2021-11-05 18:22 吉婷 王梦涵  计算机学院 审核人:   (点击: )


报告一:Hyperspectral Imagery Processing and Classification


西北工业大学计算机学院教授。2012年博士毕业于西北工业大学计算机学院并留校,现为计算机学院信息工程系教师。主要研究方向为遥感图像处理与分析,已主持3项国家自然科学基金项目,并在IJCV、TIP、TGRS、CVPR等高水平刊物上发表学术论文30余篇。担任遥感领域著名期刊IEEE JSTARS编委,IEEE高级会员,CVPR、AAAI、ACM MM、IEEE TIP、TGRS等会议和期刊的程序委员或审稿人。



报告二:Vision-language interaction: technologies behind applications


西北工业大学计算机学院副教授。2015年于中国科学技术大学自动化系,获得工学学士学位;2020年于中国科学院自动化研究所模式识别国家重点实验室,获得工学博士学位。博士毕业后于2020年10月加入西北工业大学计算机学院,任职副教授,从事计算机科学与技术学科方向的教学及科研工作。长期专注于多模态数据分析、计算机视觉、模式识别等相关领域的科学研究工作,特别是在视觉-语言交互前沿领域,以第一作者发表包括IEEE TIP, ACM MM, PR等在内的多篇国际高水平学术论文。

报告简介:The goal of this course is to give students an understanding of many vision-language interaction tasks that can be seen everywhere in our daily life, to understand the latest technologies behind these applications, and to look forward to the future development of AI technology.

The course is organized into three parts: 1. introduction to the vision-language interaction applications, 2. task abstraction and definition, and 3. the key technologies in solution. In part one, several common vision-language interaction tasks are introduced, including their application scenarios, characteristics, and so on. Part two shows the way that scientists and engineers give abstraction and definition of these application problems for further studying. The last part gives detailed explanations of the key technologies for solving these problems.



报告三:Comprehending Human Cognitions of Uncertainty Visualizations


西北工业大学计算机学院副教授,于2017年和2012年分别获美国克莱姆森大学计算机博士和硕士学位,后创办人工智能科技公司,于2020年加入西工大。曾参与多项美国国家级科研项目,其中不确定性可视化研究为美国自然科学基金会(NSF IIS)支持的最高级别项目。研究方向包括可视化、视觉认知、计算机图形和人工智能学等。

报告简介:Uncertainty inevitably exists in all stages of scientific data analysis pipelines. Effectively acquiring data uncertainty plays a vital role in exploring complex natural and scientific phenomena behind the data. Visualizations maximize utility of visual processing, being considered as one of the most effective ways of uncertainty delivery. However, we have experimentally demonstrated an existing discrepancy between the expected and authentic users’ comprehensions of visual encodings of uncertainty. To address this issue, we have proposed a unique category of decision-making biases termed visual-spatial biases as well as a novel design framework termed representative implicit uncertainty visualizations.



报告四:Adaptive feature weight learning for robust clustering problem with sparse constraint


西北工业大学计算机学院博士研究生,曾在多个国际期刊和会议上发表多篇学术论文,如:IEEE Transactions on Knowledge and Data Engineering (TKDE)、 TRANSACTIONS ON CYBERNETICS(T-CYB)、IEEE International Conference on Acoustics Speech and Signal Processing(ICASSP)等。研究方向为机器学习与模式识别。

报告简介:Clustering task has been greatly developed in recent years like partition-based and graph-based methods. However, in terms of improving robustness, most existing algorithms only focus on noise and outliers between data, while ignoring the noise in feature space. To deal with this situation, we propose a novel weight learning mechanism to adaptively reweight each feature in the data. Combining with the clustering task, we further propose a robust fuzzy K-Means model based on the auto-weighted feature learning, which can effectively reduce the proportion of noisy features. Besides, a regularization term is introduced into our model to make the sample-to-clusters memberships of each sample have suitable sparsity. Specifically, we design an effective strategy to determine the value of the regularization parameter. In this talk, I will introduce the background, the concept and the mechanism of the proposed method.



报告五:Some classical machine learning algorithms


西北工业大学计算机学院博士研究生。于2018年6月获得中北大学计算机科学与技术硕士学位。已在国际期刊和会议上发表5篇学术论文,包括:IEEE Transactions on Neural Networks and Learning Systems (TNNLS),International Joint Conference on Artificial Intelligence (IJCAI),IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)等。研究兴趣包括特征选择、聚类和降维等机器学习算法。

报告简介:Machine learning is a discipline widely used in the fields of science and engineering. Dimensionality reduction, clustering, and classification are fundamental topics in machine learning. In this report, I will introduce the basic concepts of machine learning, and some representative machine learning algorithms, including a dimensionality reduction algorithm, namely PCA (Principal Component Analysis), a clustering algorithm, namely k-means clustering, and a classification algorithm, namely SVM (Support Vector Machine). Furthermore, I will share some writing skills and submission experience.