Keep it accurate and diverse: Enhancing action recognition performance by ensemble learning

Abstract

The performance of different action recognition techniques has recently been studied by several computer vision researchers. However, the potential improvement in classification through classifier fusion by ensemble-based methods has remained unattended. In this work, we evaluate the performance of an ensemble of action learning techniques, each performing the recognition task from a different perspective. The underlying idea is that instead of aiming a very sophisticated and powerful representation/learning technique, we can learn action categories using a set of relatively simple and diverse classifiers, each trained with different feature set. In addition, combining the outputs of several learners can reduce the risk of an unfortunate selection of a learner on an unseen action recognition scenario. This leads to having a more robust and general-applicable framework. In order to improve the recognition performance, a powerful combination strategy is utilized based on the Dempster-Shafer theory, which can effectively make use of diversity of base learners trained on different sources of information. The recognition results of the individual classifiers are compared with those obtained from fusing the classifiers' output, showing enhanced performance of the proposed methodology.

The Mediating Role of Critical Thinking Abilities in the Relationship Between English as a Foreign Language Learners’ Writing Performance and Their Language Learning Strategies

“…Considering the relationship between intermediate EFL learners’ learning strategies and their critical thinking, it was shown that these two variables were significantly correlated. This study is in line with Bagheri (2015) and Zarrinabadi et al (2021) , who reported a significant relationship between CTA and language learning strategies. Besides, this study also confirmed Nikoopour et al (2011) .…”

“… O’Malley and Chamot (1990) defined learning strategies as the particular thoughts or compartments that everybody uses to understand, learn, or maintain new information. On the other hand, Chamot (2004) , Bagheri (2015) , and Zarrinabadi et al (2021) claim that learning strategies are the purposive thoughts and behavior that students take to earn a learning goal. More importantly, successful learners have their unique techniques to learn.…”

“…In modern society, even in everyday life, people frequently need to deal with complicated public and political issues, make decisions, and solve problems ( Bagheri, 2015 ; Zarrinabadi et al, 2021 ). To do this efficiently and effectively, citizens must evaluate critically what they see, hear, and read.…”

Action Recognition Framework using Saliency Detection and Random Subspace Ensemble Classifier

“…So, an ensemble classification is used for improving the efficiency, compensating for an insufficiency in one learner. The experimental outcomes show that the recognition accuracy can significantly be enhanced [4].…”

DIY Human Action Dataset Generation

“…Video data sets or specifically human action data sets are more difficult to compile. There are two common scenarios to generate a human action data set: (1) asking subjects to do a series of actions in front of a camera (2) labeling an existing video from the internet. The first scenario is not scaleable considering the number of subjects and the limitations imposed by the capturing environment.…”