Retrieval-augmented-generation-enhanced Dense Video Caption for Human Indoor Activities: Disambiguating Caption Using Spatial Information Beyond Field of View Constraints
BLEU-3, METEOR, CIDEr, and Precision metrics, but shows a small decline in ROUGE-L and Recall metrics compared with GVL.These results demonstrate that our method effectively incorporates spatial information and reduces ambiguity for indoor human activity caption applications.
Authors
- Yugo Nakamura (ORCID: https://orcid.org/0000-0002-8834-5323)
- Yutaka Arakawa (ORCID: https://orcid.org/0000-0002-7156-9160)
- Bin Chen (ORCID: https://orcid.org/0000-0002-6708-4101)
- Shogo Fukushima (ORCID: https://orcid.org/0000-0001-9718-6646)
Institutions
- Kyushu University (JP)
Publication Details
- Journal
- Sensors and Materials
- Published
- 2024-10-28
- DOI
- https://doi.org/10.18494/sam5238
- Citations
- 1
- Primary Topic
- Multimodal Machine Learning Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.25