MMAD: Multi-label Micro-Action Detection in Videos

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Kun, Liu, Pengyu, Guo, Dan, Wang, Fei, Wu, Zhiliang, Fan, Hehe, Wang, Meng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912545267253248
author Li, Kun
Liu, Pengyu
Guo, Dan
Wang, Fei
Wu, Zhiliang
Fan, Hehe
Wang, Meng
author_facet Li, Kun
Liu, Pengyu
Guo, Dan
Wang, Fei
Wu, Zhiliang
Fan, Hehe
Wang, Meng
contents Human body actions are an important form of non-verbal communication in social interactions. This paper specifically focuses on a subset of body actions known as micro-actions, which are subtle, low-intensity body movements with promising applications in human emotion analysis. In real-world scenarios, human micro-actions often temporally co-occur, with multiple micro-actions overlapping in time, such as concurrent head and hand movements. However, current research primarily focuses on recognizing individual micro-actions while overlooking their co-occurring nature. To address this gap, we propose a new task named Multi-label Micro-Action Detection (MMAD), which involves identifying all micro-actions in a given short video, determining their start and end times, and categorizing them. Accomplishing this requires a model capable of accurately capturing both long-term and short-term action relationships to detect multiple overlapping micro-actions. To facilitate the MMAD task, we introduce a new dataset named Multi-label Micro-Action-52 (MMA-52) and propose a baseline method equipped with a dual-path spatial-temporal adapter to address the challenges of subtle visual change in MMAD. We hope that MMA-52 can stimulate research on micro-action analysis in videos and prompt the development of spatio-temporal modeling in human-centric video understanding. The proposed MMA-52 dataset is available at: https://github.com/VUT-HFUT/Micro-Action.
format Preprint
id arxiv_https___arxiv_org_abs_2407_05311
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MMAD: Multi-label Micro-Action Detection in Videos
Li, Kun
Liu, Pengyu
Guo, Dan
Wang, Fei
Wu, Zhiliang
Fan, Hehe
Wang, Meng
Computer Vision and Pattern Recognition
Human body actions are an important form of non-verbal communication in social interactions. This paper specifically focuses on a subset of body actions known as micro-actions, which are subtle, low-intensity body movements with promising applications in human emotion analysis. In real-world scenarios, human micro-actions often temporally co-occur, with multiple micro-actions overlapping in time, such as concurrent head and hand movements. However, current research primarily focuses on recognizing individual micro-actions while overlooking their co-occurring nature. To address this gap, we propose a new task named Multi-label Micro-Action Detection (MMAD), which involves identifying all micro-actions in a given short video, determining their start and end times, and categorizing them. Accomplishing this requires a model capable of accurately capturing both long-term and short-term action relationships to detect multiple overlapping micro-actions. To facilitate the MMAD task, we introduce a new dataset named Multi-label Micro-Action-52 (MMA-52) and propose a baseline method equipped with a dual-path spatial-temporal adapter to address the challenges of subtle visual change in MMAD. We hope that MMA-52 can stimulate research on micro-action analysis in videos and prompt the development of spatio-temporal modeling in human-centric video understanding. The proposed MMA-52 dataset is available at: https://github.com/VUT-HFUT/Micro-Action.
title MMAD: Multi-label Micro-Action Detection in Videos
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.05311