Adaptive anchor detection using online trained audio/visual model

An anchor person is the hosting character in broadcast programs. Anchor segments in video often provide the landmarks for detecting the content boundaries so that it is important to identify such segments during automatic content-based multimedia indexing. Previous e orts are mostly focused on audio information (e.g. acoustic speaker models) or visual information (e.g. visual anchor model such as face) alone for anchor detection using either model based methods via o -line trained models or unsupervised clustering methods. The in exibility of the o -line model based approach (allows only xed target) and the increasing di culty in achieving detection reliability using clustering approach lead to a new approach proposed in this paper. The goal is to detect an arbitrary anchor in a given broadcast news program. The proposed approach exploits both audio and visual cues so that on-line acoustic and visual models for the anchor can be built dynamically during data processing. In addition to the capability of identifying any given anchor, the proposed method can also be used to enhance the performance by combining with the algorithm that detects a prede ned anchor. Preliminary experiment results are shown and discussed. It is demonstrated that this proposed new approach enables the exibility of detecting an arbitrary anchor without losing the performance.