A presentation of the REPERE challenge

2014 12th International Workshop on Content-Based Multimedia Indexing (CBMI)

et al. 2014

Abstract-Our goal is to automatically identify people in TV news and debates without any predefined dictionary of people. In this paper, we focus on the problem of person identification beyond face authentication in order to improve the identification results and not only where the face is detectable. We propose to use automatic scene analysis as features for people identification. We exploit two features: scene classification (studio and report) and camera identification. Then, people are identified by propagation strategies of overlaid names (OCR results) and speakers to scene classes and specific camera shots. Experiments performed on the REPERE corpus show improvement of face identification using scene understanding features (+13.9% of Fmeasure compared to the baseline).

“…This work was conducted as part of the REPERE evaluation campaign [12]. The main purpose of the challenge is to identify people in TV news and debates.…”

Section: Motivationmentioning

confidence: 99%

Scene understanding for identifying persons in TV shows: Beyond face authentication

Rouvier

2014 12th International Workshop on Content-Based Multimedia Indexing (CBMI)

et al. 2014

“…This step is the focus of our paper. Figure 1 illustrates that process on a debate video from the REPERE 1 corpus [6].…”

Section: Introductionmentioning

confidence: 99%

Unsupervised face identification in TV content using audio-visual sources

2013 11th International Workshop on Content-Based Multimedia Indexing (CBMI)

Charlet

et al. 2013

Our goal is to automatically identify faces in TV content without pre-defined dictionary of identities. Most of methods are based on identity detection (from OCR and ASR) and require a propagation strategy based on visual clusterings. In TV content, people appear with many variation making the clustering very difficult. In this case, identifying speakers can be a reliable link to identify faces. In this work, we propose to combine reliable unsupervised face and speaker identification systems through talking-faces detection in order to improve face identification results. First, OCR and ASR results are combined to extract locally the identities. Then, the reliable visual associations are used to propagate those identities locally. The reliable identified faces are used as unsupervised models to identify similar faces. Finally speaker identities are propagated to the faces in case of lip activity detection. Experiments performed on the REPERE database show an improvement of the recall of +5% compared to the baseline, without degrading the precision.

“…We used the TV recording corpus "phase1 train" from the REPERE Challenge [15]: 135 videos from LCP and BFMTV channels. It consists of 8624 annotated keyframes (about 1 every 10s).…”

Section: Corpusmentioning

confidence: 99%

Multiple-view constrained clustering for unsupervised face identification in TV-broadcast

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Charlet

et al. 2014

Our goal is to automatically identify faces in TV broadcast without a pre-defined dictionary of identities. Most methods are based on identity detection (from OCR and ASR) and require a propagation strategy based on visual clustering. In TV content, people appear with many variations making the clustering difficult. In this case, speaker clustering can be a reliable link for face clustering. We propose in this paper to build automatically an incomplete speaker-face mapping based on local evidence of OCR and Lip activity links. Then, we propose schemes of speaker constraints propagation to the face constrained-clustering problem. Experiments performed on the REPERE corpus show an improvement of face identification by propagating names to face clusters (+3.7% F-measure compared to the baseline).