<button id="lbda9"><sub id="lbda9"></sub></button>
      1. <button id="lbda9"><acronym id="lbda9"></acronym></button>
      2. <dd id="lbda9"><noscript id="lbda9"></noscript></dd>
      3. <rp id="lbda9"><object id="lbda9"><blockquote id="lbda9"></blockquote></object></rp>
            <rp id="lbda9"></rp>
          1. <legend id="lbda9"></legend>

            海天學者王歆講座通知

            2019年06月19日  點擊:[]

            報告人:王歆(紐約州立大學石溪分校,我校海天學者)

            報告時間:6月20日,10:00-11:20

            報告地點:開發區教學樓A401

            報告題目:Crossing-Domain Generative AdversarialNetworks for Unsupervised Multi-Domain Image-to-Image Translation

            報告內容:State-of-the-art techniques in Generative Adversarial Networks(GANs) have shown remarkable success in image-to-image translationfrom peer domain X to domain Y using paired image data.However, obtaining abundant paired data is a non-trivial and expensiveprocess in the majority of applications. When there is aneed to translate images across n domains, if the training is performedbetween every two domains, the complexity of the trainingwill increase quadratically. Moreover, training with data from twodomains only at a time cannot benefit from data of other domains,which prevents the extraction of more useful features and hindersthe progress of this research area. In this work, we propose a generalframework for unsupervised image-to-image translation acrossmultiple domains, which can translate images from domain X toany a domain without requiring direct training between the twodomains involved in image translation. A byproduct of the frameworkis the reduction of computing time and computing resources,since it needs less time than training the domains in pairs as is donein state-of-the-art work. Our proposed framework consists of apair of encoders along with a pair of GANs which learns high-levelfeatures across different domains to generate diverse and realisticsamples from. Our framework shows competing results on manyimage-to-image tasks compared with state-of-the-art techniques.

            報告人簡介:Dr. Wang is currently the director of the Wireless Networking and Systems lab of the department of Electrical and Computer Engineering of the State University of New York (SUNY) at Stony Brook. She was a Member of Technical Staff in the area of mobile and wireless networking at Bell Labs Research, Lucent Technologies, New Jersey between 2001 and 2003. Dr. Wang has been conducting and leading research work in the design of network architectures, protocols and algorithms. The work of her group falls into a few directions, including advanced wireless network architecture, mobile cloud computing and distributed computing, and big data analysis and deep learning. Dr. Wang obtained her PhD from Columbia University, BS and MS from Beijing University of Post and Telecommunications, respectively. She is a recipient of NSF career award in 2005 and the ONR Chief of Naval Research (CNR) Challenge award in 2011.

            She currently serves as an associate editor of IEEE Transactions of Mobile Computing (TMC). She also serves TPC chair or program committee members in many technical conferences, including ACM MobiCom, IEEE Infocom, IEEE ICDCS, and IEEE PerCom. Her research group has published more than 100 papers in highly reputed conferences and journals, including ACM Sigmetrics, ACM MobiCom, USENIX NSDI, IEEE ICNP, IEEE Infocom, IEEE ICDCS, IEEE Percom, IEEE TON, IEEE TMC, IEEE JSAC, IEEE TC, and IEEE TDSC.

            備注:本科生可算學分

            歡迎廣大師生參加

            上一條:麻省大學熊杰教授學術報告 下一條:智能網絡安全技術研討會

            關閉

            第九影院在线观看视频