree in Computer Science from Zhejiang University, China and Columbia University, US, in 2010 and 2012, respectively.

Dr. Li has published in ACM Multimedia, TMM, ICMR, EMNLP, NAACL, SPIE and other venues. He received best poster award in ACM ICMR 2018. He is the winner of grand challenge (first place) in ACM Multimedia 2012. Dr. Li severed in program committee of major international conferences, including ACM MM, ICME, IJCAI, etc. He also severed as a reviewer in journals including IEEE TMM, IEEE TCSVT, TPAMI, JVCI, JVIS, etc.

五、报告摘要

Visual patterns are the discriminative and representative image content found in objects or local image regions seen in an image collection. Visual patterns can also be used to summarize the major visual concepts in an image collection. In this talk, I’ll discuss the following question: given a new target domain and associated data corpora, how do we rapidly discover nameable content patterns that are semantically coherent, visually consistent, and can be automatically named with semantic concepts related to the events of interest in the target domains? We develop pattern discovery methods that focus on visual content as well as multimodal data including text and visual. Traditional visual pattern mining methods only focus on analysis of the visual content, and do not have the ability to automatically name the patterns. To address this, we propose a new multimodal visual pattern mining and naming method that specifically addresses this shortcoming. The named visual patterns can be used as discovered semantic concepts relevant to the target data corpora. By combining information from multiple modalities, we can ensure that the discovered patterns are not only visually similar, but also have consistent meaning, as well. To discover better visual patterns, we further improve the visual model in the multimodal visual pattern mining pipeline, by developing a convolutional neural network (CNN) architecture that allows for the discovery of scale-invariant patterns.

六、时间

2018912日上午10:00-11:00

六、地点

软件园校区行政楼办公楼202会议室

 

 



【作者:许信顺        来自:软件学院    责任编辑:王浩铭 张丹丹  】

 匿名发布 验证码 看不清楚,换张图片
0条评论    共1页   当前第1拖动光标可翻页查看更多评论

最新发布

新闻排行

免责声明

您是本站的第: 位访客

新闻中心电话:0531-88362831 0531-88369009  联系信箱:xwzx@sdu.edu.cn
建议使用IE6.0以上浏览器和1024*768分辨率浏览本站以取得最佳浏览效果

欢迎关注山大视点微信