Introduction

The Micro-Action Analysis Grand Challenge focuses on computer vision and machine learning methods for automatic human behavior based on whole-body micro-action that is bound up with psychological and mental state and emotion state analysis. Micro-actions are spontaneous body movements that indicate a person's true feelings and potential intentions, yet recognizing, distinguishing, and understanding micro-actions are challenging because they are subtle and appear for milliseconds compared to normal actions. To address these challenges, we successfully organized the 1st Micro-Action Analysis Grand Challenge (MAC 2024@ACM MM 2024), attracting over 40 teams from 37 leading research institutions worldwide, demonstrating the growing interest in this emerging field. Building on this momentum, we are excited to announce the 2nd Micro-Action Analysis Grand Challenge (MAC 2025). 

This challenge aims to foster innovative research in this emerging domain and provide benchmark evaluations to stimulate new approaches for utilizing whole-body micro-actions in human behavior understanding. Ultimately, our goal is to promote technological advancements in deep psychological assessment and emotional state analysis, and to inspire interdisciplinary collaboration within the research community.

Datasets

To support the Micro-Actions Analysis Challenge (MAC 2025), we have collected two new spontaneous whole-body micro-action video datasets consisting of 52 action categories through psychological interviews.

Dataset Collection

• 205 volunteers, the proportion of males to females is close to 1:1, there is a relatively even age distribution

• Professional face-to-face psychological interviews

• Under the guidance of the Symptom Checklist 90 (SCL90) test (a comprehensive 90-item psychological assessment questionnaire)

• A high-resolution 1920×1080 camera to capture authentic and spontaneous micro-behaviors.

• To collect authentic spontaneous micro-actions, we aimed to minimize interference with the respondents’ bodily action expressions and capture as many varied and rich micro-actions as possible.

• To ensure participants' comfort and relaxation, they remained seated during the interview. 

Annotations of two datasets

• The Micro-Action-52 (MA-52) dataset consists of trimmed video samples with single micro-action (MA) annotations. The duration of these samples ranges from 1 second to 7 seconds, with an average duration of 1.9 seconds and a total span of 12.29 hours. During the annotation of the MA-52 dataset, our focus was on annotating the beginning and ending segments of a single micro-action occurrence, to avoid annotating multiple micro-action behaviors within the same time period. This approach ensures clarity and accuracy of the annotations, resulting in a consistent and reliable dataset. 

• The  Multi-label Micro-Action-52 (MMA-52) dataset includes video samples of multiple micro-actions (MMA) with overlapping and intersecting occurrences. The duration of these samples ranges from 5 seconds to 15 seconds, with an average duration of 10.61 seconds and a total duration of 30.44 hours. During the annotation process of the MMA-52 dataset, the edited video segments may contain partially unannotated content, but at least two micro-movements are annotated per video clip.

Challenges

MAC 2025 focuses on the recognition and detection of micro-action, this challenge aims to develop and benchmark models that are capable of human micro-action recognition (MAR) and multi-label micro-action detection (MMAD), in preparation for exploring the relationship between micro-actions and human emotions. 

Track 1: Micro-Action Recognition (MAR)

Micro-Action Recognition (MAR) aims to recognize and distinguish subtle body actions that typically occur in a brief instant. The MAR task is similar to conventional action recognition, as it involves using video instances as input and requires precise and efficient algorithms. However, it is uniquely complex due to the presence of low-amplitude fluctuations in gestures and postures.

Track 2: Multi-label Mirco-Action Detection (MMAD)

Considering the co-occurrence of human micro-actions, i.e., the same micro-action may be repeated in time and different micro-actions may occur at the same time, Multi-label Micro-Action Detection (MMAD) is necessary for a deeper understanding of human bodily behavior. Multi-label Micro-Action Detection (MMAD) refers to the task of identifying and localizing all micro-actions in a given uncut and densely annotated video, determining their corresponding start and end times, as well as their categories. This task takes an entire video as input and requires a model capable of accurately capturing both long-term and short-term action relationships to detect and locate multiple micro-actions. Designing a model for MMAD is more challenging due to the brief duration and small magnitude of micro-actions. 

News and Updates

• 14, July. 2025 Challenge is officially over! Final results can be found here.

• 9, July. 2025 Challenge ends. Please follow the instructions here to submit the code.

• 30, June. 2025 We released the test set.  [News!!!]

• 30, Mar. 2025 We released the Codalab links!

• 28, Feb. 2025 Our Grand Challenge is accepted for ACM MM 2025!