Paper
28 April 2023 Instance-based adaptive attention algorithm for human-object interaction detection
Qing Ye, Xikun Wang
Author Affiliations +
Proceedings Volume 12610, Third International Conference on Artificial Intelligence and Computer Engineering (ICAICE 2022); 126105E (2023) https://doi.org/10.1117/12.2671090
Event: Third International Conference on Artificial Intelligence and Computer Engineering (ICAICE 2022), 2022, Wuhan, China
Abstract
Aiming at the problem of unclear human-object interaction behavior objects in complex background, we propose an Instance-Based Adaptive Attention (IBAA) algorithm. The algorithm adaptively generates a series of attention matrices according to the objects and subjects of human-object interaction instances. These attention matrices are then used to update the feature map to reduce the interference of the complex background. In order to enrich the human object interaction information, we use the graphical model to represent the interactions between human and objects and use the graph convolutional neural network to update it. Experimental results on HICO-DET dataset show that the proposed algorithm has significantly improved accuracy and multi-scale object detection ability compared with other human object interaction algorithms.
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Qing Ye and Xikun Wang "Instance-based adaptive attention algorithm for human-object interaction detection", Proc. SPIE 12610, Third International Conference on Artificial Intelligence and Computer Engineering (ICAICE 2022), 126105E (28 April 2023); https://doi.org/10.1117/12.2671090
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Object detection

Detection and tracking algorithms

Computer vision technology

Feature extraction

Matrices

Convolutional neural networks

Convolution

Back to Top