Audio-visual object localization and separation using low-rank and sparsity

@article{Pu2017AudiovisualOL,
  title={Audio-visual object localization and separation using low-rank and sparsity},
  author={Jie Pu and Yannis Panagakis and Stavros Petridis and Maja Pantic},
  journal={2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  year={2017},
  pages={2901-2905}
}
  • Jie Pu, Yannis Panagakis, +1 author Maja Pantic
  • Published in
    IEEE International Conference…
    2017
  • Computer Science
  • The ability to localize visual objects that are associated with an audio source and at the same time seperate the audio signal is a corner stone in several audio-visual signal processing applications. Past efforts usually focused on localizing only the visual objects, without audio separation abilities. Besides, they often rely computational expensive pre-processing steps to segment images pixels into object regions before applying localization approaches. We aim to address the problem of audio… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Citations

    Publications citing this paper.
    SHOWING 1-7 OF 7 CITATIONS

    Co-Separating Sounds of Visual Objects

    VIEW 6 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Learning to Separate Object Sounds by Watching Unlabeled Video

    VIEW 9 EXCERPTS
    CITES METHODS, BACKGROUND & RESULTS
    HIGHLY INFLUENCED

    Deep Audio-Visual Learning: A Survey

    VIEW 3 EXCERPTS
    CITES BACKGROUND & METHODS

    Self-supervised Audio-visual Co-segmentation

    VIEW 1 EXCERPT
    CITES METHODS

    2.5D Visual Sound

    VIEW 1 EXCERPT

    Audio-Visual Scene Analysis with Self-Supervised Multisensory Features

    VIEW 1 EXCERPT
    CITES METHODS

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 25 REFERENCES

    Multimodal Analysis for Identification and Segmentation of Moving-Sounding Objects

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Pixels that sound

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Robust Correlated and Individual Component Analysis

    Temporal Subspace Clustering for Human Motion Segmentation

    • Sheng Li, Kang Li, Yun Fu
    • Computer Science
    • 2015 IEEE International Conference on Computer Vision (ICCV)
    • 2015
    VIEW 1 EXCERPT

    What ’ s making that sound ? , ” in Proceedings of the 22 nd ACM international conference on Multimedia

    • Kai Li, Jun Ye, Kien A Hua
    • ACM
    • 2014

    What's Making that Sound?

    VIEW 2 EXCERPTS

    Active Subspace: Toward Scalable Low-Rank Learning

    Singing-voice separation from monaural recordings using robust principal component analysis

    VIEW 2 EXCERPTS