Learning a good ranking function plays a key role for many applications including the task of (multimedia) information retrieval. While there are a few rank learning methods availa...
Abstract. Bag-of-words representation with visual keypoints has recently emerged as an attractive approach for video search. In this paper, we study the degree of improvement when ...
The Carnegie Mellon University Informedia group has enjoyed consistent success with TRECVID interactive search using traditional storyboard interfaces for shot-based retrieval. Fo...
The objective of this paper is classifying images by the object categories they contain, for example motorbikes or dolphins. There are three areas of novelty. First, we introduce ...
We propose to incorporate hundreds of pre-trained concept detectors to provide contextual information for improving the performance of multimodal video search. The approach takes ...