CAPability: A Comprehensive Visual Caption Benchmark for Evaluating Both Correctness and Thoroughness

TL;DR

CAPability introduces a comprehensive benchmark for evaluating visual captioning, assessing correctness and thoroughness across multiple views using human annotations, QA conversions, and new metrics to identify strengths and gaps in MLLMs.

Contribution

This work presents a novel multi-view benchmark with 11K annotated images and videos, introducing new metrics like extit{know but cannot tell} to evaluate captioning performance more holistically.

Findings

CAPability effectively evaluates caption correctness and thoroughness.

It reveals significant performance gaps in current MLLMs' captioning abilities.

The benchmark guides future improvements in multimodal captioning models.

Abstract

Visual captioning benchmarks have become outdated with the emergence of modern multimodal large language models (MLLMs), as the brief ground-truth sentences and traditional metrics fail to assess detailed captions effectively. While recent benchmarks attempt to address this by focusing on keyword extraction or object-centric evaluation, they remain limited to vague-view or object-view analyses and incomplete visual element coverage. In this paper, we introduce CAPability, a comprehensive multi-view benchmark for evaluating visual captioning across 12 dimensions spanning six critical views. We curate nearly 11K human-annotated images and videos with visual element annotations to evaluate the generated captions. CAPability stably assesses both the correctness and thoroughness of captions with \textit{precision} and \textit{hit} metrics. By converting annotations to QA pairs, we further introduce a heuristic metric, \textit{know but cannot tell} ($K\bar{T}$), indicating a significant performance gap between QA and caption capabilities. Our work provides a holistic analysis of MLLMs' captioning abilities, as we identify their strengths and weaknesses across various dimensions, guiding future research to enhance specific aspects of their capabilities.