The REPERE challenge: finding people in a multimodal context
نویسندگان
چکیده
The REPERE Challenge aims to support research on people recognition in multimodal conditions. To assess the technology progress, annual evaluation campaigns will be organized from 2012 to 2014. In this context, the REPERE corpus, a French video corpus with multimodal annotation, has been developed. The systems which participated in the dry run had to answer the following questions : Who is speaking ? Who is present in the video ? What names are cited ? What names are displayed ? The first results obtained during a dry run show that significant progress are quite possible. The challenge is to combine the various information coming from the speech and the images.
منابع مشابه
REPERE : premiers résultats d'un défi autour de la reconnaissance multimodale des personnes (REPERE : preliminary results of a multimodal person recognition challenge) [in French]
REPERE : preliminary results of a multimodal person recognition challenge The REPERE Challenge aims at supporting researches on people recognition in multimodal conditions. To estimate the technology progress, annual evaluation campaigns on multimodal recognition of people in videos will be organized from 2012 to 2014. In this context, the REPERE corpus, a French videos corpus with multimodal a...
متن کاملThe REPERE Corpus : a multimodal corpus for person recognition
The REPERE Challenge aims to support research on people recognition in multimodal conditions. To assess the technology progression, annual evaluation campaigns will be organized from 2012 to 2014. In this context, the REPERE corpus, a French videos corpus with multimodal annotation, has been developed. This paper presents datasets collected for the dry run test that took place at the beginning ...
متن کاملThe second official REPERE evaluation
The REPERE Challenge aims at supporting research on people recognition in multimodal conditions. Following a 2012 dry-run [1] and a first official campaign [2], the second official evaluation of systems has been conducted at the beginning of 2014. To both help system development and assess the technology progress a specific corpus has been developed. It current totals 60 hours of video with mul...
متن کاملThe First Official REPERE Evaluation
The REPERE Challenge aims to support research on people recognition in multimodal conditions. Following a 2012 dryrun [1], the first official evaluation of systems has been conducted at the beginning of 2013. To both help system development and assess the technology progress a specific corpus is developed. It current totals at 30 hours of video with multimodal annotations. The systems have to a...
متن کاملAnalysis of i-vector framework for speaker identification in TV-shows
Inspired from the Joint Factor Analysis, the I-vector-based analysis has become the most popular and state-of-the-art framework for the speaker verification task. Mainly applied within the NIST/SRE evaluation campaigns, many studies have been proposed to improve more and more performance of speaker verification systems. Nevertheless, while the i-vector framework has been used in other speech pr...
متن کامل