詳細資料
|
08/13(四)邀請Dr. Mark Zhang來系演講
各位老師、同學： 主辦單位：國立成功大學 資訊工程系 內容摘要： The problem of multimodal data mining in a multimedia database can be addressed as a structured prediction problem where we learn the mapping from an input to the structured and interdependent variables. In this talk, I will introduce a new max-margin learning approach called Enhanced Max-Margin Learning (EMML) framework. In addition, I will show that the EMML framework can be applied as an effective solution to the multimodal data mining problem in a multimedia database. I will show that EMML is much more efficient in learning with a much faster convergence rate, which is guaranteed through theoretical analysis and is also verified in empirical evaluations. I will also show that EMML as an effective solution to the multimodal data mining problem that is highly scalable in the sense that the query response time is independent of the database scale, allowing facilitating a multimodal data mining querying to a very large scale multimedia database, and excelling many existing multimodal data mining methods in the literature that do not scale up at all. To showcase the strength of EMML, we apply it to the Berkeley Drosophila embryo image database, and I will report the performance comparison with a state-of-the-art multimodal data mining method. This is a joint work with Zhen Guo of SUNY Binghamton, and Eric P. Xing and Christos Faloutsos of CMU. 個人簡介： Zhongfei Zhang is an associate professor at the Computer Science Department at State University of New York (SUNY) at Binghamton, and the director of the Multimedia Research Laboratory in the Department. He received a B.S. in Electronics Engineering (with Honors), an M.S. in Information Sciences, both from Zhejiang University, China, and a PhD in Computer Science from the University of Massachusetts at Amherst, USA. He was on the faculty of Computer Science and Engineering Department, and a research scientist at the Center of Excellence for Document Analysis and Recognition, both at SUNY Buffalo, before he joined the faculty of computer science at SUNY Binghamton. He was one of the few who initiated the research in multimedia data mining and is the author of the very first monograph on this topic published recently, together with Ruofei Zhang at Yahoo! Labs. His research has been funded by a number of federal government agencies including NSF, AFOSR, and AFRL, industry research labs including Kodak Research and Microsoft Research, as well as a number of private foundations and foreign funding agencies such as French CNRS and Japanese JSPS. He holds more than ten inventions, has served as reviewers/PC members for many conferences and journals, has held the positions as regular grant review panelists for federal government funding agencies (NSF and NASA), New York State government funding agencies, and private funding agencies, and is currently in the editorial boards for several journals. He has also served as technical consultants for a number of industrial and governmental organizations. Email address: zhongfei@cs.binghamton.edu
相關網址：無 |