A fine-tuned 3.3B video description model using DWT-VGG16-LDA keyframe sampling reports 29.2% higher validation scores than GPT-4o on a 1,315-clip NBA play-by-play subset.
NSVA Subset: Basketball Video -Text Dataset,
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
unclear 1representative citing papers
citing papers explorer
-
SV3.3B: A Sports Video Understanding Model for Action Recognition
A fine-tuned 3.3B video description model using DWT-VGG16-LDA keyframe sampling reports 29.2% higher validation scores than GPT-4o on a 1,315-clip NBA play-by-play subset.