Linardos, Panagiotis, Mohedano, Eva, Nieto, Juan Jose, O'Connor, Noel E. 
ORCID: 0000-0002-4033-9135, Giró-i-Nieto, Xavier ORCID: 0000-0002-9935-5332 and McGuinness, Kevin ORCID: 0000-0003-1336-6477
(2019)
Simple vs complex temporal recurrences for video saliency prediction.
In: 30th British Machine Vision Conference (BMVC), 9-12 Sept 2019, Cardiff, Wales, UK.
This is the latest version of this item.
Full text available as:
|
PDF
- Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
1MB |
Abstract
This paper investigates modifying an existing neural network architecture for static saliency prediction using two types of recurrences that integrate information from the temporal domain. The first modification is the addition of a ConvLSTM within the architecture, while the second is a conceptually simple exponential moving average of an internal convolutional state. We use weights pre-trained on the SALICON dataset and fine-tune our model on DHF1K. Our results show that both modifications achieve state-of-the-art results and produce similar saliency maps. Source code is available at https://git.io/fjPiB.
| Item Type: | Conference or Workshop Item (Paper) |
|---|---|
| Event Type: | Conference |
| Refereed: | Yes |
| Subjects: | Computer Science > Artificial intelligence Computer Science > Image processing Computer Science > Machine learning Computer Science > Digital video |
| DCU Faculties and Centres: | DCU Faculties and Schools > Faculty of Engineering and Computing > School of Electronic Engineering Research Initiatives and Centres > INSIGHT Centre for Data Analytics |
| Published in: | 30th British Machine Vision Conference (BMVC) 2019, Proceedings. . BMVC. |
| Publisher: | BMVC |
| Official URL: | https://dx.doi.org/10.5244/C.33.185 |
| Copyright Information: | © 2019. The Authors. It may be distributed unchanged freely in print or electronic forms. |
| Use License: | This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License |
| Funders: | Science Foundation Ireland (SFI) under grant number SFI/15/SIRG/3283 and SFI/12/RC/2289., framework of project TEC2016- 75976-R, funded by the Spanish Ministerio de Economia y Competitividad., European Regional Development Fund (ERDF) |
| ID Code: | 23568 |
| Deposited On: | 04 Mar 2020 12:08 by Panagiotis Linardos . Last Modified 27 Oct 2021 13:11 |
Available Versions of this Item
-
Temporal recurrences for video saliency prediction. (deposited 10 Jul 2019 11:52)
- Simple vs complex temporal recurrences for video saliency prediction. (deposited 04 Mar 2020 12:08) [Currently Displayed]
Downloads
Downloads per month over past year
Archive Staff Only: edit this record
Altmetric
Altmetric