Abstract. In this paper we introduce a new approach aimed at solving the problem of image retrieval from text queries. We propose to estimate the word relevance of an image using a...
The automatic transcription of broadcast news and meetings involves the segmentation, identification and tracking of speaker turns during each session, which is known as speaker di...
The recognition of transitive, goal-directed actions requires a sensible balance between the representation of specific shape details of effector and goal object and robustness w...
We tackle the problem of object recognition using a Bayesian approach. A marked point process [1] is used as a prior model for the (unknown number of) objects. A sample is generat...
This paper describes an efficient approach to image annotation. It ranked first on the recent scene categorization track of the ImagEVAL1 benchmark. We show how homogeneous globa...