mlsanityData to 14 Oct 2026

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

arXiv 2509.26208 ↗First posted 30 Sep 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 28 of its 56 references that are in the map. First posted on arXiv 30 Sep 2025.

Builds on

28 of 56 references.

References · 28

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,556
  4. 2015Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Modelscited by 1,362
  5. 2016What do different evaluation metrics tell us about saliency models?cited by 185
  6. 2019Tangent Images for Mitigating Spherical Distortioncited by 79
  7. 2019Motion Guided Attention for Video Salient Object Detectioncited by 72
  8. 2018Cube Padding for Weakly-Supervised Saliency Prediction in 360deg Videoscited by 66
  9. 2020ViNet: Pushing the limits of Visual Modality for Audio-Visual Saliency Predictioncited by 43
  10. 2017Predicting Head Movement in Panoramic Video: A Deep Reinforcement Learning Approachcited by 34
  11. 2018A Memory Network Approach for Story-based Temporal Summarization of 360deg Videoscited by 29
  12. 2021Towards Accurate Text-based Image Captioning with Content Diversity Explorationcited by 25
16 more
  1. 2016Pano2Vid: Automatic Cinematography for Watching 360circ Videoscited by 22
  2. 2017Deep 360 Pilot: Learning a Deep Agent for Piloting through 360deg Sports Videocited by 22
  3. 2020ATSal: An Attention Based Architecture for Saliency Prediction in 360 Videoscited by 19
  4. 2018A Deep Ranking Model for Spatio-Temporal Highlight Detection from a 360 Videocited by 16
  5. 2022Panoramic Vision Transformer for Saliency Detection in 360deg Videoscited by 15
  6. 2017Making 360circ Video Watchable in 2D: Learning Videography for Click Free Viewingcited by 13
  7. 2021Video Salient Object Detection via Contrastive Features and Attention Modulescited by 13
  8. 2023Query-based Video Summarization with Pseudo Label Supervisioncited by 13
  9. 2024DiffSal: Joint Audio and Video Learning for Diffusion Saliency Predictioncited by 13
  10. 2020Video Saliency Prediction Using Enhanced Spatiotemporal Alignment Networkcited by 9
  11. 2024360VOTS: Visual Object Tracking and Segmentation in Omnidirectional Videoscited by 8
  12. 2024How is Visual Attention Influenced by Text Guidance? Database and Modelcited by 7
  13. 2025Text-Audio-Visual-conditioned Diffusion Model for Video Saliency Predictioncited by 3
  14. 2025SD-VSum: A Method and Dataset for Script-Driven Video Summarizationcited by 3
  15. 2023Understanding Video Scenes through Text: Insights from Text-based Video Question Answeringcited by 2
  16. 2023An Integrated System for Spatio-Temporal Summarization of 360-degrees Videoscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Follow the Saliency: Supervised Saliency for Retrieval-augmented Dense Video Captioning
  2. 2024CaRDiff: Video Salient Object Ranking Chain of Thought Reasoning for Saliency Prediction with Diffusion
  3. 2026Is It Time for the Renaissance of Salient Object Detection in the Era of MLLMs?
  4. 2024VISTA: A Visual and Textual Attention Dataset for Interpreting Multimodal Models
  5. 2024FocusChat: Text-guided Long Video Understanding via Spatiotemporal Information Filtering
  6. 2025Vision-Language Models Can't See the Obvious
  7. 2026Interpretable Motion-Attentive Maps: Spatio-Temporally Localizing Concepts in Video Diffusion Transformers
  8. 2025LET-US: Long Event-Text Understanding of Scenes