University of Oulu

A. Shah, H. Chen, H. Shi and G. Zhao, "Efficient Dense-Graph Convolutional Network with Inductive Prior Augmentations for Unsupervised Micro-Gesture Recognition," 2022 26th International Conference on Pattern Recognition (ICPR), Montreal, QC, Canada, 2022, pp. 2686-2692, doi: 10.1109/ICPR56361.2022.9956565

Efficient dense-graph convolutional network with inductive prior augmentations for unsupervised micro-gesture recognition

Saved in:
Author: Shah, Atif1; Chen, Haoyu1; Shi, Henglin1;
Organizations: 1Center for Machine Vision and Signal Analysis (CMVS), University of Oulu, Finland
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 1.7 MB)
Persistent link:
Language: English
Published: IEEE Computer Society, 2022
Publish Date: 2023-03-23


Skeleton-based action/gesture recognition has already witnessed excellent progress on processing large-scale, laboratory-based datasets with pre-defined skeleton joint topology. However, it’s still an unsolved task when it comes to real-world scenarios with practical limitations such as small-scaled dataset sizes, few-labeled samples, and various skeleton topologies. In this paper, we work on the recognition of micro-gestures, which are subtle body gestures collected in real-world scenarios. Specifically, we utilize contrastive learning to heritage the knowledge from known large-scale datasets for enhancing the learning on fewer samples of micro-gestures. To overcome the gap caused by various domain distributions and structure topologies between the datasets, we compute skeleton representations from augmented sequences via momentum-based efficient and scalable encoders as additional inductive priors. Importantly, we propose an effective dense-graph based unsupervised architecture that resorts to a queue-based dictionary to store positive and negative keys for better contrast with queries to learn substantially efficient and discriminant patterns in the feature space. Together with cross-dataset experimental results show that our model significantly improves the accuracies on two micro-gesture datasets, SMG by 7.4% and iMiGUE by 18.41% advocating its superiority.

see all

Series: International Conference on Pattern Recognition
ISSN: 1051-4651
ISSN-L: 1051-4651
ISBN: 978-1-6654-9062-7
ISBN Print: 978-1-6654-9063-4
Pages: 2686 - 2692
DOI: 10.1109/ICPR56361.2022.9956565
Host publication: 2022 26th International Conference on Pattern Recognition (ICPR)
Conference: International Conference on Pattern Recognition
Type of Publication: A4 Article in conference proceedings
Field of Science: 113 Computer and information sciences
Funding: This work was supported by the Academy of Finland for Academy Professor project EmotionAI (grants 336116, 345122), project MiGA (grant 316765) and ICT 2023 project (grant 328115).
Academy of Finland Grant Number: 336116
Detailed Information: 336116 (Academy of Finland Funding decision)
345122 (Academy of Finland Funding decision)
316765 (Academy of Finland Funding decision)
328115 (Academy of Finland Funding decision)
Copyright information: © 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.