VIStA (Visual Intelligence & Social Multimedia Analytics)
University of Rochester
Apply to group
Computer Science
Engineering/ Math/ Computer Science, Social Sciences, Natural and Biomedical Sciences
[Computer Vision]: recognition of objects, scenes, people, locations, actions, and events from images and videos [Vision and Language]: description and explanation of visual content; language-based search, retrieval, and generation [Social media data mining]: prediction, nowcasting, forecasting, profiling, and recommendation using open-source data [Machine Learning]: learning with large-scale loosely labeled web data, cross-domain learning, few-shot learning [Health informatics]: healthcare and wellness analytics using text and visual data; surgical video analysis [Pervasive computing]: context-aware applications; multimodal inference from multiple sensors [Media experience]: multimodal reliving; aesthetics, emotion, sentiment, and influence of multimedia [Note]: Undergraduate students should seek research opportunities after having done well in the related courses (240/440 Data Mining and/or 249/449 Machine Vision).