mlsanityData to 7 Oct 2026

An End-to-End Transformer Model for Crowd Localization

arXiv 2202.13065 ↗First posted 26 Feb 2022cs.CVcited by 74

Not on the map. Why?

Abstract (arXiv)

Crowd localization, predicting head positions, is a more practical and high-level task than simply counting. Existing methods employ pseudo-bounding boxes or pre-designed localization maps, relying on complex post-processing to obtain the head positions. In this paper, we propose an elegant, end-to-end Crowd Localization Transformer named CLTR that solves the task in the regression-based paradigm. The proposed method views the crowd localization as a direct set prediction problem, taking extracted features and trainable embeddings as input of the transformer-decoder. To reduce the ambiguous points and generate more reasonable matching results, we introduce a KMO-based Hungarian matcher, which adopts the nearby context as the auxiliary matching cost. Extensive experiments conducted on five datasets in various data settings show the effectiveness of our method. In particular, the proposed method achieves the best localization performance on the NWPU-Crowd, UCF-QNRF, and ShanghaiTech Part A datasets.

Key facts. Cited by 74 papers in the map (data through 7 Oct 2026). Builds on 39 of its 49 references that are in the map. First posted on arXiv 26 Feb 2022.

Builds on

39 of 49 references.

References · 39

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2020End-to-End Object Detection with Transformerscited by 7,384
  6. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  7. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  8. 2021Conditional DETR for Fast Training Convergencecited by 422
  9. 2018CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenescited by 267
  10. 2018Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowdscited by 186
  11. 2019Bayesian Loss for Crowd Count Estimation with Point Supervisioncited by 162
  12. 2021Rethinking Counting and Localization in Crowds:A Purely Point-Based Frameworkcited by 152
27 more
  1. 2020NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localizationcited by 151
  2. 2018Context-Aware Crowd Countingcited by 150
  3. 2021End-to-end Temporal Action Detection with Transformercited by 150
  4. 2019Learning from Synthetic Data for Crowd Counting in the Wildcited by 148
  5. 2020Distribution Matching for Crowd Countingcited by 143
  6. 2020JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Methodcited by 109
  7. 2019Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detectioncited by 73
  8. 2016Finding Tiny Facescited by 72
  9. 2020Localization in the Crowd with Topological Constraintscited by 68
  10. 2019Point in, Box out: Beyond Counting Persons in Crowdscited by 62
  11. 2021TransCrowd: weakly-supervised crowd counting with transformerscited by 61
  12. 2018Where are the Blobs: Counting by Localization with Point Supervisioncited by 54
  13. 2019Crowd Counting with Deep Structured Scale Integration Networkcited by 46
  14. 2019Multi-Level Bottom-Top and Top-Bottom Feature Fusion for Crowd Countingcited by 36
  15. 2020NAS-Count: Counting-by-Density with Neural Architecture Searchcited by 36
  16. 2020A Self-Training Approach for Point-Supervised Object Detection and Counting in Crowdscited by 36
  17. 2021Focal Inverse Distance Transform Maps for Crowd Localizationcited by 36
  18. 2019AutoScale: Learning to Scale for Crowd Counting and Localizationcited by 35
  19. 2019Learn to Scale: Generating Multipolar Normalized Density Maps for Crowd Countingcited by 32
  20. 2020Weighing Counts: Sequential Crowd Counting by Reinforcement Learningcited by 30
  21. 2021Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmarkcited by 30
  22. 2021CCTrans: Simplifying and Improving Crowd Counting with Transformercited by 30
  23. 2019SCAR: Spatial-/Channel-wise Attention Regression Networks for Crowd Countingcited by 28
  24. 2018Locating Objects Without Bounding Boxescited by 25
  25. 2020Learning Independent Instance Maps for Crowd Localizationcited by 24
  26. 2021Congested Crowd Instance Localization with Dilated Convolutional Swin Transformercited by 11
  27. 2021VisDrone-CC2020: The Vision Meets Drone Crowd Counting Challenge Resultscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 6; 2023: 15; 2024: 17; 2025: 24; 2026: 12.

74 papers.

Sort:

By area:

  1. 2024PointMamba: A Simple State Space Model for Point Cloud Analysiscited by 166
  2. 2023CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Modelcited by 47
  3. 2022Learning to Count Anything: Reference-less Class-agnostic Counting with Weak Supervisioncited by 41
  4. 2023Point-Query Quadtree for Crowd Counting, Localization, and Morecited by 40
  5. 2024A Survey of Camouflaged Object Detection and Beyondcited by 37
  6. 2023Vision Transformer Off-the-Shelf: A Surprising Baseline for Few-Shot Class-Agnostic Countingcited by 25
  7. 2024Improving Point-based Crowd Counting and Localization Based on Auxiliary Point Guidancecited by 22
  8. 2023CrowdDiff: Multi-hypothesis Crowd Density Estimation using Diffusion Modelscited by 20
  9. 2024Gramformer: Learning Crowd Counting via Graph-Modulated Transformercited by 19
  10. 2022Revisiting Crowd Counting: State-of-the-art, Trends, and Future Perspectivescited by 16
  11. 2023Regressor-Segmenter Mutual Prompt Learning for Crowd Countingcited by 16
  12. 2023Counting Crowds in Bad Weathercited by 14
38 more
  1. 2023Boosting Detection in Crowd Analysis via Underutilized Output Featurescited by 14
  2. 2024CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise Classificationcited by 12
  3. 2024CountFormer: Multi-View Crowd Counting Transformercited by 12
  4. 2023RGB-D Indiscernible Object Counting in Underwater Scenescited by 9
  5. 2022CrowdFormer: Weakly-supervised Crowd counting with Improved Generalizabilitycited by 8
  6. 2022Consistency-Aware Anchor Pyramid Network for Crowd Localizationcited by 8
  7. 2023DPA-P2PNet: Deformable Proposal-aware P2PNet for Accurate Point-based Cell Detectioncited by 8
  8. 2023Learning Discriminative Features for Crowd Countingcited by 8
  9. 2024FGENet: Fine-Grained Extraction Network for Congested Crowd Countingcited by 7
  10. 2024VMambaCC: A Visual State Space Model for Crowd Countingcited by 7
  11. 2025AquaticCLIP: A Vision-Language Foundation Model for Underwater Scene Analysiscited by 7
  12. 2023SoybeanNet: Transformer-Based Convolutional Neural Network for Soybean Pod Counting from Unmanned Aerial Vehicle (UAV) Imagescited by 6
  13. 2025CountingDINO: A Training-free Pipeline for Class-Agnostic Counting using Unsupervised Backbonescited by 6
  14. 2025Point-to-Region Loss for Semi-Supervised Point-Based Crowd Countingcited by 6
  15. 2022Glance to Count: Learning to Rank with Anchors for Weakly-supervised Crowd Countingcited by 5
  16. 2024Diffusion-based Data Augmentation for Object Counting Problemscited by 5
  17. 2025[De|Re]constructing VLMs' Reasoning in Countingcited by 5
  18. 2022Progressive Multi-resolution Loss for Crowd Countingcited by 4
  19. 2024Robust Zero-Shot Crowd Counting and Localization With Adaptive Resolution SAMcited by 4
  20. 2025Video Individual Counting for Moving Dronescited by 4
  21. 2025SoftHGNN: Soft Hypergraph Neural Networks for General Visual Recognitioncited by 4
  22. 2024The Effectiveness of a Simplified Model Structure for Crowd Countingcited by 3
  23. 2026UNICBench: UNIfied Counting Benchmark for MLLMcited by 3
  24. 2023Super-Resolution Information Enhancement For Crowd Countingcited by 2
  25. 2023Shifted Autoencoders for Point Annotation Restoration in Object Countingcited by 2
  26. 2024Few-shot Object Localizationcited by 2
  27. 2025SDVPT: Semantic-Driven Visual Prompt Tuning for Open-World Object Countingcited by 2
  28. 2025Text-promptable Object Counting via Quantity Awareness Enhancementcited by 2
  29. 2026Bootstrapping MLLM for Weakly-Supervised Class-Agnostic Object Countingcited by 2
  30. 2023Semi-supervised Cell Recognition under Point Supervisioncited by 1
  31. 2024Tree Counting by Bridging 3D Point Clouds with Imagerycited by 1
  32. 2024A Density-Guided Temporal Attention Transformer for Indiscernible Object Counting in Underwater Videocited by 1
  33. 2024Boosting Adverse Weather Crowd Counting via Multi-queue Contrastive Learningcited by 1
  34. 2025Depth-Assisted Network for Indiscernible Marine Object Counting with Adaptive Motion-Differentiated Feature Encodingcited by 1
  35. 2025Learning Extremely High Density Crowds as Active Matterscited by 1
  36. 2025Consistent-Point: Consistent Pseudo-Points for Semi-Supervised Crowd Counting and Localizationcited by 1
  37. 2025L2HCount:Generalizing Crowd Counting from Low to High Crowd Density via Density Simulationcited by 1
  38. 2025ProgRoCC: A Progressive Approach to Rough Crowd Countingcited by 1

50 most cited of 74 All 74 (JSON)