# Exploring Contextual Attribute Density in Referring Expression Counting

arXiv: https://arxiv.org/abs/2503.12460 · HTML: https://mlsanity.com/paper/2503.12460/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 42 references that are in the map.
- First posted on arXiv 16 Mar 2025.

## Builds on (most cited first, 29 of 29)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds](https://mlsanity.com/paper/1808.01050/) (2018)
- [Drone-based Object Counting by Spatially Regularized Regional Proposal Network](https://mlsanity.com/paper/1707.05972/) (2017)
- [Learning To Count Everything](https://mlsanity.com/paper/2104.08391/) (2021)
- [Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection](https://mlsanity.com/paper/2405.10300/) (2024)
- [Class-Agnostic Counting](https://mlsanity.com/paper/1811.00472/) (2018)
- [CLIP-Count: Towards Text-Guided Zero-Shot Object Counting](https://mlsanity.com/paper/2305.07304/) (2023)
- [Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting](https://mlsanity.com/paper/2203.08354/) (2022)
- [CounTR: Transformer-based Generalised Visual Counting](https://mlsanity.com/paper/2208.13721/) (2022)
- [Localization in the Crowd with Topological Constraints](https://mlsanity.com/paper/2012.12482/) (2020)
- [A Low-Shot Object Counting Network With Iterative Prototype Adaptation](https://mlsanity.com/paper/2211.08217/) (2022)
- [CountGD: Multi-Modal Open-World Counting](https://mlsanity.com/paper/2407.04619/) (2024)
- [Zero-shot Object Counting](https://mlsanity.com/paper/2303.02001/) (2023)
- [Density Map Guided Object Detection in Aerial Images](https://mlsanity.com/paper/2004.05520/) (2020)
- [Rethinking Spatial Invariance of Convolutional Networks for Object Counting](https://mlsanity.com/paper/2206.05253/) (2022)
- [DAVE -- A Detect-and-Verify Paradigm for Low-Shot Counting](https://mlsanity.com/paper/2404.16622/) (2024)
- [VLCounter: Text-aware Visual Representation for Zero-Shot Object Counting](https://mlsanity.com/paper/2312.16580/) (2023)
- [Open-world Text-specified Object Counting](https://mlsanity.com/paper/2306.01851/) (2023)
- [Object Counting and Instance Segmentation with Image-level Supervision](https://mlsanity.com/paper/1903.02494/) (2019)
- [NAS-Count: Counting-by-Density with Neural Architecture Search](https://mlsanity.com/paper/2003.00217/) (2020)
- [DQ-DETR: DETR with Dynamic Query for Tiny Object Detection](https://mlsanity.com/paper/2404.03507/) (2024)
- [TasselNet: Counting maize tassels in the wild via local counts regression network](https://mlsanity.com/paper/1707.02290/) (2017)
- [Vision Transformer Off-the-Shelf: A Surprising Baseline for Few-Shot Class-Agnostic Counting](https://mlsanity.com/paper/2305.04440/) (2023)

## Built on by (most cited first, 10 of 10)

- [CountGD++: Generalized Prompting for Open-World Counting](https://mlsanity.com/paper/2512.23351/) (2025)
- [What is the Right Embedding Space for Contrastive Learning in Referring Expression Counting?](https://mlsanity.com/paper/2505.22850/) (2025)
- [Text-promptable Object Counting via Quantity Awareness Enhancement](https://mlsanity.com/paper/2507.06679/) (2025)
- [Chain-of-Look Spatial Reasoning for Dense Surgical Instrument Counting](https://mlsanity.com/paper/2602.11024/) (2026)
- [Decoupling What to Count and Where to See for Referring Expression Counting](https://mlsanity.com/paper/2510.24374/) (2025)
- [CountEx: Fine-Grained Counting via Exemplars and Exclusion](https://mlsanity.com/paper/2602.19432/) (2026)
- [The MixCount Dataset: Bridging the Data Gap for Open-Vocabulary Object Counting](https://mlsanity.com/paper/2605.18063/) (2026)
- [RT-Counter: Real-Time Text-Guided Open-Vocabulary Object Counting](https://mlsanity.com/paper/2606.17561/) (2026)
- [MambaCount: Efficient Text-guided Open-vocabulary Object Counting with Spatial Sparse State Space Duality Block](https://mlsanity.com/paper/2606.17650/) (2026)
- [ABACUS: Adapting Unified Foundation Model for Bridging Image Count Understanding and Generation](https://mlsanity.com/paper/2606.23835/) (2026)

## Abstract (arXiv)

Referring expression counting (REC) algorithms are for more flexible and interactive counting ability across varied fine-grained text expressions. However, the requirement for fine-grained attribute understanding poses challenges for prior arts, as they struggle to accurately align attribute information with correct visual patterns. Given the proven importance of ''visual density'', it is presumed that the limitations of current REC approaches stem from an under-exploration of ''contextual attribute density'' (CAD). In the scope of REC, we define CAD as the measure of the information intensity of one certain fine-grained attribute in visual regions. To model the CAD, we propose a U-shape CAD estimator in which referring expression and multi-scale visual features from GroundingDINO can interact with each other. With additional density supervision, we can effectively encode CAD, which is subsequently decoded via a novel attention procedure with CAD-refined queries. Integrating all these contributions, our framework significantly outperforms state-of-the-art REC methods, achieves 30% error reduction in counting metrics and a 10% improvement in localization accuracy. The surprising results shed light on the significance of contextual attribute density for REC. Code will be at github.com/Xu3XiWang/CAD-GD.