A transformer encoder-decoder plus an inference-time style conditioning module recommends transition sequences that match a target production style, evaluated on a new style-labeled video dataset.
Foreign Language Annals (2024)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
V-Trans4Style: Visual Transition Recommendation for Video Production Style Adaptation
A transformer encoder-decoder plus an inference-time style conditioning module recommends transition sequences that match a target production style, evaluated on a new style-labeled video dataset.