Saved in:
Bibliographic Details
Main Authors: Matsuda, Ryosuke, Kudo, Keito, Yoshida, Haruto, Shimizu, Nobuyuki, Suzuki, Jun
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.29186
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911556411850752
author Matsuda, Ryosuke
Kudo, Keito
Yoshida, Haruto
Shimizu, Nobuyuki
Suzuki, Jun
author_facet Matsuda, Ryosuke
Kudo, Keito
Yoshida, Haruto
Shimizu, Nobuyuki
Suzuki, Jun
contents This paper proposes the synthetic long-video meta-evaluation (SLVMEval), a benchmark for meta-evaluating text-to-video (T2V) evaluation systems. The proposed SLVMEval benchmark focuses on assessing these systems on videos of up to 10,486 s (approximately 3 h). The benchmark targets a fundamental requirement, namely, whether the systems can accurately assess video quality in settings that are easy for humans to assess. We adopt a pairwise comparison-based meta-evaluation framework. Building on dense video-captioning datasets, we synthetically degrade source videos to create controlled "high-quality versus low-quality" pairs across 10 distinct aspects. Then, we employ crowdsourcing to filter and retain only those pairs in which the degradation is clearly perceptible, thereby establishing an effective final testbed. Using this testbed, we assess the reliability of existing evaluation systems in ranking these pairs. Experimental results demonstrate that human evaluators can identify the better long video with 84.7%-96.8% accuracy, and in nine of the 10 aspects, the accuracy of these systems falls short of human assessment, revealing weaknesses in text-to-long-video evaluation.
format Preprint
id arxiv_https___arxiv_org_abs_2603_29186
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SLVMEval: Synthetic Meta Evaluation Benchmark for Text-to-Long Video Generation
Matsuda, Ryosuke
Kudo, Keito
Yoshida, Haruto
Shimizu, Nobuyuki
Suzuki, Jun
Computer Vision and Pattern Recognition
Artificial Intelligence
This paper proposes the synthetic long-video meta-evaluation (SLVMEval), a benchmark for meta-evaluating text-to-video (T2V) evaluation systems. The proposed SLVMEval benchmark focuses on assessing these systems on videos of up to 10,486 s (approximately 3 h). The benchmark targets a fundamental requirement, namely, whether the systems can accurately assess video quality in settings that are easy for humans to assess. We adopt a pairwise comparison-based meta-evaluation framework. Building on dense video-captioning datasets, we synthetically degrade source videos to create controlled "high-quality versus low-quality" pairs across 10 distinct aspects. Then, we employ crowdsourcing to filter and retain only those pairs in which the degradation is clearly perceptible, thereby establishing an effective final testbed. Using this testbed, we assess the reliability of existing evaluation systems in ranking these pairs. Experimental results demonstrate that human evaluators can identify the better long video with 84.7%-96.8% accuracy, and in nine of the 10 aspects, the accuracy of these systems falls short of human assessment, revealing weaknesses in text-to-long-video evaluation.
title SLVMEval: Synthetic Meta Evaluation Benchmark for Text-to-Long Video Generation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2603.29186