@misc{ma2024storynizorconsistentstorygeneration,
title={Storynizor: Consistent Story Generation via Inter-Frame Synchronized and Shuffled ID Injection},
author={Yuhang Ma and Wenting Xu and Chaoyi Zhao and Keqiang Sun and Qinfeng Jin and Zeng Zhao and Changjie Fan and Zhipeng Hu},
year={2024},
eprint={2409.19624},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2409.19624},
}
@misc{ma2024characteradapterpromptguidedregioncontrol,
title={Character-Adapter: Prompt-Guided Region Control for High-Fidelity Character Customization},
author={Yuhang Ma and Wenting Xu and Jiji Tang and Qinfeng Jin and Rongsheng Zhang and Zeng Zhao and Changjie Fan and Zhipeng Hu},
year={2024},
eprint={2406.16537},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2406.16537},
}
@misc{liu2024llm4genleveragingsemanticrepresentation,
title={LLM4GEN: Leveraging Semantic Representation of LLMs for Text-to-Image Generation},
author={Mushui Liu and Yuhang Ma and Xinfeng Zhang and Yang Zhen and Zeng Zhao and Zhipeng Hu and Bai Liu and Changjie Fan},
year={2024},
eprint={2407.00737},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2407.00737},
}
@inproceedings{tang2022you,
title={You can even annotate text with voice: Transcription-only-supervised text spotting},
author={Tang, Jingqun and Qiao, Su and Cui, Benlei and Ma, Yuhang and Zhang, Sheng and Kanoulas, Dimitrios},
booktitle={Proceedings of the 30th ACM International Conference on Multimedia},
pages={4154--4163},
year={2022}
}