MEGC2026: Micro-Expression Grand Challenge on Visual Question Answering

2026-03-09

AI Summary

This work addresses the understanding of facial microexpressions under high-stakes scenarios where emotions are suppressed, introducing two novel tasks: Microexpression Video Question Answering (ME-VQA) and Microexpression Long Video Question Answering (ME-LVQA). It pioneers the application of the visual question answering (VQA) paradigm to microexpression analysis and extends it to long-duration video settings. By integrating multimodal large language models (MLLMs) with temporal modeling techniques, the approach enables fine-grained semantic reasoning about microexpressions and their cross-temporal associations. The project also establishes the first public benchmark platform and leaderboard dedicated to semantic question answering on microexpressions, advancing the field beyond basic recognition toward deeper semantic comprehension.

Technology Category

• Computer Vision: Video Understanding & Activity Analysis
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Question Answering

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Search and Retrieval-Augmented AI: Web question answering
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Facial micro-expressions (MEs) are involuntary movements of the face that occur spontaneously when a person experiences an emotion but attempts to suppress or repress the facial expression, typically found in a high-stakes environment. In recent years, substantial advancements have been made in the areas of ME recognition, spotting, and generation. The emergence of multimodal large language models (MLLMs) and large vision-language models (LVLMs) offers promising new avenues for enhancing ME analysis through their powerful multimodal reasoning capabilities. The ME grand challenge (MEGC) 2026 introduces two tasks that reflect these evolving research directions: (1) ME video question answering (ME-VQA), which explores ME understanding through visual question answering on relatively short video sequences, leveraging MLLMs or LVLMs to address diverse question types related to MEs; and (2) ME long-video question answering (ME-LVQA), which extends VQA to long-duration video sequences in realistic settings, requiring models to handle temporal reasoning and subtle micro-expression detection across extended time periods. All participating algorithms are required to submit their results on a public leaderboard. More details are available at https://megc2026.github.io.

Problem

• Micro-Expression
• Visual Question Answering
• Long Video
• Temporal Reasoning
• Multimodal Reasoning

Innovation

• micro-expression
• visual question answering
• multimodal large language models
• temporal reasoning
• long-video analysis