The Visual Saliency Transformer Goes Temporal: TempVST for Video Saliency Prediction

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F24%3A00379847" target="_blank" >RIV/68407700:21230/24:00379847 - isvavai.cz</a>

Result on the web

<a href="https://doi.org/10.1109/ACCESS.2024.3436585" target="_blank" >https://doi.org/10.1109/ACCESS.2024.3436585</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ACCESS.2024.3436585" target="_blank" >10.1109/ACCESS.2024.3436585</a>

Result language

angličtina

Original language name

The Visual Saliency Transformer Goes Temporal: TempVST for Video Saliency Prediction

Original language description

The Transformer revolutionized Natural Language Processing and Computer Vision by effectively capturing contextual relationships in sequential data through its attention mechanism. While Transformers have been explored sufficiently in traditional computer vision tasks such as image classification, their application to more intricate tasks, such as Video Saliency Prediction (VSP), remains limited. Video saliency prediction is the task of identifying the most visually salient regions in a video, which are likely to capture a viewer's attention. In this study, we propose a pure transformer architecture named Temporal Visual Saliency Transformer (TempVST) for the VSP task. Our model leverages the Visual Saliency Transformer (VST) as a backbone, with the addition of a Transformer-based temporal module that can seamlessly transition diverse architectural frameworks from image to video domain, through the incorporation of temporal recurrences. Moreover, we demonstrate that transfer learning is viable in the context of VSP through Transformer architectures and helps reduce the duration of the training phase, leading to a reduction in the duration of the training phase by 41% and 45% in two different datasets. Our experiments were conducted on two benchmark datasets, DHF1K and LEDOV, and our results show that our network can compete with all other state-of-the-art models.

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2024

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

IEEE Access

ISSN

2169-3536

e-ISSN

2169-3536

Volume of the periodical

12

Issue of the periodical within the volume

Aug

Country of publishing house

US - UNITED STATES

Number of pages

12

Pages from-to

129705-129716

UT code for WoS article

001320453600001

EID of the result in the Scopus database

2-s2.0-85200252622