mlsanityData to 14 Oct 2026

TDSal: Task-Based Top-Down Saliency Prediction Model

arXiv 2607.09827 ↗First posted 10 Jul 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Visual saliency aims to predict the regions of an image most likely to attract human visual attention. While most saliency models assume free-viewing conditions, human attention is often shaped by explicit task goals. In this work, we address task-driven saliency prediction by proposing a model that conditions visual attention on natural-language task descriptions. The model produces task-dependent saliency maps that reflect how attention shifts under different viewing intents. Through quantitative and qualitative analysis, we show that incorporating explicit task semantics enables more faithful modeling of goal-directed visual attention.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 11 of its 23 references that are in the map. First posted on arXiv 10 Jul 2026.

Builds on

11 of 23 references.

References · 11

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  2. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  3. 2021MDETR -- Modulated Detection for End-to-End Multi-Modal Understandingcited by 819
  4. 2021Visual Saliency Transformercited by 175
  5. 2024Towards Interpreting Visual Information Processing in Vision-Language Modelscited by 122
  6. 2023Gazeformer: Scalable, Effective and Fast Prediction of Goal-Directed Human Attentioncited by 38
  7. 2020AiR: Attention with Reasoning Capabilitycited by 28
  8. 2016Top-down Visual Saliency Guided by Captionscited by 22
  9. 2024Efficient Vision-Language Models by Summarizing Visual Tokens into Compact Registerscited by 19
  10. 2024How is Visual Attention Influenced by Text Guidance? Database and Modelcited by 7
  11. 2017Top-Down Saliency Detection Driven by Visual Classificationcited by 4

Built on by

Not cited yet.