@article{towardslongformspatiotemporalvideoground, title = {Towards Long-Form Spatio-Temporal Video Grounding}, author = {Xin Gu and Bing Fan and Jiali Yao and Zhipeng Zhang and Yan Huang and Cheng Han and Heng Fan and Libo Zhang}, year = {2026}, eprint = {2602.23294}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.23294}, }