.png){kind=icon}
.png){kind=icon}
Return
Cross-view action recognition with small-scale datasets
.png){kind=icon}
OA
AI
DOI：10.1016/j.imavis.2022.104403.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Cross-view action recognition refers to the task of recognizing actions observed from view-points that are unfa-miliar to the system. To address the complexity of the problem, state of the art methods often rely on large-scale datasets, where the variability of viewpoints is appropriately represented. However, this comes to a significant price, in terms of computational power, time, costs, energy for both gathering data annotation and training the model. We propose a methodological pipeline that tackles the same challenges with specific focus on small-scale datasets and attention to the amount of resources required. The core idea of our method is to transfer knowledge from an intermediate, pre-trained representation, under the hypothesis that it already may implicitly incorporate relevant cues for the task. We rely on an effective domain adaptation strategy coupled with the de-sign of a robust classifier that promotes view-invariant properties and allows us to efficiently generalise to action recognition to unseen viewpoints. In contrast to other state-of-art methods employing also alternative data mo-dalities, our approach is purely video-based and thus has a wider field of applications. We present a thorough ex-perimental analysis justifying the choices on the design of the pipeline, and providing a comparison with existing approaches in the two main scenarios of one-one learning and multiple view learning, where our approach pro-vides superior performance.(c) 2022 Elsevier B.V. All rights reserved.
Keywords:
Cross-view action recognition
Pre-trained deep features
Transfer learning
Multiview action recognition
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.