Hypothesis
Version 1
Preserved in Portico This version is not peer-reviewed
Optimised ARG Based Group Activity Recognition for Video Understanding
Version 1
: Received: 10 June 2021 / Approved: 11 June 2021 / Online: 11 June 2021 (10:37:38 CEST)
How to cite: Kumar, P. Optimised ARG Based Group Activity Recognition for Video Understanding. Preprints 2021, 2021060313. https://doi.org/10.20944/preprints202106.0313.v1 Kumar, P. Optimised ARG Based Group Activity Recognition for Video Understanding. Preprints 2021, 2021060313. https://doi.org/10.20944/preprints202106.0313.v1
Abstract
In this paper, we propose a robust video understanding model for activity recognition by learning the actor’s pair-wise correlations and relational reasoning, exploiting spatial and temporal information. In order to measure the similarity between the pair appearances and construct an actor relations map, the Zero Mean Normalized Cross-Correlation (ZNCC) and the Zero Mean Sum of Absolute Differences(ZSAD) is proposed to allow the Graph Convolution Network (GCN) to learn how to distinguish group actions. We recommend that MNASNet be used as the backbone to retrieve features. Experiments show a 38.50% and 23.7% reduction in training time in the 2-stage training process along with a 1.52% improvement in accuracy against traditional methods.
Keywords
group activity recognition; graph convolution network; video understanding; video analytics; activity recognition
Subject
Computer Science and Mathematics, Algebra and Number Theory
Copyright: This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Comments (0)
We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.
Leave a public commentSend a private comment to the author(s)
* All users must log in before leaving a comment