@inproceedings{bao2024e3m, 
title={E3M: Zero-Shot Spatio-Temporal Video Grounding with Expectation-Maximization Multimodal Modulation}, 
author={Bao, Peijun and Shao, Zihao and Yang, Wenhan and Ng, Boon Poh and Kot, Alex C}, 
booktitle={European Conference on Computer Vision (ECCV)}, 
year={2024} 
}