Audio-video fusion strategies for active speaker detection in meetings

Autor: Lionel Pibre, Francisco Madrigal, Cyrille Equoy, Frédéric Lerasle, Thomas Pellegrini, Julien Pinquier, Isabelle Ferrané

Publikováno v: Multimedia Tools and Applications
Multimedia Tools and Applications, 2022, 2022, pp.1-26. ⟨10.1007/s11042-022-13746-7⟩

International audience; Meetings are a common activity in professional contexts, and it remains challenging to endow vocal assistants with advanced functionalities to facilitate meeting management. In this context, a task like active speaker detectio

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::804d7ef69d7c32db6544c6cbecad9f0c

Audio-Video detection of the active speaker in meetings

Autor: Frédéric Lerasle, Isabelle Ferrané, Lionel Pibre, Francisco Madrigal

Publikováno v: IEEE 25th International Conference on Pattern Recognition (ICPR 2020)
IEEE 25th International Conference on Pattern Recognition (ICPR 2020), IAPR : International Association of Pattern Recognition, Jan 2021, Milan (virtual), Italy. ⟨10.1109/ICPR48806.2021.9412681⟩
ICPR

International audience; Meetings are a common activity that provide certain challenges when creating systems that assist them. Such is the case of the Speaker recognition, which can provide useful information for human interaction modeling, or human-

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c1828abea5c91a62275d64bb9d2b1623
https://hal.science/hal-03125600/file/ICPR.pdf

How to deal with multi-source data for tree detection based on deep learning

Autor: Mustapha Derras, Dino Lenco, Gérard Subsol, Lionel Pibre, Marc Chaumon

Publikováno v: GlobalSIP
5th IEEE Global Conference on Signal and Information Processing
GlobalSIP: Global Conference on Signal and Information Processing
GlobalSIP: Global Conference on Signal and Information Processing, Nov 2017, Montreal, Canada
5th IEEE Global Conference on Signal and Information Processing (GlobalSIP)
5th IEEE Global Conference on Signal and Information Processing (GlobalSIP), Nov 2017, Montreal, Canada. pp.1150-1154, ⟨10.1109/GlobalSIP.2017.8309141⟩

International audience; In the field of remote sensing, it is very common to use data from several sensors in order to make classification or seg- mentation. Most of the standard Remote Sensing analysis use machine learning methods based on image des

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::787615535b1cbaaf39a8c6e17792e0b5
https://doi.org/10.1109/globalsip.2017.8309141

Deep learning is a good steganalysis tool when embedding key is reused for different images, even if there is a cover source-mismatch

Autor: Marc Chaumont, Jérôme Pasquet, Dino Ienco, Lionel Pibre

Publikováno v: IS&T International Symposium on Electronic Imaging
EI: Electronic Imaging
EI: Electronic Imaging, Feb 2016, San Fransisco, United States
HAL
Media Watermarking, Security, and Forensics

Since the BOSS competition, in 2010, most steganalysis approaches use a learning methodology involving two steps: feature extraction, such as the Rich Models (RM), for the image representation, and use of the Ensemble Classifier (EC) for the learning

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eb0937b3a7c63cbd73300324f16f95e8
https://hal-lirmm.ccsd.cnrs.fr/lirmm-01227950