mlsanityData to 7 Oct 2026

CCTrans: Simplifying and Improving Crowd Counting with Transformer

arXiv 2109.14483 ↗First posted 29 Sep 2021cs.CVcited by 30

Not on the map. Why?

Abstract (arXiv)

Most recent methods used for crowd counting are based on the convolutional neural network (CNN), which has a strong ability to extract local features. But CNN inherently fails in modeling the global context due to the limited receptive fields. However, the transformer can model the global context easily. In this paper, we propose a simple approach called CCTrans to simplify the design pipeline. Specifically, we utilize a pyramid vision transformer backbone to capture the global crowd information, a pyramid feature aggregation (PFA) model to combine low-level and high-level features, an efficient regression head with multi-scale dilated convolution (MDC) to predict density maps. Besides, we tailor the loss functions for our pipeline. Without bells and whistles, extensive experiments demonstrate that our method achieves new state-of-the-art results on several benchmarks both in weakly and fully-supervised crowd counting. Moreover, we currently rank No.1 on the leaderboard of NWPU-Crowd. Our code will be made available.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Builds on 34 of its 49 references that are in the map. First posted on arXiv 29 Sep 2021.

Builds on

34 of 49 references.

References · 34

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  3. 2020End-to-End Object Detection with Transformerscited by 7,384
  4. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  5. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  6. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  7. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  8. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,368
  9. 2021Twins: Revisiting the Design of Spatial Attention in Vision Transformerscited by 565
  10. 2021Conditional Positional Encodings for Vision Transformerscited by 402
  11. 2018CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenescited by 267
  12. 2018Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowdscited by 186
22 more
  1. 2019Bayesian Loss for Crowd Count Estimation with Point Supervisioncited by 162
  2. 2021Rethinking Counting and Localization in Crowds:A Purely Point-Based Frameworkcited by 152
  3. 2020NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localizationcited by 151
  4. 2018Context-Aware Crowd Countingcited by 150
  5. 2019Learning from Synthetic Data for Crowd Counting in the Wildcited by 148
  6. 2020Distribution Matching for Crowd Countingcited by 143
  7. 2017Receptive Field Block Net for Accurate and Fast Object Detectioncited by 140
  8. 2017Switching Convolutional Neural Network for Crowd Countingcited by 93
  9. 2019Point in, Box out: Beyond Counting Persons in Crowdscited by 62
  10. 2021TransCrowd: weakly-supervised crowd counting with transformerscited by 61
  11. 2017Generating High-Quality Crowd Density Maps using Contextual Pyramid CNNscited by 55
  12. 2019Perspective-Guided Convolution Networks for Crowd Countingcited by 54
  13. 2019Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rankcited by 52
  14. 2018Revisiting Perspective Information for Efficient Crowd Countingcited by 49
  15. 2019From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquercited by 48
  16. 2019Crowd Counting with Deep Structured Scale Integration Networkcited by 46
  17. 2018ADCrowdNet: An Attention-injective Deformable Convolutional Network for Crowd Understandingcited by 45
  18. 2021Spatial Uncertainty-Aware Semi-Supervised Crowd Countingcited by 38
  19. 2019Counting with Focus for Freecited by 33
  20. 2020Towards Using Count-level Weak Supervision for Crowd Countingcited by 33
  21. 2020Weighing Counts: Sequential Crowd Counting by Reinforcement Learningcited by 30
  22. 2020Adaptive Mixture Regression Network with Local Counting Map for Crowd Countingcited by 28

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 7; 2023: 10; 2024: 6; 2025: 5; 2026: 1.

30 papers.

Sort:

By area:

  1. 2022An End-to-End Transformer Model for Crowd Localizationcited by 74
  2. 2023Point-Query Quadtree for Crowd Counting, Localization, and Morecited by 40
  3. 2022Recent Advances in Vision Transformer: A Survey and Outlook of Recent Workcited by 21
  4. 2023CrowdDiff: Multi-hypothesis Crowd Density Estimation using Diffusion Modelscited by 20
  5. 2022Revisiting Crowd Counting: State-of-the-art, Trends, and Future Perspectivescited by 16
  6. 2023Counting Crowds in Bad Weathercited by 14
  7. 2023Boosting Detection in Crowd Analysis via Underutilized Output Featurescited by 14
  8. 2021Scene-Adaptive Attention Network for Crowd Countingcited by 12
  9. 2024CountFormer: Multi-View Crowd Counting Transformercited by 12
  10. 2022CrowdFormer: Weakly-supervised Crowd counting with Improved Generalizabilitycited by 8
  11. 2023Focus for Free in Density-Based Countingcited by 8
  12. 2023RGB-T Multi-Modal Crowd Counting Based on Transformercited by 7
18 more
  1. 2024Vehicle Perception from Satellitecited by 7
  2. 2022Joint CNN and Transformer Network via weakly supervised Learning for efficient crowd countingcited by 6
  3. 2023SoybeanNet: Transformer-Based Convolutional Neural Network for Soybean Pod Counting from Unmanned Aerial Vehicle (UAV) Imagescited by 6
  4. 2023SQLNet: Scale-Modulated Query and Localization Network for Few-Shot Class-Agnostic Countingcited by 5
  5. 2025SoftHGNN: Soft Hypergraph Neural Networks for General Visual Recognitioncited by 4
  6. 2024The Effectiveness of a Simplified Model Structure for Crowd Countingcited by 3
  7. 2024DenseTrack: Drone-based Crowd Tracking via Density-aware Motion-appearance Synergycited by 3
  8. 2023Visual Crowd Analysis: Open Research Problemscited by 2
  9. 2023Why Existing Multimodal Crowd Counting Datasets Can Lead to Unfulfilled Expectations in Real-World Applicationscited by 1
  10. 2024Efficient Masked AutoEncoder for Video Object Counting and A Large-Scale Benchmarkcited by 1
  11. 2025ProgRoCC: A Progressive Approach to Rough Crowd Countingcited by 1
  12. 2022MAFNet: A Multi-Attention Fusion Network for RGB-T Crowd Countingcited by 0
  13. 2022A Unified Object Counting Network with Object Occupation Priorcited by 0
  14. 2024Vision Transformers for Weakly-Supervised Microorganism Enumerationcited by 0
  15. 2025Constrained Gaussian Process Motion Planning via Stein Variational Newton Inferencecited by 0
  16. 2025TP-MVCC: Tri-plane Multi-view Fusion Model for Silkie Chicken Countingcited by 0
  17. 2025Getting the Numbers Rightunicodex2014Modelling Multi-Class Object Counting in Dense and Varied Scenescited by 0
  18. 2026Count Anythingcited by 0