@article{exploitingmultimodalspatialtemporal, title = {Exploiting Multimodal Spatial-temporal Patterns for Video Object Tracking}, author = {Xiantao Hu and Ying Tai and Xu Zhao and Chen Zhao and Zhenyu Zhang and Jun Li and Bineng Zhong and Jian Yang}, year = {2024}, eprint = {2412.15691}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.15691v1}, }