A new dataset (FakeVE) and a benchmark model (MRGT) for generating natural-language explanations of why multimodal news videos are fake.
Measuring nominal scale agreement among many raters
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
-
Multimodal Fake News Video Explanation: Dataset, Analysis and Evaluation
A new dataset (FakeVE) and a benchmark model (MRGT) for generating natural-language explanations of why multimodal news videos are fake.