Cross-cultural documentary is coordinated in various cultural clusters, striving to reduce cultural barriers and maximize the meaning of the theme of the film. As the first documentary film in China to break the 100 million box office, "Twenty-Two" fully respects the main narrative rights of "comfort women" and mobilizes multi-modal resources. Reduce cultural discounts and convey the voice of the "comfort women" elderly. By integrating high-low context theory and visual grammar to construct a cross-context visual narrative model, it can be found that the multi-modal narrative strategy of Twenty-Two is developed around the common core of humanity, through the reproduction of meaning, Interactive meaning and composition of meaning and context interaction, assist cross-cultural audiences to understand the meaning, to achieve the purpose of multiple empathy.