Micro-DualNet: Dual-Path Spatio-Temporal Network for Micro-Action Recognition

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Chappa, Naga VS Raviteja, Sariyanidi, Evangelos, Yankowitz, Lisa, Nair, Gokul, Zampella, Casey J., Schultz, Robert T., Tunç, Birkan
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908987822178304
author Chappa, Naga VS Raviteja
Sariyanidi, Evangelos
Yankowitz, Lisa
Nair, Gokul
Zampella, Casey J.
Schultz, Robert T.
Tunç, Birkan
author_facet Chappa, Naga VS Raviteja
Sariyanidi, Evangelos
Yankowitz, Lisa
Nair, Gokul
Zampella, Casey J.
Schultz, Robert T.
Tunç, Birkan
contents Micro-actions are subtle, localized movements lasting 1-3 seconds such as scratching one's head or tapping fingers. Such subtle actions are essential for social communication, ubiquitously used in natural interactions, and thus critical for fine-grained video understanding, yet remain poorly understood by current computer vision systems. We identify a fundamental challenge: micro-actions exhibit diverse spatio-temporal characteristics where some are defined by spatial configurations while others manifest through temporal dynamics. Existing methods that commit to a single spatio-temporal decomposition cannot accommodate this diversity. We propose a dual-path network that processes anatomically-grounded spatial entities through parallel Spatial-Temporal (ST) and Temporal-Spatial (TS) pathways. The ST path captures spatial configurations before modeling temporal dynamics, while the TS path inverts this order to prioritize temporal dynamics. Rather than fixed fusion, we introduce entity-level adaptive routing where each body part learns its optimal processing preference, complemented by Mutual Action Consistency (MAC) loss that enforces cross-path coherence. Extensive experiments demonstrate competitive performance on MA-52 dataset and state-of-the-art results on iMiGUE dataset. Our work reveals that architectural adaptation to the inherent complexity of micro-actions is essential for advancing fine-grained video understanding.
format Preprint
id arxiv_https___arxiv_org_abs_2604_21011
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Micro-DualNet: Dual-Path Spatio-Temporal Network for Micro-Action Recognition
Chappa, Naga VS Raviteja
Sariyanidi, Evangelos
Yankowitz, Lisa
Nair, Gokul
Zampella, Casey J.
Schultz, Robert T.
Tunç, Birkan
Computer Vision and Pattern Recognition
Neurons and Cognition
Micro-actions are subtle, localized movements lasting 1-3 seconds such as scratching one's head or tapping fingers. Such subtle actions are essential for social communication, ubiquitously used in natural interactions, and thus critical for fine-grained video understanding, yet remain poorly understood by current computer vision systems. We identify a fundamental challenge: micro-actions exhibit diverse spatio-temporal characteristics where some are defined by spatial configurations while others manifest through temporal dynamics. Existing methods that commit to a single spatio-temporal decomposition cannot accommodate this diversity. We propose a dual-path network that processes anatomically-grounded spatial entities through parallel Spatial-Temporal (ST) and Temporal-Spatial (TS) pathways. The ST path captures spatial configurations before modeling temporal dynamics, while the TS path inverts this order to prioritize temporal dynamics. Rather than fixed fusion, we introduce entity-level adaptive routing where each body part learns its optimal processing preference, complemented by Mutual Action Consistency (MAC) loss that enforces cross-path coherence. Extensive experiments demonstrate competitive performance on MA-52 dataset and state-of-the-art results on iMiGUE dataset. Our work reveals that architectural adaptation to the inherent complexity of micro-actions is essential for advancing fine-grained video understanding.
title Micro-DualNet: Dual-Path Spatio-Temporal Network for Micro-Action Recognition
topic Computer Vision and Pattern Recognition
Neurons and Cognition
url https://arxiv.org/abs/2604.21011