@conference {cBernal,
title = {Transcription-Enriched Joint Embeddings or Spoken Descriptions of Images and Videos},
booktitle = {CVPR 2020 Workshop on Egocentric Perception, Interaction and Computing},
year = {2020},
month = {06/2020},
publisher = {arXiv},
organization = {arXiv},
address = {Seattle, WA, USA},
abstract = {
In this work, we propose an effective approach for training unique embedding representations by combining three simultaneous modalities: image and spoken and textual narratives. The proposed methodology departs from a baseline system that spawns a embedding space trained with only spoken narratives and image cues. Our experiments on the EPIC-Kitchen and Places Audio Caption datasets show that introducing the human-generated textual transcriptions of the spoken narratives helps to the training procedure yielding to get better embedding representations. The triad speech, image and words allows for a better estimate of the point embedding and show an improving of the performance within tasks like image and speech retrieval,\ even when text third modality, text, is not present in the task.
},
author = {Oriol, Benet and Luque, J. and Diego, Ferran and Xavier Gir{\'o}-i-Nieto}
}
@article {aSalah08,
title = {Multimodal identification and localization of users in a smart environment},
journal = {Journal on Multimodal user interfaces},
volume = {2},
number = {2},
year = {2008},
pages = {75{\textendash}91},
issn = {1783-7677},
doi = {10.1007/s12193-008-0008-y},
url = {http://hdl.handle.net/2117/6326},
author = {Salah, A. and Morros, J.R. and Luque, J. and Segura, C. and Hernando, J. and Ambekar, O. and Schouten, B. and Pauwels, E.}
}
@conference {cLuque06a,
title = {Audio, Video and Multimodal Person Identification in a Smart Room},
booktitle = {CLEAR{\textquoteright}06 Evaluation Campaign and Workshop - Classification of Events, Activities and Relationships},
year = {2007},
pages = {258{\textendash}269},
isbn = {978-3-540-69567-7},
author = {Luque, J. and Morros, J.R. and Garde, A. and Anguita, J. and Farr{\'u}s, M. and Macho, D. and Marqu{\'e}s, F. and Mart{\'\i}nez, C. and Ver{\'o}nica Vilaplana and Hernando, J.}
}
@inbook {bLuque06,
title = {Audio, Video and Multimodal Person Identification in a Smart Room},
booktitle = {Lecture notes in computer science - Multimodal Technologies for Perception of Humans},
volume = {4122},
year = {2006},
pages = {258{\textendash}269},
issn = {0302-9743},
doi = {10.1007/978-3-540-69568-4_23},
author = {Luque, J. and Morros, J.R. and Garde, A. and Anguita, J. and Farr{\'u}s, M. and Macho, D. and Marqu{\'e}s, F. and Mart{\'\i}nez, C. and Ver{\'o}nica Vilaplana and Hernando, J.}
}
@conference {cLuque06,
title = {Multimodal Person Identification in a Smart Room},
booktitle = {IV Jornadas en Tecnolog{\'\i}a del Habla},
year = {2006},
pages = {327{\textendash}331},
isbn = {84-96214-82-6},
author = {Luque, J. and Morros, J.R. and Anguita, J. and Farr{\'u}s, M. and Macho, D. and Marqu{\'e}s, F. and Mart{\'\i}nez, C. and Ver{\'o}nica Vilaplana and Hernando, J.}
}