Rémi Auguste

Unsupervised face identification in TV content using audio-visual sources

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.

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

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).

Motion similarity measure between video sequences using multivariate time series modeling

The analysis and interpretation of video contents is an important component of modern vision applications such as surveillance, motion synthesis and web-based user interfaces. A requirement shared by these very different applications is the ability to learn statistical models of appearance and motion from a collection of videos, and then use them for recognizing actions or persons in a new video. Measuring the similarity and dissimilarity between video sequences is crucial in any video sequences analysis and decision-making process. Furthermore, many data analysis processes effectively deal with moving objects and need to compute the similarity between trajectories. In this paper, we propose a similarity measure for multivariate time series using the Euclidean distance based on Vector Autoregressive (VAR) models. The proposed approach allows us to identify and recognize actions of persons in video sequences. The performance of our methodology is tested on a real dataset.

Introducing FoxPersonTracks: A benchmark for person re-identification from TV broadcast shows

This paper introduces a novel person track dataset dedicated to person re-identification. The dataset is built from a set of real life TV shows broadcasted from BFMTV and LCP TV French channels, provided during the REPERE challenge. It contains a total of 4,604 persontracks (short video sequences featuring an individual with no background) from 266 persons. The dataset has been built from the REPERE dataset by following several automated processing and manual selection/filtering steps. It is meant to serve as a benchmark in person re-identification from images/videos. The dataset also provides re-identifications results using space-time histograms as a baseline, together with an evaluation tool in order to ease the comparison to other re-identification methods.