Computer Vision for Audio-Visual Media


Improving Speaker Turn Embedding by Crossmodal Transfer Learning From Face Embedding
Nam Le,
Jean-Marc Odobez
[pdf] [arXiv]
[bibtex]
@InProceedings{Le_2017_ICCV_Workshops,
author = {Le, Nam and Odobez, Jean-Marc},
title = {Improving Speaker Turn Embedding by Crossmodal Transfer Learning From Face Embedding},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2017}
}

Unsupervised Cross-Modal Deep-Model Adaptation for Audio-Visual Re-Identification With Wearable Cameras
Alessio Brutti,
Andrea Cavallaro
[pdf]
[bibtex]
@InProceedings{Brutti_2017_ICCV_Workshops,
author = {Brutti, Alessio and Cavallaro, Andrea},
title = {Unsupervised Cross-Modal Deep-Model Adaptation for Audio-Visual Re-Identification With Wearable Cameras},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2017}
}

Exploiting the Complementarity of Audio and Visual Data in Multi-Speaker Tracking
Yutong Ban,
Laurent Girin,
Xavier Alameda-Pineda,
Radu Horaud
[pdf]
[bibtex]
@InProceedings{Ban_2017_ICCV_Workshops,
author = {Ban, Yutong and Girin, Laurent and Alameda-Pineda, Xavier and Horaud, Radu},
title = {Exploiting the Complementarity of Audio and Visual Data in Multi-Speaker Tracking},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2017}
}

Improved Speech Reconstruction From Silent Video
Ariel Ephrat,
Tavi Halperin,
Shmuel Peleg
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ephrat_2017_ICCV_Workshops,
author = {Ephrat, Ariel and Halperin, Tavi and Peleg, Shmuel},
title = {Improved Speech Reconstruction From Silent Video},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2017}
}

Visual Music Transcription of Clarinet Video Recordings Trained With Audio-Based Labelled Data
Pablo Zinemanas,
Pablo Arias,
Gloria Haro,
Emilia Gomez
[pdf]
[bibtex]
@InProceedings{Zinemanas_2017_ICCV_Workshops,
author = {Zinemanas, Pablo and Arias, Pablo and Haro, Gloria and Gomez, Emilia},
title = {Visual Music Transcription of Clarinet Video Recordings Trained With Audio-Based Labelled Data},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2017}
}