GTM-UVigo Systems for Person Discovery Task at MediaEval 2015
Paula Lopez‐Otero, Rosalía Barros, Laura Docío-Fernández, Elisardo González-Agulla, José Luis Alba‐Castro, Carmén García Mateo · MediaEval · 2015
In this paper, we present the systems developed by GTMUVigo team for the Multimedia Person Discovery in Broadcast TV task at MediaEval 2015. The systems propose two different strategies for person discovery in audio through speaker diarization (one based on an online clustering strategy with error correction using OCR information and the other based on agglomerative hierarchical clustering) as well as intrashot and intershot strategies for face clustering.