Micro-Expression Spotting: A Benchmark

TL;DR

This paper introduces a standardized benchmark for micro-expression spotting, providing evaluation protocols, a multi-scale framework, and baseline results to advance research in this rapidly growing field.

Contribution

The paper establishes the first comprehensive benchmark for micro-expression spotting, including evaluation protocols, a multi-scale framework, and baseline results to standardize performance assessment.

Findings

Established a micro-expression spotting benchmark (MESB)

Developed a multi-scale evaluation framework

Provided baseline results for popular methods

Abstract

Micro-expressions are rapid and involuntary facial expressions, which indicate the suppressed or concealed emotions. Recently, the research on automatic micro-expression (ME) spotting obtains increasing attention. ME spotting is a crucial step prior to further ME analysis tasks. The spotting results can be used as important cues to assist many other human-oriented tasks and thus have many potential applications. In this paper, by investigating existing ME spotting methods, we recognize the immediacy of standardizing the performance evaluation of micro-expression spotting methods. To this end, we construct a micro-expression spotting benchmark (MESB). Firstly, we set up a sliding window based multi-scale evaluation framework. Secondly, we introduce a series of protocols. Thirdly, we also provide baseline results of popular methods. The MESB facilitates the research on ME spotting with fairer and more comprehensive evaluation and also enables to leverage the cutting-edge machine learning tools widely.