# Boosting Detection in Crowd Analysis via Underutilized Output Features

arXiv: https://arxiv.org/abs/2308.16187 · HTML: https://mlsanity.com/paper/2308.16187/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 48 of its 73 references that are in the map.
- First posted on arXiv 30 Aug 2023.

## Builds on (most cited first, 30 of 48)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Soft-NMS -- Improving Object Detection With One Line of Code](https://mlsanity.com/paper/1704.04503/) (2017)
- [WIDER FACE: A Face Detection Benchmark](https://mlsanity.com/paper/1511.06523/) (2015)
- [CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes](https://mlsanity.com/paper/1802.10062/) (2018)
- [Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds](https://mlsanity.com/paper/1808.01050/) (2018)
- [FSRNet: End-to-End Learning Face Super-Resolution with Facial Priors](https://mlsanity.com/paper/1711.10703/) (2017)
- [Bayesian Loss for Crowd Count Estimation with Point Supervision](https://mlsanity.com/paper/1908.03684/) (2019)
- [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)
- [Context-Aware Crowd Counting](https://mlsanity.com/paper/1811.10452/) (2018)
- [Learning from Synthetic Data for Crowd Counting in the Wild](https://mlsanity.com/paper/1903.03303/) (2019)
- [Distribution Matching for Crowd Counting](https://mlsanity.com/paper/2009.13077/) (2020)
- [DSFD: Dual Shot Face Detector](https://mlsanity.com/paper/1810.10220/) (2018)
- [Learning non-maximum suppression](https://mlsanity.com/paper/1705.02950/) (2017)
- [JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method](https://mlsanity.com/paper/2004.03597/) (2020)
- [Touch and Go: Learning from Human-Collected Vision and Touch](https://mlsanity.com/paper/2211.12498/) (2022)
- [An End-to-End Transformer Model for Crowd Localization](https://mlsanity.com/paper/2202.13065/) (2022)
- [Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detection](https://mlsanity.com/paper/1906.07538/) (2019)
- [Boosting Crowd Counting via Multifaceted Attention](https://mlsanity.com/paper/2203.02636/) (2022)
- [Finding Tiny Faces](https://mlsanity.com/paper/1612.04402/) (2016)
- [Localization in the Crowd with Topological Constraints](https://mlsanity.com/paper/2012.12482/) (2020)
- [Invariant Grounding for Video Question Answering](https://mlsanity.com/paper/2206.02349/) (2022)
- [Adaptive NMS: Refining Pedestrian Detection in a Crowd](https://mlsanity.com/paper/1904.03629/) (2019)
- [Point in, Box out: Beyond Counting Persons in Crowds](https://mlsanity.com/paper/1904.01333/) (2019)
- [PyramidBox: A Context-assisted Single Shot Face Detector](https://mlsanity.com/paper/1803.07737/) (2018)
- [What Can Be Transferred: Unsupervised Domain Adaptation for Endoscopic Lesions Segmentation](https://mlsanity.com/paper/2004.11500/) (2020)
- [Revisiting Perspective Information for Efficient Crowd Counting](https://mlsanity.com/paper/1807.01989/) (2018)
- [Iterative Crowd Counting](https://mlsanity.com/paper/1807.09959/) (2018)
- [From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquer](https://mlsanity.com/paper/1908.06473/) (2019)

## Built on by (most cited first, 14 of 14)

- [WorDepth: Variational Language Prior for Monocular Depth Estimation](https://mlsanity.com/paper/2404.03635/) (2024)
- [NeuroBind: Towards Unified Multimodal Representations for Neural Signals](https://mlsanity.com/paper/2407.14020/) (2024)
- [CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise Classification](https://mlsanity.com/paper/2403.09281/) (2024)
- [VCISR: Blind Single Image Super-Resolution with Video Compression Synthetic Data](https://mlsanity.com/paper/2311.00996/) (2023)
- [Storyboard guided Alignment for Fine-grained Video Action Recognition](https://mlsanity.com/paper/2410.14238/) (2024)
- [Shifted Autoencoders for Point Annotation Restoration in Object Counting](https://mlsanity.com/paper/2312.07190/) (2023)
- [ZIP: Scalable Crowd Counting via Zero-Inflated Poisson Modeling](https://mlsanity.com/paper/2506.19955/) (2025)
- [Text-promptable Object Counting via Quantity Awareness Enhancement](https://mlsanity.com/paper/2507.06679/) (2025)
- [Bootstrapping MLLM for Weakly-Supervised Class-Agnostic Object Counting](https://mlsanity.com/paper/2602.12774/) (2026)
- [Depth-Assisted Network for Indiscernible Marine Object Counting with Adaptive Motion-Differentiated Feature Encoding](https://mlsanity.com/paper/2503.08152/) (2025)
- [Exploring Scale Shift in Crowd Localization under the Context of Domain Generalization](https://mlsanity.com/paper/2510.19330/) (2025)
- [FSCA-Net: Feature-Separated Cross-Attention Network for Robust Multi-Dataset Training](https://mlsanity.com/paper/2602.01540/) (2026)
- [DenseControl: Instance-Level Controllable Synthesis of Dense Crowd Image](https://mlsanity.com/paper/2606.15592/) (2026)
- [Depth-Guided Video Object Counting in Crowded Scenes](https://mlsanity.com/paper/2608.06236/) (2026)

## Abstract (arXiv)

Detection-based methods have been viewed unfavorably in crowd analysis due to their poor performance in dense crowds. However, we argue that the potential of these methods has been underestimated, as they offer crucial information for crowd analysis that is often ignored. Specifically, the area size and confidence score of output proposals and bounding boxes provide insight into the scale and density of the crowd. To leverage these underutilized features, we propose Crowd Hat, a plug-and-play module that can be easily integrated with existing detection models. This module uses a mixed 2D-1D compression technique to refine the output features and obtain the spatial and numerical distribution of crowd-specific information. Based on these features, we further propose region-adaptive NMS thresholds and a decouple-then-align paradigm that address the major limitations of detection-based methods. Our extensive evaluations on various crowd analysis tasks, including crowd counting, localization, and detection, demonstrate the effectiveness of utilizing output features and the potential of detection-based methods in crowd analysis.