# Decoupling What to Count and Where to See for Referring Expression Counting

arXiv: https://arxiv.org/abs/2510.24374 · HTML: https://mlsanity.com/paper/2510.24374/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 47 references that are in the map.
- First posted on arXiv 28 Oct 2025.

## Builds on (most cited first, 30 of 36)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Detection and Tracking Meet Drones Challenge](https://mlsanity.com/paper/2001.06303/) (2020)
- [Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds](https://mlsanity.com/paper/1808.01050/) (2018)
- [Bayesian Loss for Crowd Count Estimation with Point Supervision](https://mlsanity.com/paper/1908.03684/) (2019)
- [Drone-based Object Counting by Spatially Regularized Regional Proposal Network](https://mlsanity.com/paper/1707.05972/) (2017)
- [Rethinking Counting and Localization in Crowds:A Purely Point-Based Framework](https://mlsanity.com/paper/2107.12746/) (2021)
- [NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization](https://mlsanity.com/paper/2001.03360/) (2020)
- [Learning To Count Everything](https://mlsanity.com/paper/2104.08391/) (2021)
- [JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method](https://mlsanity.com/paper/2004.03597/) (2020)
- [UA-DETRAC: A New Benchmark and Protocol for Multi-Object Detection and Tracking](https://mlsanity.com/paper/1511.04136/) (2015)
- [CLIP-Count: Towards Text-Guided Zero-Shot Object Counting](https://mlsanity.com/paper/2305.07304/) (2023)
- [CounTR: Transformer-based Generalised Visual Counting](https://mlsanity.com/paper/2208.13721/) (2022)
- [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)
- [Perspective-Guided Convolution Networks for Crowd Counting](https://mlsanity.com/paper/1909.06966/) (2019)
- [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)
- [STEERER: Resolving Scale Variations for Counting and Localization via Selective Inheritance Learning](https://mlsanity.com/paper/2308.10468/) (2023)
- [Point-Query Quadtree for Crowd Counting, Localization, and More](https://mlsanity.com/paper/2308.13814/) (2023)
- [CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting](https://mlsanity.com/paper/2504.15485/) (2025)
- [Vision Transformer Off-the-Shelf: A Surprising Baseline for Few-Shot Class-Agnostic Counting](https://mlsanity.com/paper/2305.04440/) (2023)
- [Crowded Scene Analysis: A Survey](https://mlsanity.com/paper/1502.01812/) (2015)
- [T2ICount: Enhancing Cross-modal Understanding for Zero-Shot Counting](https://mlsanity.com/paper/2502.20625/) (2025)
- [A Fixed-Point Approach to Unified Prompt-Based Counting](https://mlsanity.com/paper/2403.10236/) (2024)
- [Exploring Contextual Attribute Density in Referring Expression Counting](https://mlsanity.com/paper/2503.12460/) (2025)
- [Counting Stacked Objects](https://mlsanity.com/paper/2411.19149/) (2024)
- [DISCount: Counting in Large Image Collections with Detector-Based Importance Sampling](https://mlsanity.com/paper/2306.03151/) (2023)
- [Single Domain Generalization for Few-Shot Counting via Universal Representation Matching](https://mlsanity.com/paper/2505.16778/) (2025)
- [Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting](https://mlsanity.com/paper/2505.21943/) (2025)

## Built on by (most cited first, 1 of 1)

- [The MixCount Dataset: Bridging the Data Gap for Open-Vocabulary Object Counting](https://mlsanity.com/paper/2605.18063/) (2026)

## Abstract (arXiv)

Referring Expression Counting (REC) extends class-level object counting to the fine-grained subclass-level, aiming to enumerate objects matching a textual expression that specifies both the class and distinguishing attribute. A fundamental challenge, however, has been overlooked: annotation points are typically placed on class-representative locations (e.g., heads), forcing models to focus on class-level features while neglecting attribute information from other visual regions (e.g., legs for "walking"). To address this, we propose W2-Net, a novel framework that explicitly decouples the problem into "what to count" and "where to see" via a dual-query mechanism. Specifically, alongside the standard what-to-count (w2c) queries that localize the object, we introduce dedicated where-to-see (w2s) queries. The w2s queries are guided to seek and extract features from attribute-specific visual regions, enabling precise subclass discrimination. Furthermore, we introduce Subclass Separable Matching (SSM), a novel matching strategy that incorporates a repulsive force to enhance inter-subclass separability during label assignment. W2-Net significantly outperforms the state-of-the-art on the REC-8K dataset, reducing counting error by 22.5% (validation) and 18.0% (test), and improving localization F1 by 7% and 8%, respectively. Code will be available.