Interactive Video Saliency Prediction: The Stacked-convLSTM Approach

Conference proceeding

N. Wondimu, U. Visser and C. Buche

ICAART 2023 - Proceedings of the 15th International Conference on Agents and Artificial Intelligence - (Volume 2), Vol.2, pp.157-168

2023

Abstract

ConvLSTM

Gaze Prediction

Human Attention

Saliency Prediction

Video Saliency

Video Saliency Dataset

url

https://doi.org/10.5220/0011664600003393View

Published (Version of record) Open

1 Record Views

Title: Interactive Video Saliency Prediction: The Stacked-convLSTM Approach
Creators: N. Wondimu - École nationale d'ingénieurs de Brest
U. Visser - University of Miami
C. Buche - Université de Bretagne Occidentale
Publication Details: ICAART 2023 - Proceedings of the 15th International Conference on Agents and Artificial Intelligence - (Volume 2), Vol.2, pp.157-168
Number of pages: 12
Grant note: ENIB Ministry of Education - Singapore (http://data.elsevier.com/vocabulary/SciValFunders/501100001459) Brest National School of Engineering Ministry of Education, Ethiopia (http://data.elsevier.com/vocabulary/SciValFunders/501100003081) French Embassy in Ethiopia
Academic Unit: College of A&S; A&S - Computer Science
Language: English
Resource Type: Conference proceeding
Record Identifier: 991032795951602976