KDD 2026ADS Track

A Multi-Stage Structural Captioning Framework for Enhancing Chinese Image-to-Video Generation in Baidu.

Lei Shen, Zhipeng Jin, Xiawei Li, Wen Tao, Shiyuan Li, Yi Yang 0031, Cong Han 0002, Shuanglong Li, Zhongmin Cai, Lin Liu

PDF 由论文原始站点提供，PaperCompass 不保存论文文件。DOI 10.1145/3770854.3783931 ↗

摘要

该来源暂未提供摘要。