BioVL2: An Egocentric Biochemical Video-and-Language Dataset
-
- Nishimura Taichi
- Graduate School of Informatics, Kyoto University
-
- Sakoda Kojiro
- Graduate School of Informatics, Kyoto University
-
- Ushiku Atsushi
- Graduate School of Informatics, Kyoto University
-
- Hashimoto Atsushi
- OMRON SINIC X Corporation
-
- Okuda Natsuko
- Department of Physiology, Division of Life Sciences, Faculty of Medicine, Osaka Medical College
-
- Ono Fumihito
- Department of Physiology, Division of Life Sciences, Faculty of Medicine, Osaka Medical College
-
- Kameko Hirotaka
- Academic Center for Computing and Media Studies, Kyoto University
-
- Mori Shinsuke
- Academic Center for Computing and Media Studies, Kyoto University
Bibliographic Information
- Other Title
-
- BioVL2データセット:生化学分野における一人称視点の実験映像への言語アノテーション
Abstract
<p> In this study, we propose an egocentric biochemical video-and-language dataset called BioVL2 comprising eight videos for each of four experiments, with a total duration of 2.5 hours for all 32 samples. Each video corresponds to a protocol and two types of linguistic annotations are provided: (1) video-and-text alignment and (2) bounding boxes linked to objects in the protocol. As an application of the BioVL2 dataset, we consider the task of generating a protocol from an experimental video. Our experimental results show that the proposed system can generate better protocols than a weak baseline designed to output objects appearing in the video frames. The BioVL2 dataset will be released for research purposes only.</p>
Journal
-
- Journal of Natural Language Processing
-
Journal of Natural Language Processing 29 (4), 1106-1137, 2022
The Association for Natural Language Processing
- Tweet
Details 詳細情報について
-
- CRID
- 1390012954685727360
-
- ISSN
- 21858314
- 13407619
-
- HANDLE
- 2433/284969
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- IRDB
- Crossref
- KAKEN
-
- Abstract License Flag
- Disallowed