# TDSal: Task-Based Top-Down Saliency Prediction Model

arXiv: https://arxiv.org/abs/2607.09827 · HTML: https://mlsanity.com/paper/2607.09827/

## 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 (most cited first, 11 of 11)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding](https://mlsanity.com/paper/2104.12763/) (2021)
- [Visual Saliency Transformer](https://mlsanity.com/paper/2104.12099/) (2021)
- [Towards Interpreting Visual Information Processing in Vision-Language Models](https://mlsanity.com/paper/2410.07149/) (2024)
- [Gazeformer: Scalable, Effective and Fast Prediction of Goal-Directed Human Attention](https://mlsanity.com/paper/2303.15274/) (2023)
- [AiR: Attention with Reasoning Capability](https://mlsanity.com/paper/2007.14419/) (2020)
- [Top-down Visual Saliency Guided by Captions](https://mlsanity.com/paper/1612.07360/) (2016)
- [Efficient Vision-Language Models by Summarizing Visual Tokens into Compact Registers](https://mlsanity.com/paper/2410.14072/) (2024)
- [How is Visual Attention Influenced by Text Guidance? Database and Model](https://mlsanity.com/paper/2404.07537/) (2024)
- [Top-Down Saliency Detection Driven by Visual Classification](https://mlsanity.com/paper/1709.05307/) (2017)

## 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.