Visual Recipe Flow: A Dataset for Learning Visual State Changes of Objects with Recipe Flows
-
- Shirai Keisuke
- Graduate School of Informatics, Kyoto University
-
- Hashimoto Atsushi
- OMRON SINIC X Corporation
-
- Nishimura Taichi
- Graduate School of Informatics, Kyoto University
-
- Kameko Hirotaka
- Academic Center for Media Studies, Kyoto University
-
- Kurita Shuhei
- RIKEN AIP, JST PRESTO
-
- Mori Shinsuke
- Academic Center for Media Studies, Kyoto University
Bibliographic Information
- Other Title
-
- 調理動作後の物体の視覚的状態予測を目指した Visual Recipe Flow データセットの構築と評価
Description
<p>We present a new multimodal dataset called Visual Recipe Flow, which enables us to learn each cooking action result in a recipe text. The dataset consists of object state changes and the workflow of the recipe text. The state change is represented as an image pair, while the workflow is represented as a recipe flow graph (r-FG). We explain the data collection and annotation procedure and evaluate the dataset by measuring the inter-annotator agreement. Finally, we investigate the importance of each annotation component by conducting multi-modal information retrieval experiments. </p>
Journal
-
- Journal of Natural Language Processing
-
Journal of Natural Language Processing 30 (3), 1042-1060, 2023
The Association for Natural Language Processing
- Tweet
Keywords
Details 詳細情報について
-
- CRID
- 1390015984923647104
-
- ISSN
- 21858314
- 13407619
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- Crossref
-
- Abstract License Flag
- Disallowed