Video Caption Dataset for Describing Human Actions in Japanese
This provides a domain-specific resource for Japanese video captioning, addressing a gap in available datasets, but it is incremental as it adapts existing approaches to a new language.
The authors tackled the lack of a Japanese video caption dataset for human actions by constructing a large-scale dataset with 79,822 videos and 399,233 captions, and they evaluated two caption generation methods to establish benchmark results.
In recent years, automatic video caption generation has attracted considerable attention. This paper focuses on the generation of Japanese captions for describing human actions. While most currently available video caption datasets have been constructed for English, there is no equivalent Japanese dataset. To address this, we constructed a large-scale Japanese video caption dataset consisting of 79,822 videos and 399,233 captions. Each caption in our dataset describes a video in the form of "who does what and where." To describe human actions, it is important to identify the details of a person, place, and action. Indeed, when we describe human actions, we usually mention the scene, person, and action. In our experiments, we evaluated two caption generation methods to obtain benchmark results. Further, we investigated whether those generation methods could specify "who does what and where."