MIRecipe: A Recipe Dataset for Stage-Aware Recognition of Changes in Appearance of Ingredients
MIRecipe: A Recipe Dataset for Stage-Aware Recognition of Changes in Appearance of Ingredients
复制标题
DOI：
10.1145/3469877.3490596
复制
发表时间：
2021-12
期刊：
影响因子：
--
通讯作者：
Yixin Zhang;Yoko Yamakata;Keishi Tajima
中科院分区：
文献类型：
--
作者：
Yixin Zhang;Yoko Yamakata;Keishi Tajima
在本文中，我们引入了一个新的食谱数据集MIRecipe （multimedia - teaching recipe）。它有每个烹饪步骤的文本和图像数据，而传统的食谱数据集只包含最终的菜肴图像，和/或仅包含某些步骤的图像。它由26,725个食谱组成，总共包括239,973个步骤。在与烹饪步骤相关的图像中对配料的识别提出了新的挑战：由于配料是在烹饪过程中加工的，同一种配料在烹饪的开始和结束阶段的外观是非常不同的。一般的物体识别方法，假设物体的外观不变，不能很好地识别这些物体。为了解决这个问题，我们提出了两种阶段感知技术：阶段智能模型学习，它为每个阶段训练一个单独的模型，以及阶段感知课程学习，它从开始阶段的训练数据开始，并继续到后期阶段。我们对数据集的实验表明，我们的方法比使用所有数据而不考虑阶段的模型获得了更高的精度。我们的数据集可以在我们的GitHub存储库中获得。
In this paper, we introduce a new recipe dataset MIRecipe (Multimedia-Instructional Recipe). It has both text and image data for every cooking step, while the conventional recipe datasets only contain final dish images, and/or images only for some of the steps. It consists of 26,725 recipes, which include 239,973 steps in total. The recognition of ingredients in images associated with cooking steps poses a new challenge: Since ingredients are processed during cooking, the appearance of the same ingredient is very different in the beginning and finishing stages of the cooking. The general object recognition methods, which assume the constant appearance of objects, do not perform well for such objects. To solve the problem, we propose two stage-aware techniques: stage-wise model learning, which trains a separate model for each stage, and stage-aware curriculum learning, which starts with the training data from the beginning stage and proceeds to the later stages. Our experiment with our dataset shows that our method achieves higher accuracy than the model trained using all the data without considering the stages. Our dataset is available at our GitHub repository.