“LIAMA系列学术讲座”由中欧信息自动化与应用数学联合实验室（LIAMA）发起，中国科学院自动化研究所和LIAMA共同赞助。旨在为模式识别领域的中外专家学者提供一个自由交流的平台。LIAMA系列讲座将定期邀请国内外相关领域专家参与，分享最前沿的学术成果，启发思考，平等交流，为中欧双边科研合作提供更加稳定、开放的平台。
讲座日期：
2021年9月25日
报告日程：
15：00-16：00
报告人：黄民烈 清华大学
Emotional Intelligence in Dialog Systems
16：00-17：00
报告人：鲁继文 清华大学
Deep Metric Learning for Visual Content Understanding
主持人：
陶建华研究员
观看方式：
『中科院自动化所』B站直播间！
报告摘要
1. Emotional Intelligence in Dialog Systems
Emotional intelligence refers to “the ability to monitor one’s own and other people’s emotions, to discriminate between different emotions and label them appropriately, and to use emotional information to guide thinking and behavior”, which has been viewed as one of the most important intelligent behaviors of human being. So, do today’s dialog systems possess emotional intelligence? Can dialog systems accomplish tasks like emotion comforting, expressing empathy, or even counselling? In this talk, the speaker will present his research and related works on this topic, namely, generating controllable emotions, empathetic dialogs, providing emotional support, and even generating professional counselling responses.
2. Deep Metric Learning for Visual Content Understanding
In this talk, I will overview the trend of deep metric learning techniques and discuss how they are employed to boost the performance of various visual content understanding tasks. Specifically, I will introduce some of our proposed deep metric learning methods including discriminative deep metric learning, deep localized metric learning, deep coupled metric learning, multi-manifold deep metric learning, deep transfer metric learning, deep adversarial metric learning, multi-view deep metric learning, and interpretable deep metric learning, which are developed for different application-specific visual content understanding tasks such as face recognition, person re-identification, object recognition, action recognition, visual tracking, image set classification, and visual search. Lastly, I will discuss some open problems in deep metric learning to show how to further develop more advanced deep metric learning methods in the future.