Li, J. et al. 2026. TubeRMC: Tube-conditioned Reconstruction with Mutual Constraints for Weakly-supervised Spatio-Temporal Video Grounding. Proceedings of the AAAI Conference on Artificial Intelligence. 40, 8 (Mar. 2026), 6253–6261. DOI:https://doi.org/10.1609/aaai.v40i8.37551.