Labeling objects in images is an essential prerequisite for many visual learning and recognition applications that depend on training data, such as image retrieval, object detecti...
In this paper, we propose and investigate a new user scenario for face annotation, in which users are allowed to multi-select a group of photographs and assign names to these phot...
Lei Zhang, Yuxiao Hu, Mingjing Li, Wei-Ying Ma, Ho...
Fusion of multimedia streams for enhanced performance is a critical problem for retrieval. However, fusion performance tends to easily overfit the hillclimb set used to learn fus...
In many applications, we find large video collections from different genres where the user is often only interested in one or two specific video genres. So, when users are queryin...
Abstract. In the pattern recognition context, objects can be represented as graphs with attributed nodes and edges involving their relations. Consequently, matching attributed grap...