Sora Detector: A Unified Hallucination Detection for Large Text-to-Video Models

arXiv:2405.04180v1 Announce Type: new
Abstract: The rapid advancement in text-to-video (T2V) generative models has enabled the synthesis of high-fidelity video content guided by textual descriptions. Despite this significant progress, these models are often susceptible to hallucination, generating contents that contradict the input text, which poses a challenge to their reliability and practical deployment. To address this critical issue, we introduce the SoraDetector, a novel unified framework designed to detect hallucinations across diverse large T2V models, including the cutting-edge Sora model. …

abstract advancement arxiv challenge contents cs.lg detection fidelity generative generative models hallucination progress reliability sora synthesis text text-to-video textual type video