演讲人: Dr. Zhi LIU
时间: 2014 年 6 月 5 日（周四）中午 12:00
地点: 计算机楼 405 室
承办单位: 复旦大学计算机科学技术学院
联系人：路红老师（honglu@fudan.edu.cn）
Abstract:
Saliency detection has been a hot research topic in the recent years, due to its broad range of applications including human fixation prediction, salient object detection and segmentation, content-aware image/video retargeting, content-based image/video compression, and content-based image retrieval, etc. In this talk, region-based saliency models showing high saliency detection performance for images and videos will be presented. First, a saliency tree model which enables a hierarchical representation of saliency is proposed to effectively handle complicated images with low contrast between objects and background, heterogeneous objects, cluttered background and the issue of object scales. Then, a superpixel-based spatiotemporal saliency model which exploits effective superpixel-level temporal/spatial saliency measurement, pixel-level saliency derivation and adaptive fusion for spatiotemporal saliency map generation is proposed for saliency detection in videos. Experimental results on several public datasets demonstrate that the above proposed two saliency models consistently outperform the state-of-the-art saliency models.
Biography:
Zhi Liu received the B.E. and M.E. degrees from Tianjin University, China, and the Ph.D. degree from the Institute of Image Processing and Pattern Recognition, Shanghai Jiaotong University, China, in 1999, 2002, and 2005, respectively.
He is currently a Professor with the School of Communication and Information Engineering, Shanghai University, China. Since Aug. 2012, he has also been a Visiting Researcher with the SIROCCO Team, IRISA/INRIA-Rennes, France, with the support by EU FP7 Marie Curie Actions. His current research interests include saliency model, image/video segmentation, image/video retargeting, video coding, and multimedia communication.
Dr. Liu has published more than 100 refereed technical papers in international journals and conferences. He served as a TPC Member with ICME 2014, WIAMIS 2013, IWVP 2011, PCM 2010, and ISPACS 2010. He co-organized special sessions on visual attention, saliency models, and applications at WIAMIS 2013 and ICME 2014.
