This paper addresses the challenging problem of learning from multiple annotators whose labeling accuracy (reliability) differs and varies over time. We propose a framework based ...
We present a method for unsupervised learning of event classes from videos in which multiple actions might occur simultaneously. It is assumed that all such activities are produce...
Muralikrishna Sridhar, Anthony G. Cohn, David C. H...
It is difficult to apply machine learning to new domains because often we lack labeled problem instances. In this paper, we provide a solution to this problem that leverages domai...
Abstract. In this paper, the Ssair (Semi-Supervised Active Image Retrieval) approach, which attempts to exploit unlabeled data to improve the performance of content-based image ret...
Analyzing videos of human activities involves not only
recognizing actions (typically based on their appearances),
but also determining the story/plot of the video. The storyline...
Abhinav Gupta (University of Maryland), Praveen Sr...