Rao, V. R., M. I. Khalil, H. Li, P. Dai, and J. Lu. “Decompose the Sounds and Pixels, Recompose the Events”. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, no. 2, June 2022, pp. 2144-52, doi:10.1609/aaai.v36i2.20111.