A New Multi-Domain Benchmark for Micro-Action Recognition and Detection

• URL: http://arxiv.org/abs/2606.14096v2
• Date: Tue, 16 Jun 2026 08:41:34 GMT
• Title: A New Multi-Domain Benchmark for Micro-Action Recognition and Detection
• Abstract summary: MMA-82 is a large-scale multi-domain extension of the MA-52 benchmark for micro-action analysis.<n>MMA-82 is a comprehensive and challenging benchmark for realistic micro-action analysis and a valuable resource for human-centered AI.
• Score: 48.34038271380391
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Micro-actions are short-duration, low-amplitude subtle body movements at the whole-body level that can reveal latent intentions, involuntary reactions, and fine-grained affective changes. Our previous MA-52 benchmark has provided an important foundation for micro-action recognition, but it remains limited in scale, scene diversity, task coverage, and evaluation protocols. To advance micro-action analysis toward more realistic and comprehensive settings, we introduce MMA-82, a large-scale multi-domain extension of MA-52. MMA-82 expands the label space from 52 to 82 fine-grained micro-action categories and covers four distinct domains, including laboratory interviews, street interviews, psychiatric patient interviews, and emotion-rich television videos, resulting in 77,856 annotated instances from 454 subjects. Built upon MMA-82, we establish two core tasks: Micro-Action Recognition and Multi-label Micro-Action Detection. For recognition, we further define in-domain and cross-domain protocols, including few-shot and zero-shot settings, to evaluate model robustness, transferability, and generalization. Extensive experiments show that current methods still struggle with realistic micro-action understanding, especially under domain shift, long-tailed category distributions, and complex temporal localization. Beyond benchmarking, we investigate the relationship between micro-actions and emotion, showing that micro-actions are strongly associated with emotional states and provide complementary cues to facial micro-expressions for improved emotion recognition. These results demonstrate that MMA-82 serves as a comprehensive and challenging benchmark for realistic micro-action analysis and a valuable resource for human-centered AI. MMA-82 is available at https://lpynow.github.io/MMA-82-AIM/.

Related papers

• MAC 2026: Advancing Micro-Action Analysis Towards Fine-Grained Understanding [59.15655077579845]
  Micro-Action Analysis Grand Challenge (MAC) is a public benchmark platform for micro-action analysis research.<n>We introduce a new task named fine-grained micro-action understanding, evaluated with the assistance of multimodal large language models.<n>We summarize the datasets, task settings, evaluation protocols, competition results, and representative solutions from top-performing teams.
  arXiv  Detail & Related papers  (2026-07-10T12:31:27Z)
• MMAE: A Massive Multitask Audio Editing Benchmark [66.74229858407413]
  MMAE is the first comprehensive evaluation testbed designed for general-purpose instruction-based audio editing.<n>It comprises 2,000 high-fidelity samples paired with a pioneering rubric-based evaluation framework.<n>Our evaluation reveals that current systems remain far from achieving reliable edits.
  arXiv  Detail & Related papers  (2026-06-05T12:52:41Z)
• MMAD: Multi-label Micro-Action Detection in Videos [37.02734647950794]
  This paper focuses on a subset of body actions known as micro-actions, which are subtle, low-intensity body movements.<n>In real-world scenarios, human micro-actions often temporally co-occur, with multiple micro-actions overlapping in time.<n>We propose a new task named Multi-label Micro-Action Detection (MMAD), which involves identifying all micro-actions in a given short video.
  arXiv  Detail & Related papers  (2024-07-07T09:45:14Z)
• Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning [55.127202990679976]
  We introduce the MERR dataset, containing 28,618 coarse-grained and 4,487 fine-grained annotated samples across diverse emotional categories. This dataset enables models to learn from varied scenarios and generalize to real-world applications. We propose Emotion-LLaMA, a model that seamlessly integrates audio, visual, and textual inputs through emotion-specific encoders.
  arXiv  Detail & Related papers  (2024-06-17T03:01:22Z)
• Adaptive Temporal Motion Guided Graph Convolution Network for Micro-expression Recognition [48.21696443824074]
  We propose a novel framework for micro-expression recognition, named the Adaptive Temporal Motion Guided Graph Convolution Network (ATM-GCN) Our framework excels at capturing temporal dependencies between frames across the entire clip, thereby enhancing micro-expression recognition at the clip level.
  arXiv  Detail & Related papers  (2024-06-13T10:57:24Z)
• Identity-free Artificial Emotional Intelligence via Micro-Gesture Understanding [21.94739567923136]
  We focus on a special group of human body language -- the micro-gesture (MG)<n>MG differs from the range of ordinary illustrative gestures in that they are not intentional behaviors performed to convey information to others, but rather unintentional behaviors driven by inner feelings.<n>We explore various augmentation strategies that take into account the subtle spatial and brief temporal characteristics of micro-gestures, often accompanied by repetitiveness, to determine more suitable augmentation methods.
  arXiv  Detail & Related papers  (2024-05-21T21:16:55Z)
• Benchmarking Micro-action Recognition: Dataset, Methods, and Applications [26.090557725760934]
  Micro-action is imperceptible non-verbal behaviour characterised by low-intensity movement. In this study, we innovatively collect a new micro-action dataset designated as Micro-action-52 (MA-52) Uniquely, MA-52 provides the whole-body perspective including gestures, upper- and lower-limb movements.
  arXiv  Detail & Related papers  (2024-03-08T11:48:44Z)
• Video-based Facial Micro-Expression Analysis: A Survey of Datasets, Features and Algorithms [52.58031087639394]
  micro-expressions are involuntary and transient facial expressions. They can provide important information in a broad range of applications such as lie detection, criminal detection, etc. Since micro-expressions are transient and of low intensity, their detection and recognition is difficult and relies heavily on expert experiences.
  arXiv  Detail & Related papers  (2022-01-30T05:14:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.