Recent technological advancements have led to a deluge of data from distinctive domains
(eg, health care and scientific sensors, user-generated data, Internet and financial …

Big data refer to the massive amounts and varieties of information in the structured and
unstructured form, generated by social networking sites, biomedical equipment, financial …

Recognizing visual content in unconstrained videos has become a very important problem
for many applications. Existing corpora for video analysis lack scale and/or content diversity …

Zero-shot complex event detection has been an emerging task in coping with the scarcity of
labeled training videos in practice. Aiming to progress beyond the state-of-the-art zero-shot …

The goal of high-level event recognition is to automatically detect complex high-level events
in a given video sequence. This is a difficult task especially when videos are captured under …

In this paper, we propose a rank minimization method to fuse the predicted confidence
scores of multiple models, each of which is obtained based on a certain kind of feature …

The rapid development of social media sharing has created a huge demand for automatic
media classification and annotation techniques. Attribute learning has emerged as a …

Abstract Multimedia Event Detection (MED) is a multimedia retrieval task with the goal of
finding videos of a particular event in video archives, given example videos and event …

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 …

This paper aims for event recognition when video examples are scarce or even completely
absent. The key in such a challenging setting is a semantic video representation. Rather …