mlsanityData to 14 Oct 2026

Online Micro-gesture Recognition Using Data Augmentation and Spatial-Temporal Attention

arXiv 2507.09512 ↗First posted 13 Jul 2025cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

In this paper, we introduce the latest solution developed by our team, HFUT-VUT, for the Micro-gesture Online Recognition track of the IJCAI 2025 MiGA Challenge. The Micro-gesture Online Recognition task is a highly challenging problem that aims to locate the temporal positions and recognize the categories of multiple micro-gesture instances in untrimmed videos. Compared to traditional temporal action detection, this task places greater emphasis on distinguishing between micro-gesture categories and precisely identifying the start and end times of each instance. Moreover, micro-gestures are typically spontaneous human actions, with greater differences than those found in other human actions. To address these challenges, we propose hand-crafted data augmentation and spatial-temporal attention to enhance the model's ability to classify and localize micro-gestures more accurately. Our solution achieved an F1 score of 38.03, outperforming the previous state-of-the-art by 37.9%. As a result, our method ranked first in the Micro-gesture Online Recognition track.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 27 of its 34 references that are in the map. First posted on arXiv 13 Jul 2025.

Builds on

27 of 34 references.

References · 27

  1. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  2. 2022VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Trainingcited by 1,322
  3. 2023VideoMAE V2: Scaling Video Masked Autoencoders with Dual Maskingcited by 528
  4. 2022ActionFormer: Localizing Moments of Actions with Transformerscited by 311
  5. 2023TriDet: Temporal Action Detection with Relative Boundary Modelingcited by 142
  6. 2018Diagnosing Error in Temporal Action Detectorscited by 71
  7. 2021iMiGUE: An Identity-free Video Dataset for Micro-Gesture Understanding and Emotion Analysiscited by 63
  8. 2024Benchmarking Micro-action Recognition: Dataset, Methods, and Applicationscited by 48
  9. 2023End-to-End Temporal Action Detection with 1B Parameters Across 1000 Framescited by 47
  10. 2021MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detectioncited by 42
  11. 2021Modeling Multi-Label Action Dependencies for Temporal Action Localizationcited by 32
  12. 2024Frequency Decoupling for Motion Magnification via Multi-Level Isomorphic Architecturecited by 28
15 more
  1. 2023EulerMormer: Robust Eulerian Motion Magnification via Dynamic Filtering within Transformercited by 27
  2. 2023Joint Skeletal and Semantic Embedding Loss for Micro-gesture Classificationcited by 25
  3. 2022PointTAD: Multi-Label Temporal Action Detection with Learnable Query Pointscited by 22
  4. 2024Prototypical Calibrating Ambiguous Samples for Micro-Action Recognitioncited by 22
  5. 2023Unified Multi-modal Unsupervised Representation Learning for Skeleton-based Action Understandingcited by 20
  6. 2024MMAD: Multi-label Micro-Action Detection in Videoscited by 20
  7. 2024DyFADet: Dynamic Feature Aggregation for Temporal Action Detectioncited by 19
  8. 2024Micro-gesture Online Recognition using Learnable Query Pointscited by 18
  9. 2024Prototype Learning for Micro-gesture Classificationcited by 18
  10. 2023Data Augmentation for Human Behavior Analysis in Multi-Person Conversationscited by 15
  11. 2024Repetitive Action Counting with Hybrid Temporal Relation Modelingcited by 13
  12. 2024Temporal-Frequency State Space Duality: An Efficient Paradigm for Speech Emotion Recognitioncited by 10
  13. 2025Exploiting Ensemble Learning for Cross-View Isolated Sign Language Recognitioncited by 10
  14. 2024Identity-free Artificial Emotional Intelligence via Micro-Gesture Understandingcited by 8
  15. 2025A Survey on fMRI-based Brain Decoding for Reconstructing Multimodal Stimulicited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 9.

11 papers.

  1. 2025Motion Matters: Motion-guided Modulation Network for Skeleton-based Micro-Action Recognitioncited by 11
  2. 2026MA-Bench: Towards Fine-grained Micro-Action Understandingcited by 9
  3. 2026Spatial-Temporal Decoupled Adapter for Micro-gesture Online Recognitioncited by 4
  4. 2026Self-supervised Learning Matters: A Simple Ensemble Solution for Micro-Gesture Recognitioncited by 4
  5. 2026Rethinking the Role of Feature Engineering and Learning Strategies in Few-Shot Hidden Emotion Recognitioncited by 3
  6. 2026MAC 2026: Advancing Micro-Action Analysis Towards Fine-Grained Understandingcited by 2
  7. 2025MSF-Mamba: Motion-aware State Fusion Mamba for Efficient Micro-Gesture Recognitioncited by 1
  8. 2026Motion Reinforces Appearance: RGB-Skeleton Gated Residual Fusion for Micro-Gesture Online Recognitioncited by 0
  9. 2026A Multi-Modal Framework with Cross-Subject Pseudo-Labeling and Semantic Alignment for Micro-Gesture Recognitioncited by 0
  10. 2026Zero-MELO: Test-Time Evidence Calibration with Multimodal LLMs for Zero-Shot Micro-Gesture Recognitioncited by 0
  11. 2026Recognition-Conditioned Reasoning: A Training-Free Multimodal-LLM Pipeline for Fine-Grained Micro-Action Understandingcited by 0