您当前的位置:

【学术报告】德国马普所孙倩茹博士于4月14日来访实验室

发布时间:2017-04-14

报告题目:Human activity analysis -from a computer vision view to a social psychology view

时 间:2017年4月14日下午15:00-16:00
地 点:计算所436教室


报告摘要:
When the classical recognition of human activity can be well solved by deep models, we try to contribute more efforts to highly social semantic level analysis on human interaction behaviors. One important direction is the social relation recognition in daily life photos.
Social domain-based theory from social psychology is a great starting point to systematically approach social relation recognition. This theory provides a coverage of all aspects of social relations and equally is concrete and predictive about the visual attributes and behaviors defining the relations in each domain. We provide the first photo dataset built on this holistic conceptualization of social life that is composed of a hierarchical label space of social domains and social relations, and contributes the first models to recognize such domains and relations and find superior performance for attribute based features. Beyond the encouraging performances, we have some findings of interpretable features that are in accordance with the predictions from social psychology literature. Our work mainly contributes to interleave visual recognition and social psychology theory that has the potential to complement the theoretical work in the area with empirical and data-driven models of social life.


报告人简介:

Qianru Sun is currently a post-doctor in the department of Computer Vision and Multimodal Computing, Max Planck Institute for Informatics, Saarbruecken, Germany. Collaborators are Prof. Bernt Schiele and Dr. Mario Fritz. She obtained her PhD degree in the School of Electronics Engineering and Computer Science, Peking University, in Jan. 2016. Her research interests include computer vision, pattern recognition and time series prediction. Specific application experiences have been made in human action recognition, prediction and anomaly detection in surveillance videos, and social relation recognition in daily life photos.



附件下载: