Feature Space Data Augmentation for Viewpoint-Robust Action Recognition in Videos

The ongoing research on human action recognition models is achieving very promising results, and the existing models reach very high performances. However, they still suffer from one major challenge: their performance decreases on viewpoints not seen in the training step of the model. In this paper,...

Full description

Saved in:
Bibliographic Details
Published in2023 IEEE International Conference on Image Processing (ICIP) pp. 585 - 589
Main Authors Geara, Carla, Setkov, Aleksandr, Orcesi, Astrid, Luvison, Bertrand
Format Conference Proceeding
LanguageEnglish
Published IEEE 08.10.2023
Subjects
Action Recognition
Cameras
Data augmentation
Data models
Image recognition
Pipelines
Robustness
Training
Viewpoint Robustness
Online AccessGet full text

Cover

More Information
Summary:The ongoing research on human action recognition models is achieving very promising results, and the existing models reach very high performances. However, they still suffer from one major challenge: their performance decreases on viewpoints not seen in the training step of the model. In this paper, we introduce a new approach based on virtual viewpoint augmentation in the feature space to increase the robustness of the action recognition models to different camera viewpoints. This approach was evaluated on two action recognition datasets: DAHLIA and Toyota SmartHome. Our model shows promising results, with a significant performance increase on both datasets for viewpoints not seen during the training step.
DOI:10.1109/ICIP49359.2023.10222026