Multimodal Person Discovery in Broadcast TV: lessons learned from MediaEval 2015

Abstract : We describe the " Multimodal Person Discovery in Broadcast TV " task of MediaEval 2015 benchmarking initiative. Participants were asked to return the names of people who can be both seen as well as heard in every shot of a collection of videos. The list of people was not known a priori and their names had to be discovered in an unsupervised way from media content using text overlay or speech transcripts. The task was evaluated using information retrieval metrics, based on a posteriori collaborative annotation of the test corpus. The first edition of the task gathered 9 teams which submitted 34 runs. This paper provides quantitative and qualitative comparisons of participants submissions. We also investigate why all systems failed for particular shots, paving the way for future promising research directions.
Document type :
Journal articles
Complete list of metadatas

Cited literature [58 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01690581
Contributor : Claude Barras <>
Submitted on : Tuesday, January 23, 2018 - 11:07:57 AM
Last modification on : Saturday, May 4, 2019 - 1:20:23 AM
Long-term archiving on : Thursday, May 24, 2018 - 11:05:19 AM

File

Poignant2017.pdf
Files produced by the author(s)

Identifiers

Citation

Johann Poignant, Hervé Bredin, Claude Barras. Multimodal Person Discovery in Broadcast TV: lessons learned from MediaEval 2015. Multimedia Tools and Applications, Springer Verlag, 2017, 76 (21), pp.22547 - 22567. ⟨10.1007/s11042-017-4730-x⟩. ⟨hal-01690581⟩

Share

Metrics

Record views

105

Files downloads

56