VCapsBench: A Large-scale Fine-grained Benchmark for Video Caption Quality Evaluation

TL;DR

VCapsBench is a comprehensive large-scale benchmark designed to evaluate the fine-grained quality of video captions, emphasizing spatial-temporal details to improve text-to-video generation models.

Contribution

It introduces the first extensive fine-grained benchmark with detailed annotations and novel evaluation metrics for assessing video caption quality.

Findings

Benchmark includes 5,677 videos and 109,796 QA pairs across 21 dimensions.

Proposes three metrics: Accuracy, Inconsistency Rate, Coverage Rate.

Automated evaluation pipeline using large language models for caption verification.

Abstract

Video captions play a crucial role in text-to-video generation tasks, as their quality directly influences the semantic coherence and visual fidelity of the generated videos. Although large vision-language models (VLMs) have demonstrated significant potential in caption generation, existing benchmarks inadequately address fine-grained evaluation, particularly in capturing spatial-temporal details critical for video generation. To address this gap, we introduce the Fine-grained Video Caption Evaluation Benchmark (VCapsBench), the first large-scale fine-grained benchmark comprising 5,677 (5K+) videos and 109,796 (100K+) question-answer pairs. These QA-pairs are systematically annotated across 21 fine-grained dimensions (e.g., camera movement, and shot type) that are empirically proven critical for text-to-video generation. We further introduce three metrics (Accuracy (AR), Inconsistency Rate (IR), Coverage Rate (CR)), and an automated evaluation pipeline leveraging large language model (LLM) to verify caption quality via contrastive QA-pairs analysis. By providing actionable insights for caption optimization, our benchmark can advance the development of robust text-to-video models. The dataset and codes are available at website: https://github.com/GXYM/VCapsBench.