Li, Jinxuan, et al. “TubeRMC: Tube-Conditioned Reconstruction With Mutual Constraints for Weakly-Supervised Spatio-Temporal Video Grounding”. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 40, no. 8, Mar. 2026, pp. 6253-61, doi:10.1609/aaai.v40i8.37551.