RefVQA uses a query-centered reference graph and graph-guided difference aggregation to improve AI-generated video quality assessment by incorporating inter-video comparisons.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
DVAR turns video authenticity detection into an iterative debate between a generative hypothesis agent and a natural mechanism agent, resolved via minimum description length and a knowledge base for better generalization than supervised detectors.
citing papers explorer
-
Comparison Drives Preference: Reference-Aware Modeling for AI-Generated Video Quality Assessment
RefVQA uses a query-centered reference graph and graph-guided difference aggregation to improve AI-generated video quality assessment by incorporating inter-video comparisons.
-
DVAR: Adversarial Multi-Agent Debate for Video Authenticity Detection
DVAR turns video authenticity detection into an iterative debate between a generative hypothesis agent and a natural mechanism agent, resolved via minimum description length and a knowledge base for better generalization than supervised detectors.