# VQD: Visual Query Detection in Natural Scenes

arXiv: https://arxiv.org/abs/1904.02794 · HTML: https://mlsanity.com/paper/1904.02794/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Apr 2019.

## Built on by (most cited first, 7 of 7)

- [QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension](https://mlsanity.com/paper/2107.12708/) (2021)
- [Overcoming the Stability Gap in Continual Learning](https://mlsanity.com/paper/2306.01904/) (2023)
- [What Variables Affect Out-of-Distribution Generalization in Pretrained Models?](https://mlsanity.com/paper/2405.15018/) (2024)
- [Selective Replay Enhances Learning in Online Continual Analogical Reasoning](https://mlsanity.com/paper/2103.03987/) (2021)
- [Calibrating Uncertainty Quantification of Multi-Modal LLMs using Grounding](https://mlsanity.com/paper/2505.03788/) (2025)
- [Revisiting Multi-Modal LLM Evaluation](https://mlsanity.com/paper/2408.05334/) (2024)
- [UniRef-UAV: A Multimodal Benchmark for Universal Referring in UAV Imagery](https://mlsanity.com/paper/2607.08267/) (2026)

## Abstract (arXiv)

We propose Visual Query Detection (VQD), a new visual grounding task. In VQD, a system is guided by natural language to localize a variable number of objects in an image. VQD is related to visual referring expression recognition, where the task is to localize only one object. We describe the first dataset for VQD and we propose baseline algorithms that demonstrate the difficulty of the task compared to referring expression recognition.