A two-level fine-tuned LVLM pipeline generates stylized football captions, claiming improved F1 and BERT scores over zero-shot and directly fine-tuned models, but the F1 evidence is absent and evaluation is limited to one event.
A survey of large language models for healthcare: from data, technology, and applications to accountability and ethics, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
REJECT 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Large VLM-based Stylized Sports Captioning
A two-level fine-tuned LVLM pipeline generates stylized football captions, claiming improved F1 and BERT scores over zero-shot and directly fine-tuned models, but the F1 evidence is absent and evaluation is limited to one event.