A new multimodal benchmark for predicting implicit ingredients in procedural cooking videos, with a fine-tuned model that outperforms GPT-4o by 14.7-17% relative F1.
add flour and spices in a bowl and mix
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Predicting Implicit Arguments in Procedural Video Instructions
A new multimodal benchmark for predicting implicit ingredients in procedural cooking videos, with a fine-tuned model that outperforms GPT-4o by 14.7-17% relative F1.