@conference{wang_contextual_2025, author = {Wang, Hanlin and Tong, Zhan and Zheng, Kecheng and Shen, Yujun and Wang, Limin}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, language = {en}, title = {Contextual AD narration with interleaved multimodal sequence}, url = {https://arxiv.org/abs/2403.12922}, year = {2025} }