中国计算机学会青年计算机科技论坛
CCF YOCSEF
于2014年12月10日（星期三）10:15-11:45
在南开大学（伯苓楼东区306会议室）
研讨会主题
PRISM: Person Re-Identification via Structured Matching
10:15 签到
10:30 报告会开始
特邀讲者：张子明 博士，研究员，美国波士顿大学
报告题目：PRISM: Person Re-Identification via Structured Matching
执行主席：刘晓光 博士， 教授，南开大学，CCF YOCSEF天津主席
执行主席：程明明 博士，副教授，南开大学
执行主席：杨巨峰 博士，副教授，南开大学，CCF YOCSEF天津AC
(1)报告内容简介：
Person re-identification (re-id), an emerging problem in visual surveillance, deals with maintaining entities of individuals whist they traverse various locations surveilled by a camera network. From a visual perspective re-id is challenging due to significant changes in visual appearance of individuals in cameras with different pose, illumination and calibration. Globally the challenge arises from the need to maintain structurally consistent matches among all the individual entities across different camera views.
We propose PRISM, a structured matching method to jointly account for these challenges. We view the global problem as a weighted graph matching problem and estimate edge weights by learning to predict them based on the co-occurrences of visual patterns in the training examples. These co-occurrence based scores in turn account for appearance changes by inferring likely and unlikely visual co-occurrences appearing in training instances. We implement PRISM on single shot, multi-shot and some open-world scenarios. PRISM uniformly outperforms state of the art by as much as 10%-30% in matching rate while being computationally efficient.
(2)个人简介：
Dr. Ziming Zhang received an MS degree in 2010 from School of Computing Science at Simon Fraser University, Canada. Later he received a PhD degree in Computer Science from Oxford Brookes University, UK, under the supervision of Prof. Philip H. S. Torr in 2013. Currently he is holding a research position in Boston University, MA. His research areas includes object recognition and detection, machine learning, optimization, large-scale information retrieval, visual surveillance, and medical imaging. His works have been published at top conferences such as CVPR, ECCV, and NIPS.
京公网安备 11010802032778号