Putting Captions to the Test: Evaluating Video Caption Quality through Multiple-Choice Question Answering

Evaluating video captioning remains a critical challenge for Visual Large Language Models (VLLMs). Existing metrics primarily rely on matching generated text against ground-truth references. This paradigm suffers from the “one-to-many” nature of video description, where high-quality captions are often penalized for lexical mismatches or valid shifts in visual focus. Furthermore, such assessments are typically one-dimensional, failing to provide a fine-grained analysis of caption quality. To address this, we redefine caption quality via information fidelity: A caption must maximize the coverage of salient visual information while ensuring strict factuality. We introduce CapQuiz, a novel reference-free benchmark that assesses captions based on their utility in answering human-verified, fine-grained, multiple-choice questions derived from the video. CapQuiz features a hierarchical taxonomy of 10 question types (spanning Descriptive and Inferential categories) across 24 diverse video domains. We further formulate CapF1, a composite metric that synthesizes CapP (measuring factuality) and CapR (measuring coverage). Extensive experiments demonstrate that CapQuiz correlates significantly better with human judgments than existing metrics and offers interpretable insights into model performance.

Related readings and updates.

Image captioning is one of the most fundamental tasks in computer vision. Owing to its open-ended nature, it has received significant attention in the era of multimodal large language models (MLLMs). In pursuit of ever more detailed and accurate captions, recent work has increasingly turned to reinforcement learning (RL). However, existing captioning-RL methods and evaluation metrics often emphasize a narrow notion of caption quality, inducing…

Recent advancements in multimodal models highlight the value of rewritten captions for improving performance, yet key challenges remain. Notably, the role of synthetic captions and their interaction with original web-crawled AltTexts in pre-training is still unclear. Additionally, different multimodal foundation models may have distinct preferences for specific caption formats while the efforts of studying the optimal captions for each foundation…