Search Results for author: Xavier Bost

Found 14 papers, 4 papers with code

Improved optimization strategies for deep Multi-Task Networks

no code implementations21 Sep 2021 Lucas Pascal, Pietro Michiardi, Xavier Bost, Benoit Huet, Maria A. Zuluaga

In Multi-Task Learning (MTL), it is a common practice to train multi-task networks by optimizing an objective function, which is a weighted average of the task-specific objective functions.

Computational Efficiency Multi-Task Learning

Maximum Roaming Multi-Task Learning

1 code implementation17 Jun 2020 Lucas Pascal, Pietro Michiardi, Xavier Bost, Benoit Huet, Maria A. Zuluaga

Multi-task learning has gained popularity due to the advantages it provides with respect to resource usage and performance.

Inductive Bias Multi-Task Learning

Serial Speakers: a Dataset of TV Series

1 code implementation LREC 2020 Xavier Bost, Vincent Labatut, Georges Linares

For over a decade, TV series have been drawing increasing interest, both from the audience and from various academic fields.

Retrieval

Remembering Winter Was Coming: Character-Oriented Video Summaries of TV Series

no code implementations5 Sep 2019 Xavier Bost, Serigne Gueye, Vincent Labatut, Martha Larson, Georges Linarès, Damien Malinas, Raphaël Roth

In this paper, we tackle plot modeling by considering the social network of interactions between the characters involved in the narrative: substantial, durable changes in a major character's social environment suggest a new development relevant for the summary.

Extraction and Analysis of Fictional Character Networks: A Survey

1 code implementation5 Jul 2019 Vincent Labatut, Xavier Bost

We first describe the extraction process in a generic way, and explain how its constituting steps are implemented in practice, depending on the medium of the narrative, the goal of the network analysis, and other factors.

Descriptive Information Retrieval +2

Multiple topic identification in telephone conversations

no code implementations21 Dec 2018 Xavier Bost, Marc El Bèze, Renato de Mori

Furthermore, using the theme skeleton of a conversation from which thematic densities are derived, it will be possible to extract components of an automatic conversation report to be used for improving the service performance.

Document Classification

Audiovisual speaker diarization of TV series

no code implementations18 Dec 2018 Xavier Bost, Georges Linarès, Serigne Gueye

Speaker diarization may be difficult to achieve when applied to narrative films, where speakers usually talk in adverse acoustic conditions: background music, sound effects, wide variations in intonation may hide the inter-speaker variability and make audio-based speaker diarization approaches error prone.

speaker-diarization Speaker Diarization

Constrained speaker diarization of TV series based on visual patterns

no code implementations18 Dec 2018 Xavier Bost, Georges Linares

Speaker diarization, usually denoted as the ''who spoke when'' task, turns out to be particularly challenging when applied to fictional films, where many characters talk in various acoustic conditions (background music, sound effects...).

Clustering speaker-diarization +1

D{é}tection de locuteurs dans les s{é}ries TV

no code implementations18 Dec 2018 Xavier Bost, Georges Linares

Speaker diarization of audio streams turns out to be particularly challenging when applied to fictional films, where many characters talk in various acoustic conditions (background music, sound effects, variations in intonation...).

Clustering speaker-diarization +1

Systèmes du LIA à DEFT'13

no code implementations21 Feb 2017 Xavier Bost, Ilaria Brunetti, Luis Adrián Cabrera-Diego, Jean-Valère Cossu, Andréa Linhares, Mohamed Morchid, Juan-Manuel Torres-Moreno, Marc El-Bèze, Richard Dufour

The 2013 D\'efi de Fouille de Textes (DEFT) campaign is interested in two types of language analysis tasks, the document classification and the information extraction in the specialized domain of cuisine recipes.

Document Classification General Classification

Narrative Smoothing: Dynamic Conversational Network for the Analysis of TV Series Plots

1 code implementation25 Feb 2016 Xavier Bost, Vincent Labatut, Serigne Gueye, Georges Linarès

In order to assess our method, we apply it to a new corpus of 3 popular TV series, and compare it to both standard approaches.

Cannot find the paper you are looking for? You can Submit a new open access paper.