Learning Mutual Excitation for Hand-to-Hand and Human-to-Human Interaction Recognition

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Mengyuan, Chen, Chen, Wu, Songtao, Meng, Fanyang, Liu, Hong
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910760363360256
author Liu, Mengyuan
Chen, Chen
Wu, Songtao
Meng, Fanyang
Liu, Hong
author_facet Liu, Mengyuan
Chen, Chen
Wu, Songtao
Meng, Fanyang
Liu, Hong
contents Recognizing interactive actions, including hand-to-hand interaction and human-to-human interaction, has attracted increasing attention for various applications in the field of video analysis and human-robot interaction. Considering the success of graph convolution in modeling topology-aware features from skeleton data, recent methods commonly operate graph convolution on separate entities and use late fusion for interactive action recognition, which can barely model the mutual semantic relationships between pairwise entities. To this end, we propose a mutual excitation graph convolutional network (me-GCN) by stacking mutual excitation graph convolution (me-GC) layers. Specifically, me-GC uses a mutual topology excitation module to firstly extract adjacency matrices from individual entities and then adaptively model the mutual constraints between them. Moreover, me-GC extends the above idea and further uses a mutual feature excitation module to extract and merge deep features from pairwise entities. Compared with graph convolution, our proposed me-GC gradually learns mutual information in each layer and each stage of graph convolution operations. Extensive experiments on a challenging hand-to-hand interaction dataset, i.e., the Assembely101 dataset, and two large-scale human-to-human interaction datasets, i.e., NTU60-Interaction and NTU120-Interaction consistently verify the superiority of our proposed method, which outperforms the state-of-the-art GCN-based and Transformer-based methods.
format Preprint
id arxiv_https___arxiv_org_abs_2402_02431
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning Mutual Excitation for Hand-to-Hand and Human-to-Human Interaction Recognition
Liu, Mengyuan
Chen, Chen
Wu, Songtao
Meng, Fanyang
Liu, Hong
Computer Vision and Pattern Recognition
Machine Learning
Recognizing interactive actions, including hand-to-hand interaction and human-to-human interaction, has attracted increasing attention for various applications in the field of video analysis and human-robot interaction. Considering the success of graph convolution in modeling topology-aware features from skeleton data, recent methods commonly operate graph convolution on separate entities and use late fusion for interactive action recognition, which can barely model the mutual semantic relationships between pairwise entities. To this end, we propose a mutual excitation graph convolutional network (me-GCN) by stacking mutual excitation graph convolution (me-GC) layers. Specifically, me-GC uses a mutual topology excitation module to firstly extract adjacency matrices from individual entities and then adaptively model the mutual constraints between them. Moreover, me-GC extends the above idea and further uses a mutual feature excitation module to extract and merge deep features from pairwise entities. Compared with graph convolution, our proposed me-GC gradually learns mutual information in each layer and each stage of graph convolution operations. Extensive experiments on a challenging hand-to-hand interaction dataset, i.e., the Assembely101 dataset, and two large-scale human-to-human interaction datasets, i.e., NTU60-Interaction and NTU120-Interaction consistently verify the superiority of our proposed method, which outperforms the state-of-the-art GCN-based and Transformer-based methods.
title Learning Mutual Excitation for Hand-to-Hand and Human-to-Human Interaction Recognition
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2402.02431