ActivityForensics is the first large-scale benchmark for temporally localizing activity-level forgeries in videos, paired with a diffusion-based baseline called TADiff.
A survey on video dif- fusion models.ACM Computing Surveys, 57(2):1–42
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
LocalDPO creates localized preference pairs from real videos by applying random spatio-temporal masks and restoring masked regions with the frozen base model, then applies region-restricted DPO loss to improve fidelity and coherence in video diffusion models.
citing papers explorer
-
ActivityForensics: A Comprehensive Benchmark for Localizing Manipulated Activity in Videos
ActivityForensics is the first large-scale benchmark for temporally localizing activity-level forgeries in videos, paired with a diffusion-based baseline called TADiff.
-
Mind the Generative Details: Direct Localized Detail Preference Optimization for Video Diffusion Models
LocalDPO creates localized preference pairs from real videos by applying random spatio-temporal masks and restoring masked regions with the frozen base model, then applies region-restricted DPO loss to improve fidelity and coherence in video diffusion models.