Alexandros Stergiou
Class Feature Pyramids for Video Explanation
Stergiou, Alexandros; Kapidis, Georgios; Kalliatakis, Grigorios; Chrysoulas, Christos; Poppe, Ronald; Veltkamp, Remco
Authors
Georgios Kapidis
Grigorios Kalliatakis
Dr Christos Chrysoulas C.Chrysoulas@napier.ac.uk
Lecturer
Ronald Poppe
Remco Veltkamp
Abstract
Deep convolutional networks are widely used in video
action recognition. 3D convolutions are one prominent approach to deal with the additional time dimension. While
3D convolutions typically lead to higher accuracies, the inner workings of the trained models are more difficult to interpret. We focus on creating human-understandable visual
explanations that represent the hierarchical parts of spatiotemporal networks. We introduce Class Feature Pyramids,
a method that traverses the entire network structure and
incrementally discovers kernels at different network depths
that are informative for a specific class. Our method does
not depend on the network’s architecture or the type of 3D
convolutions, supporting grouped and depth-wise convolutions, convolutions in fibers, and convolutions in branches.
We demonstrate the method on six state-of-the-art 3D convolution neural networks (CNNs) on three action recognition (Kinetics-400, UCF-101, and HMDB-51) and two
egocentric action recognition datasets (EPIC-Kitchens and
EGTEA Gaze+).
Citation
Stergiou, A., Kapidis, G., Kalliatakis, G., Chrysoulas, C., Poppe, R., & Veltkamp, R. (2020). Class Feature Pyramids for Video Explanation. . https://doi.org/10.1109/iccvw.2019.00524
Presentation Conference Type | Conference Paper (Published) |
---|---|
Conference Name | 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) |
Start Date | Oct 27, 2019 |
End Date | Oct 28, 2019 |
Acceptance Date | Aug 20, 2019 |
Online Publication Date | Mar 5, 2020 |
Publication Date | Mar 5, 2020 |
Deposit Date | Mar 26, 2020 |
Publisher | Institute of Electrical and Electronics Engineers |
Series ISSN | 2473-9944 |
DOI | https://doi.org/10.1109/iccvw.2019.00524 |
Public URL | http://researchrepository.napier.ac.uk/Output/2648982 |
You might also like
Multiply and conquer: A replication framework for building fault tolerant industrial applications
(2015)
Presentation / Conference Contribution
A service oriented QoS architecture targeting the smart grid world & machine learning aspects
(2016)
Presentation / Conference Contribution
Building an Adaptive E-Learning System
(2017)
Presentation / Conference Contribution
Teaching Industrial Automation Concepts with the use of Virtual/Augmented Reality - The IEC 61499 Case
(2018)
Presentation / Conference Contribution
Granularity Cost Analysis for Function Block as a Service
(2020)
Presentation / Conference Contribution
Downloadable Citations
About Edinburgh Napier Research Repository
Administrator e-mail: repository@napier.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2024
Advanced Search