本讲座着重介绍视频监控下的行人识别和交互行为分析。智能视频监控.doc

Topic： Distance Metric Learning in Person Re-identification Abstract: Matching people across non-overlapping camera views at different locations and different time, known as person re-identification, is both a hard and important problem for associating behavior of people observed in a large distributed space over a prolonged period of time. Person re-identification is fundamentally challenging because of the large visual appearance changes caused by variations in view angle, gesture, lighting, background clutter, and occlusion. Due to these challenges, it is hard to extract distinctive and reliable visual features across camera views. Hence, seeking an optimal and robust similarity measure that quantifies a wide range of features against realistic viewing conditions is critically important for person re-identification. This talk will present our recent research works on distance metric learning for robust cross-view matching, including relative distance comparison model and its transfer extension for solving the open-world matching problem, an asymmetric view-transform distance model, a cross-scale subspace model, a cross-scenario transfer model, and a top-push distance metric learning for video re-id. Bio: 郑伟诗博士，中山大学数据科学与计算机学院教授，国家优秀青年科学基金获得者、英国皇家学会牛顿高级学者基金获得者、广东省自然科学杰出青年基金获得者、微软亚洲研究院青年学者铸星计划入选者。他主要面向智能视频监控，展开视频图像信息与信号的处理研究。他目前的主要研究方向是：视频监控下的行人身份识别与行为理解，其中他在国内外较早和持续开展行人再标识的研究，并发表一系列以跨视域度量学习为主线的研究工作。已发表/接受含5篇PAMI在内的80余篇主要学术论文，其中40余篇发表在图像识别和模式分类IEEE TPAMI、IEEE TIP、IEEE TNN、PR、IEEE TCSVT、IEEE TSMC-B等国际主流权威期刊和ICCV、CVPR、IJCAI等计算机学会推荐A类国际学术会议。在所发表的论文中，曾发表ESI高被引论文3篇。近5年来，与国内外同行一道，他在计算机学会推荐A类国际学术会议ICCV和CVPR上以及其它著名国际学术会议期间做Tutorial。他曾担任IEEE AVSS的Area Chair，担任2012年、2015年和2016年全国生物特征识别学术会议的联合程序委员会主席。