Introduces the MMTT dataset of 152k manipulated facial images with masks and text descriptions, plus the ForgeryTalker model that jointly outputs localization masks and explanatory text, reporting 59.3 CIDEr and 73.67 IoU.
Gen- face: A large-scale fine-grained face forgery bench- mark and cross appearance-edge learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Generating Attribution Reports for Manipulated Facial Images: A Dataset and Baseline
Introduces the MMTT dataset of 152k manipulated facial images with masks and text descriptions, plus the ForgeryTalker model that jointly outputs localization masks and explanatory text, reporting 59.3 CIDEr and 73.67 IoU.