ZHANG, Xiao-Yu; SHI, Haichao; LI, Changsheng; LI, Peng. Multi-Instance Multi-Label Action Recognition and Localization Based on Spatio-Temporal Pre-Trimming for Untrimmed Videos. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 34, n. 07, p. 12886–12893, 2020. DOI: 10.1609/aaai.v34i07.6986. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/6986. Acesso em: 25 may. 2026.