Efficient Class-Incremental Learning Based on Bag-of-Sequencelets Model for Activity Recognition

Jong-Woo LEE  Ki-Sang HONG  

IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E102-A   No.9   pp.1293-1302
Publication Date: 2019/09/01
Online ISSN: 1745-1337
DOI: 10.1587/transfun.E102.A.1293
Type of Manuscript: PAPER
Category: Vision
activity recognition,  action classification,  class-incremental learning,  video classification,  

Full Text: PDF>>
Buy this Article

We propose a class-incremental learning framework for human activity recognition based on the Bag-of-Sequencelets model (BoS). The framework updates learned models efficiently without having to relearn them when training data of new classes are added. In this framework, all types of features including hand-crafted features and Convolutional Neural Networks (CNNs) based features and combinations of those features can be used as features for videos. Compared with the original BoS, the new framework can reduce the learning time greatly with little loss of classification accuracy.