Zobrazeno 1 - 10
of 53
pro vyhledávání: '"Bost, Xavier"'
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. Although the computational advantages of this strategy are c
Externí odkaz:
http://arxiv.org/abs/2109.11678
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence: 35(10), 9331-9341 (2021)
Multi-task learning has gained popularity due to the advantages it provides with respect to resource usage and performance. Nonetheless, the joint optimization of parameters with respect to multiple tasks remains an active research topic. Sub-partiti
Externí odkaz:
http://arxiv.org/abs/2006.09762
Publikováno v:
12th International Conference on Language Resources and Evaluation (LREC 2020), p.4256-4264, May 2020, Marseille, France
For over a decade, TV series have been drawing increasing interest, both from the audience and from various academic fields. But while most viewers are hooked on the continuous plots of TV serials, the few annotated datasets available to researchers
Externí odkaz:
http://arxiv.org/abs/2002.06923
In recent years, representation learning approaches have disrupted many multimedia computing tasks. Among those approaches, deep convolutional neural networks (CNNs) have notably reached human level expertise on some constrained image classification
Externí odkaz:
http://arxiv.org/abs/1909.12916
Autor:
Bost, Xavier, Gueye, Serigne, Labatut, Vincent, Larson, Martha, Linarès, Georges, Malinas, Damien, Roth, Raphaël
Publikováno v:
Multimedia Tools and Applications, Springer, 2019, 78(24):35373-35399
Today's popular TV series tend to develop continuous, complex plots spanning several seasons, but are often viewed in controlled and discontinuous conditions. Consequently, most viewers need to be re-immersed in the story before watching a new season
Externí odkaz:
http://arxiv.org/abs/1909.02423
Autor:
Labatut, Vincent, Bost, Xavier
Publikováno v:
ACM Computing Surveys, Association for Computing Machinery, 2019, 52 (5), pp.89
A character network is a graph extracted from a narrative, in which vertices represent characters and edges correspond to interactions between them. A number of narrative-related problems can be addressed automatically through the analysis of charact
Externí odkaz:
http://arxiv.org/abs/1907.02704
Deep learning is at the core of recent spoken language understanding (SLU) related tasks. More precisely, deep neural networks (DNNs) drastically increased the performances of SLU systems, and numerous architectures have been proposed. In the real-li
Externí odkaz:
http://arxiv.org/abs/1905.01957
Publikováno v:
Interspeech, Aug 2013, Lyon, France
This paper deals with the automatic analysis of conversations between a customer and an agent in a call centre of a customer care service. The purpose of the analysis is to hypothesize themes about problems and complaints discussed in the conversatio
Externí odkaz:
http://arxiv.org/abs/1812.09321
Publikováno v:
2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Apr 2015, Brisbane, Australia. IEEE, pp.4799-4803, 2015
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 mak
Externí odkaz:
http://arxiv.org/abs/1812.07205
Autor:
Bost, Xavier, Linares, Georges
Publikováno v:
Coria 2015, Mar 2015, Paris, France
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...). Despite this acou
Externí odkaz:
http://arxiv.org/abs/1812.07200