FlowCaps: Optical Flow Estimation with Capsule Networks For Action Recognition

Page view(s)
51
Checked on Dec 03, 2024
FlowCaps: Optical Flow Estimation with Capsule Networks For Action Recognition
Title:
FlowCaps: Optical Flow Estimation with Capsule Networks For Action Recognition
Journal Title:
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
DOI:
Publication URL:
Publication Date:
08 January 2021
Citation:
Abstract:
Capsule networks (CapsNets) have recently shown promise to excel in most computer vision tasks, especially pertaining to scene understanding. In this paper, we explore CapsNet's capabilities in optical flow estimation, a task at which convolutional neural networks (CNNs) have already outperformed other approaches. We propose a CapsNet-based architecture, termed FlowCaps, which attempts to a) achieve better correspondence matching via finer-grained, motion-specific, and more-interpretable encoding crucial for optical flow estimation, b) perform better-generalizable optical flow estimation, c) utilize lesser ground truth data, and d) significantly reduce the computational complexity in achieving good performance, in comparison to its CNN-counterparts.
License type:
Funding Info:
This research is supported by the National Research Foundation Singapore under its AI Singapore Programme (Award Number: AISG-RP-2019-010).
Description:
ISBN:

Files uploaded:
File Size Format Action
There are no attached files.