mhamilton723/DenseAV

@misc{hamilton2024separating,
      title={Separating the "Chirp" from the "Chat": Self-supervised Visual Grounding of Sound and Language}, 
      author={Mark Hamilton and Andrew Zisserman and John R. Hershey and William T. Freeman},
      year={2024},
      eprint={2406.05629},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}