论文标题
分解生成网络，并具有配方生成的结构预测
Decomposing Generation Networks with Structure Prediction for Recipe Generation
论文作者
论文摘要
食物图像和成分的食谱生成是一项艰巨的任务，它需要从另一种方式中解释信息。与图像字幕任务不同，该任务通常有一个句子，烹饪说明包含多个句子并具有明显的结构。为了帮助该模型捕获食谱结构并避免缺少一些烹饪细节，我们提出了一个新颖的框架：用结构预测的分解生成网络（DGN），以获得更具结构化和完整的食谱生成输出。具体而言，我们将每个烹饪指令分为几个阶段，并为每个阶段分配不同的子基因生成器。我们的方法包括两个新颖的想法：（i）学习具有全球结构预测成分的配方结构，以及（ii）基于预测的结构在亚基因烯量输出组件中产生配方阶段。关于具有挑战性的大规模配方1M数据集的广泛实验验证了我们提出的模型的有效性，这改善了对最新结果的性能。
Recipe generation from food images and ingredients is a challenging task, which requires the interpretation of the information from another modality. Different from the image captioning task, where the captions usually have one sentence, cooking instructions contain multiple sentences and have obvious structures. To help the model capture the recipe structure and avoid missing some cooking details, we propose a novel framework: Decomposing Generation Networks (DGN) with structure prediction, to get more structured and complete recipe generation outputs. Specifically, we split each cooking instruction into several phases, and assign different sub-generators to each phase. Our approach includes two novel ideas: (i) learning the recipe structures with the global structure prediction component and (ii) producing recipe phases in the sub-generator output component based on the predicted structure. Extensive experiments on the challenging large-scale Recipe1M dataset validate the effectiveness of our proposed model, which improves the performance over the state-of-the-art results.
