{"ID":2862766,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.26208","arxiv_id":"2509.26208","title":"TSalV360: A Method and Dataset for Text-driven Saliency Detection in 360-Degrees Videos","abstract":"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.","short_abstract":"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 ad...","url_abs":"https://arxiv.org/abs/2509.26208","url_pdf":"https://arxiv.org/pdf/2509.26208v1","authors":"[\"Ioannis Kontostathis\",\"Evlampios Apostolidis\",\"Vasileios Mezaris\"]","published":"2025-09-30T13:11:16Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Language Model\"]","has_code":false}