Towards large scale multimedia indexing: a case study on person discovery in broadcast news

Citació

  • Le N, Bredin H, Sargent G, India M, Lopez-Otero P, Barras B, Guinaudeau C, Gravier G, Barbosa da Fonseca G, Lyon Freire I, Patrocínio Z, Guimarães SJF, Martí G, Morros JR, Hernando J, Docio-Fernandez L, Garcia-Mateo C, Meignier S, Odobez JM. Towards large scale multimedia indexing: a case study on person discovery in broadcast news. In: Proceedings of the 15th International Workshop on Content-Based Multimedia Indexing (CBMI'17); 2017 Jun 19-21; Firenze, Italy. [New York]: ACM; 2017. Article No. 18. DOI: 10.1145/3095713.3095732

Enllaç permanent

Descripció

  • Resum

    The rapid growth of multimedia databases and the human interest in their peers make indices representing the location and identity of people in audio-visual documents essential for searching archives. Person discovery in the absence of prior identity knowledge requires accurate association of audio-visual cues and detected names. To this end, we present 3 different strategies to approach this problem: clustering-based naming, verification-based naming, and graph-based naming. Each of these strategies utilizes different recent advances in unsupervised face / speech representation, verification, and optimization. To have a better understanding of the approaches, this paper also provides a quantitative and qualitative comparative study of these approaches using the associated corpus of the Person Discovery challenge at MediaEval 2016. From the results of our experiments, we can observe the pros and cons of each approach, thus paving the way for future promising research directions.
  • Descripció

    Comunicació presentada a: the 15th International Workshop on Content-Based Multimedia Indexing (CBMI'17), celebrat a Florència, Itàlia, del 19 al 21 de juny de 2017
  • Mostra el registre complet