We address the challenge of sentiment analysis from visual content. In contrast to existing
methods which infer sentiment or emotion directly from visual low-level features, we propose …

Image tagging is an essential step for developing Automatic Image Annotation (AIA)
methods that are based on the learning by example paradigm. However, manual image …

With the explosive growth of web videos on the Internet, it becomes challenging to efficiently
browse hundreds or even thousands of videos. When searching an event query, users are …

This paper proposes a new video representation for few-example event recognition and
translation. Different from existing representations, which rely on either low-level features, or …

The purpose of this study was to develop and evaluate the video on demand learning
system. This study integrated the thematic instructional strategy into interactive video-based …

Time-sync video tagging aims to automatically generate tags for each video shot. It can
improve the user's experience in previewing a video's timeline structure compared to …

This study implemented and examined the effects of a self-paced learning environment-
interactive thematic video (ITV) designed to enhance learner's achievement and motivation …

Learning classifiers for many visual concepts are important for image categorization and
retrieval. As a classifier tends to misclassify negative examples which are visually similar to …

To collect extensive data on realistic driving behavior, we propose a framework using online
public traffic cam video streams. We implement the Traffic Camera Pipeline (TCP), a system …

We present an extension of automatic image annotation that takes the context of a picture
into account. Our core assumption is that users do not only provide individual images to be …