@article{fedorishin_mohan_jawade_setlur_govindaraju_2022, 
  title={Hear The Flow: Optical Flow-Based Self-Supervised Visual Sound Source   Localization}, 
  abstractNote={Learning to localize the sound source in videos without explicit annotations
is a novel area of audio-visual research. Existing work in this area focuses on
creating attention maps to capture the correlation between the two modalities
to localize the source of the sound. In a video, oftentimes, the objects
exhibiting movement are the ones generating the sound. In this work, we capture
this characteristic by modeling the optical flow in a video as a prior to
better aid in localizing the sound source. We further demonstrate that the
addition of flow-based attention substantially improves visual sound source
localization. Finally, we benchmark our method on standard sound source
localization datasets and achieve state-of-the-art performance on the Soundnet
Flickr and VGG Sound Source datasets. Code:
https://github.com/denfed/heartheflow.}, 
  author={Fedorishin and Mohan and Jawade and Setlur and Govindaraju}, 
  year={2022}, 
  month={Nov}
  }