各部门、各单位：
应我校通信与信息工程学院的邀请，西安电子科技大学王晗丁教授、唐旭博士将于9月13日来我校做专题学术讲座，欢迎广大师生参加！报告的具体安排如下：
报告时间：2018年9月13日（周四）下午15:00—17:00。
报告地点：长安校区通院大楼106室。
报 告 一：Offline and Online Data-Driven Evolutionary Optimization（王晗丁 教授）9月13日下午15:00-16:00
摘要：很多工业界实际问题可建模成黑盒优化问题，优化方法需多次评价候选解，但是实际问题函数评价的运算代价高或存在多个精度，这阻碍了已有优化方法的垂直应用。数据驱动的优化方法是新兴的人工智能方法论，以进化计算为优化方法，将实际问题函数评价看作数据，利用已有成熟的机器学习算法训练得到近似的函数评价来辅助优化方法进行搜索，大大提高了传统优化算法实用性。
报告人简介：王晗丁，西安电子科技大学电子工程学院博士，现为西安电子科技大学人工智能学院教授，博士生导师，英国萨里大学计算机系研究员。研究方向包括计算智能、机器学习、多目标优化及代理模型。
近五年发表高水平论文24篇，其中以第一作者/通讯作者发表JCR一区8篇，JCR二区2篇，包括计算智能领域国际顶级期刊《IEEE Trans. on Evolutionary Computation》、《IEEE Trans. on Cybernetics》、《Evolutionary Computation》和《Information Sciences》，且其中一篇入选IEEE Computational Intelligence Society当季Spotlight文章。
在海外研究期间，作为主研身份参与1项英国工程与物理科学研究资助局（EPSRC）项目《Data-driven surrogate-assisted evolutionary fluid dynamicoptimization》。
王晗丁教授是国际计算智能研究领域非常活跃的年轻学者。现担任IEEE计算智能协会演化计算技术委员会（Intelligent Systems Applications Technical Committee of IEEE Computational Intelligence Society）Task Force 13主席。兼职计算智能国际期刊《IEEE Computation Intelligence Magazine》和模式识别国际期刊《Complex & Intelligent Systems》编委（Associate Editor）。曾担任神经计算领域国际知名期刊《Neurocomputing》、《IEEE Transactions on Emerging Topics in Computational Intelligence》与《IEEE Access》客座编委（Guest Editor），并担任演化计算领域顶级国际会议《Genetic and Evolutionary ComputationConference》、《IEEE Congress of Evolutionary Computation》及多个其他国际会议的程序委员会成员。长期担任计算智能领域多个国际顶级期刊审稿人。
报 告 二：Unsupervised Deep Feature Learning for Remote Sensing Image Retrieval（唐旭 博士）9月13日下午16:00-17:00
摘要：Due to the specific characteristics and complicated contents of remote sensing (RS) images, remote sensing image retrieval (RSIR) is always an open and tough research topic in the RS community. There are two basic blocks in RSIR, including feature learning and similarity matching. In this paper, we focus on developing an effective feature learning method for RSIR. With the help of the deep learning technique, the proposed feature learning method is designed under the bag-of-words (BOW) paradigm. Thus, we name the obtained feature deep BOW (DBOW). The learning process consists of two parts, including image descriptor learning and feature construction. First, to explore the complex contents within the RS image, we extract the image descriptor in the image patch level rather than the whole image. In addition, instead of using the handcrafted feature to describe the patches, we propose the deep convolutional auto-encoder (DCAE) model to deeply learn the discriminative descriptor for the RS image. Second, the k-means algorithm is selected to generate the codebook using the obtained deep descriptors. Then, the final histogrammic DBOW features are acquired by counting the frequency of the single code word. When we get the DBOW features from the RS images, the similarities between RS images are measured using L1-norm distance. Then, the retrieval results can be acquired according to the similarity order. The encouraging experimental results counted on four public RS image archives demonstrate that our DBOW feature is effective for the RSIR task. Compared with the existing RS image features, our DBOW can achieve improved behavior on RSIR.
报告人简介：Xu Tang (S’13) received the B.S., M.S., and Doctor Degrees fromXidianUniversity,Xi’an,China, in 2007, 2010 and 2017, respectively. Now, he is currently a member of the Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education,XidianUniversity. His current research interests include remote sensing image processing, remote sensing image content-based retrieval and reranking.
特此通知。
科研处
通信与信息工程学院
2018年9月7日
