mlsanityData to 7 Oct 2026

CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes

arXiv 1802.10062 ↗First posted 27 Feb 2018cs.CVcited by 267

Not on the map. Why?

Abstract (arXiv)

We propose a network for Congested Scene Recognition called CSRNet to provide a data-driven and deep learning method that can understand highly congested scenes and perform accurate count estimation as well as present high-quality density maps. The proposed CSRNet is composed of two major components: a convolutional neural network (CNN) as the front-end for 2D feature extraction and a dilated CNN for the back-end, which uses dilated kernels to deliver larger reception fields and to replace pooling operations. CSRNet is an easy-trained model because of its pure convolutional structure. We demonstrate CSRNet on four datasets (ShanghaiTech dataset, the UCF_CC_50 dataset, the WorldEXPO'10 dataset, and the UCSD dataset) and we deliver the state-of-the-art performance. In the ShanghaiTech Part_B dataset, CSRNet achieves 47.3% lower Mean Absolute Error (MAE) than the previous state-of-the-art method. We extend the targeted applications for counting other objects, such as the vehicle in TRANCOS dataset. Results show that CSRNet significantly improves the output quality with 15.4% lower MAE than the previous state-of-the-art approach.

Key facts. Cited by 267 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 53; 2022: 66; 2023: 41; 2024: 42; 2025: 33; 2026: 32.

267 papers.

Sort:

By area:

  1. 2021Rethinking Counting and Localization in Crowds:A Purely Point-Based Frameworkcited by 152
  2. 2021Learning To Count Everythingcited by 149
  3. 2022An End-to-End Transformer Model for Crowd Localizationcited by 74
  4. 2022Boosting Crowd Counting via Multifaceted Attentioncited by 73
  5. 2023Deep Learning for Time Series Classification and Extrinsic Regression: A Current Surveycited by 68
  6. 2022Few-shot Object Counting with Similarity-Aware Feature Enhancementcited by 62
  7. 2021TransCrowd: weakly-supervised crowd counting with transformerscited by 61
  8. 2022Rethinking Spatial Invariance of Convolutional Networks for Object Countingcited by 54
  9. 2023CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Modelcited by 47
  10. 2023Improving Deep Regression with Ordinal Entropycited by 44
  11. 2022Learning to Count Anything: Reference-less Class-agnostic Counting with Weak Supervisioncited by 41
  12. 2023STEERER: Resolving Scale Variations for Counting and Localization via Selective Inheritance Learningcited by 41
38 more
  1. 2023Point-Query Quadtree for Crowd Counting, Localization, and Morecited by 40
  2. 2021Harnessing Perceptual Adversarial Patches for Crowd Countingcited by 39
  3. 2021Spatial Uncertainty-Aware Semi-Supervised Crowd Countingcited by 38
  4. 2021Focal Inverse Distance Transform Maps for Crowd Localizationcited by 36
  5. 2022When Counting Meets HMER: Counting-Aware Network for Handwritten Mathematical Expression Recognitioncited by 35
  6. 2022Exemplar Free Class Agnostic Countingcited by 32
  7. 2021Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmarkcited by 30
  8. 2021CCTrans: Simplifying and Improving Crowd Counting with Transformercited by 30
  9. 2022Cross-View Cross-Scene Multi-View Crowd Countingcited by 28
  10. 2021Single-Layer Vision Transformers for More Accurate Early Exits with Less Overheadcited by 26
  11. 2021Leveraging Self-Supervision for Cross-Domain Crowd Countingcited by 24
  12. 2023Calibrating Uncertainty for Semi-Supervised Crowd Countingcited by 22
  13. 2024Improving Point-based Crowd Counting and Localization Based on Auxiliary Point Guidancecited by 22
  14. 2021Uniformity in Heterogeneity:Diving Deep into Count Interval Partition for Crowd Countingcited by 20
  15. 2023CrowdDiff: Multi-hypothesis Crowd Density Estimation using Diffusion Modelscited by 20
  16. 2022Discrete-Constrained Regression for Local Counting Modelscited by 19
  17. 2024Gramformer: Learning Crowd Counting via Graph-Modulated Transformercited by 19
  18. 2021Direct Measure Matching for Crowd Countingcited by 18
  19. 2022DR.VIC: Decomposition and Reasoning for Video Individual Countingcited by 18
  20. 2022Semi-supervised Crowd Counting via Density Agencycited by 18
  21. 2022Redesigning Multi-Scale Neural Network for Crowd Countingcited by 17
  22. 2024Single Domain Generalization for Crowd Countingcited by 17
  23. 2022Revisiting Crowd Counting: State-of-the-art, Trends, and Future Perspectivescited by 16
  24. 2023Regressor-Segmenter Mutual Prompt Learning for Crowd Countingcited by 16
  25. 2024OmniCount: Multi-label Object Counting with Semantic-Geometric Priorscited by 16
  26. 2021Crowd Counting via Perspective-Guided Fractional-Dilation Convolutioncited by 15
  27. 2021Variational Attention: Propagating Domain-Specific Knowledge for Multi-Domain Learning in Crowd Countingcited by 15
  28. 2022TAFNet: A Three-Stream Adaptive Fusion Network for RGB-T Crowd Countingcited by 15
  29. 2022Backbones-Review: Feature Extraction Networks for Deep Learning and Deep Reinforcement Learning Approachescited by 15
  30. 2023Counting Crowds in Bad Weathercited by 14
  31. 2023Boosting Detection in Crowd Analysis via Underutilized Output Featurescited by 14
  32. 2024NWPU-MOC: A Benchmark for Fine-grained Multi-category Object Counting in Aerial Imagescited by 14
  33. 2021Video Crowd Localization with Multi-focus Gaussian Neighborhood Attention and a Large-Scale Benchmarkcited by 13
  34. 2022FusionCount: Efficient Crowd Counting via Multiscale Feature Fusioncited by 13
  35. 2021Audio-Visual Transformer Based Crowd Countingcited by 12
  36. 2021Scene-Adaptive Attention Network for Crowd Countingcited by 12
  37. 2024AFreeCA: Annotation-Free Counting for Allcited by 12
  38. 2024CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise Classificationcited by 12

50 most cited of 267 All 267 (JSON)