@article{M7297D522,
title = "Teacher-Student Architecture Based CNN for Action Recognition",
journal = "The Transactions of the Korea Information Processing Society",
year = "2022",
issn = "null",
doi = "https://doi.org/10.3745/KTCCS.2022.11.3.99",
author = "Yulan Zhao/Hyo Jong Lee",
keywords = "Two-Stream Network, Teacher-Student Architecture, CNN, Optical Flow, Action Recognition",
abstract = "Convolutional neural network (CNN) generally uses two-stream architecture RGB and optical flow stream for its action recognition
function. RGB frames stream display appearance and optical flow stream interprets its action. However, the standard method of using
optical flow is costly in its computational time and latency associated with increased action recognition. The purpose of the study was
to evaluate a novel way to create a two sub-networks in neural networks. The optical flow sub-network was assigned as a teacher and
the RGB frames as a student. In the training stage, the optical flow sub-network extracts features through the teacher sub-network and
transmits the information to student sub-network for baseline training. In the test stage, only student sub-network was operational with
decreased in latency without computing optical flow. Experimental results shows that our network fed only by RGB stream gets a competitive
accuracy of 54.5% on HMDB51, which is 1.5 times better than that on R3D-18."
}