SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

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 through the lens of information fidelity: A caption must max

Read original source ↗ Open in workspace

recordType

paper

region

Global