TSalV360: A Method and Dataset for Text-driven Saliency Detection in 360-Degrees Videos

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kontostathis, Ioannis, Apostolidis, Evlampios, Mezaris, Vasileios
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911185868161024
author Kontostathis, Ioannis
Apostolidis, Evlampios
Mezaris, Vasileios
author_facet Kontostathis, Ioannis
Apostolidis, Evlampios
Mezaris, Vasileios
contents In this paper, we deal with the task of text-driven saliency detection in 360-degrees videos. For this, we introduce the TSV360 dataset which includes 16,000 triplets of ERP frames, textual descriptions of salient objects/events in these frames, and the associated ground-truth saliency maps. Following, we extend and adapt a SOTA visual-based approach for 360-degrees video saliency detection, and develop the TSalV360 method that takes into account a user-provided text description of the desired objects and/or events. This method leverages a SOTA vision-language model for data representation and integrates a similarity estimation module and a viewport spatio-temporal cross-attention mechanism, to discover dependencies between the different data modalities. Quantitative and qualitative evaluations using the TSV360 dataset, showed the competitiveness of TSalV360 compared to a SOTA visual-based approach and documented its competency to perform customized text-driven saliency detection in 360-degrees videos.
format Preprint
id arxiv_https___arxiv_org_abs_2509_26208
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TSalV360: A Method and Dataset for Text-driven Saliency Detection in 360-Degrees Videos
Kontostathis, Ioannis
Apostolidis, Evlampios
Mezaris, Vasileios
Computer Vision and Pattern Recognition
In this paper, we deal with the task of text-driven saliency detection in 360-degrees videos. For this, we introduce the TSV360 dataset which includes 16,000 triplets of ERP frames, textual descriptions of salient objects/events in these frames, and the associated ground-truth saliency maps. Following, we extend and adapt a SOTA visual-based approach for 360-degrees video saliency detection, and develop the TSalV360 method that takes into account a user-provided text description of the desired objects and/or events. This method leverages a SOTA vision-language model for data representation and integrates a similarity estimation module and a viewport spatio-temporal cross-attention mechanism, to discover dependencies between the different data modalities. Quantitative and qualitative evaluations using the TSV360 dataset, showed the competitiveness of TSalV360 compared to a SOTA visual-based approach and documented its competency to perform customized text-driven saliency detection in 360-degrees videos.
title TSalV360: A Method and Dataset for Text-driven Saliency Detection in 360-Degrees Videos
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.26208