STEC: A Reference-Free Spatio-Temporal Entropy Coverage Metric for Evaluating Sampled Video Frames

TL;DR

STEC is a new, reference-free metric that evaluates the quality of sampled video frames by measuring their spatio-temporal information coverage, helping to improve video understanding tasks.

Contribution

We introduce STEC, a lightweight, non-reference metric that assesses sampled video frames based on spatial information, temporal coverage, and redundancy, filling a gap in evaluation methods.

Findings

STEC effectively differentiates various sampling strategies.

It reveals robustness patterns not captured by average performance.

STEC serves as a diagnostic tool for frame sampling quality.

Abstract

Frame sampling is a fundamental component in video understanding and video--language model pipelines, yet evaluating the quality of sampled frames remains challenging. Existing evaluation metrics primarily focus on perceptual quality or reconstruction fidelity, and are not designed to assess whether a set of sampled frames adequately captures informative and representative video content. We propose Spatio-Temporal Entropy Coverage (STEC), a simple and non-reference metric for evaluating the effectiveness of video frame sampling. STEC builds upon Spatio-Temporal Frame Entropy (STFE), which measures per-frame spatial information via entropy-based structural complexity, and evaluates sampled frames based on their temporal coverage and redundancy. By jointly modeling spatial information strength, temporal dispersion, and non-redundancy, STEC provides a principled and lightweight measure of sampling quality. Experiments on the MSR-VTT test-1k benchmark demonstrate that STEC clearly differentiates common sampling strategies, including random, uniform, and content-aware methods. We further show that STEC reveals robustness patterns across individual videos that are not captured by average performance alone, highlighting its practical value as a general-purpose evaluation tool for efficient video understanding. We emphasize that STEC is not designed to predict downstream task accuracy, but to provide a task-agnostic diagnostic signal for analyzing frame sampling behavior under constrained budgets.