Abstract. We present a discriminatively trained model for joint modelling of object class labels (e.g. “person”, “dog”, “chair”, etc.) and their visual attributes (e.g....
In this contribution we firstly review some approaches to recover the 3D shape of human figures and the related movements. Then we present an improved and reliable version of an e...
A musical piece typically has a repetitive structure. Analysis of this structure will be useful for music segmentation, indexing and thumbnailing. This paper presents an algorithm...
Although there are many quality domains in which ideas and concepts about quality are represented, these representations are often informal. The TOVE Quality Ontology is the forma...
The usefulness of a video database depends on whether the video of interest can be easily located. In this paper, we propose a video retrieval algorithm based on the integration o...