mlsanityData to 14 Oct 2026

Context-Aware Crowd Counting

arXiv 1811.10452 ↗First posted 26 Nov 2018cs.CVcited by 150

Not on the map. Why?

Abstract (arXiv)

State-of-the-art methods for counting people in crowded scenes rely on deep networks to estimate crowd density. They typically use the same filters over the whole image or over large image patches. Only then do they estimate local scale to compensate for perspective distortion. This is typically achieved by training an auxiliary classifier to select, for predefined image patches, the best kernel size among a limited set of choices. As such, these methods are not end-to-end trainable and restricted in the scope of context they can leverage. In this paper, we introduce an end-to-end trainable deep architecture that combines features obtained using multiple receptive field sizes and learns the importance of each such feature at each image location. In other words, our approach adaptively encodes the scale of the contextual information required to accurately predict crowd density. This yields an algorithm that outperforms state-of-the-art crowd counting methods, especially when perspective effects are strong.

Key facts. Cited by 150 papers in the map (data through 14 Oct 2026). First posted on arXiv 26 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 37; 2022: 32; 2023: 24; 2024: 22; 2025: 21; 2026: 14.

150 papers.

Sort:

By area:

  1. 2021Rethinking Counting and Localization in Crowds:A Purely Point-Based Frameworkcited by 152
  2. 2021Learning To Count Everythingcited by 150
  3. 2022An End-to-End Transformer Model for Crowd Localizationcited by 74
  4. 2022Boosting Crowd Counting via Multifaceted Attentioncited by 73
  5. 2021TransCrowd: weakly-supervised crowd counting with transformerscited by 61
  6. 2023Zero-shot Object Countingcited by 57
  7. 2022Few-shot Object Counting and Detectioncited by 55
  8. 2024DAVE -- A Detect-and-Verify Paradigm for Low-Shot Countingcited by 49
  9. 2023VLCounter: Text-aware Visual Representation for Zero-Shot Object Countingcited by 45
  10. 2022TransRAC: Encoding Multi-scale Temporal Correlation with Transformers for Repetitive Action Countingcited by 44
  11. 2023STEERER: Resolving Scale Variations for Counting and Localization via Selective Inheritance Learningcited by 41
  12. 2023Point-Query Quadtree for Crowd Counting, Localization, and Morecited by 40
38 more
  1. 2021Harnessing Perceptual Adversarial Patches for Crowd Countingcited by 39
  2. 2021Spatial Uncertainty-Aware Semi-Supervised Crowd Countingcited by 38
  3. 2021Focal Inverse Distance Transform Maps for Crowd Localizationcited by 36
  4. 2022Exemplar Free Class Agnostic Countingcited by 32
  5. 2021Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmarkcited by 31
  6. 2021CCTrans: Simplifying and Improving Crowd Counting with Transformercited by 30
  7. 2022Cross-View Cross-Scene Multi-View Crowd Countingcited by 28
  8. 2021Leveraging Self-Supervision for Cross-Domain Crowd Countingcited by 24
  9. 2023Calibrating Uncertainty for Semi-Supervised Crowd Countingcited by 22
  10. 2024A Novel Unified Architecture for Low-Shot Counting by Detection and Segmentationcited by 21
  11. 2021Uniformity in Heterogeneity:Diving Deep into Count Interval Partition for Crowd Countingcited by 20
  12. 2023CrowdDiff: Multi-hypothesis Crowd Density Estimation using Diffusion Modelscited by 20
  13. 2024Teach CLIP to Develop a Number Sense for Ordinal Regressioncited by 20
  14. 2021Direct Measure Matching for Crowd Countingcited by 18
  15. 2022Revisiting Crowd Counting: State-of-the-art, Trends, and Future Perspectivescited by 16
  16. 2023Regressor-Segmenter Mutual Prompt Learning for Crowd Countingcited by 16
  17. 2021Crowd Counting via Perspective-Guided Fractional-Dilation Convolutioncited by 15
  18. 2022Backbones-Review: Feature Extraction Networks for Deep Learning and Deep Reinforcement Learning Approachescited by 15
  19. 2025CrowdVLM-R1: Expanding R1 Ability to Vision Language Model for Crowd Counting using Fuzzy Group Relative Policy Rewardcited by 15
  20. 2023Boosting Detection in Crowd Analysis via Underutilized Output Featurescited by 14
  21. 2024NWPU-MOC: A Benchmark for Fine-grained Multi-category Object Counting in Aerial Imagescited by 14
  22. 2021Video Crowd Localization with Multi-focus Gaussian Neighborhood Attention and a Large-Scale Benchmarkcited by 13
  23. 2021Object Counting: You Only Need to Look at Onecited by 13
  24. 2022FusionCount: Efficient Crowd Counting via Multiscale Feature Fusioncited by 13
  25. 2021Audio-Visual Transformer Based Crowd Countingcited by 12
  26. 2021Scene-Adaptive Attention Network for Crowd Countingcited by 12
  27. 2024CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise Classificationcited by 12
  28. 2024CountFormer: Multi-View Crowd Counting Transformercited by 12
  29. 2021Adaptive Convolutions with Per-pixel Dynamic Filter Atomcited by 11
  30. 2024Mind the Prompt: A Novel Benchmark for Prompt-based Class-Agnostic Countingcited by 11
  31. 2021Dense Point Prediction: A Simple Baseline for Crowd Counting and Localizationcited by 10
  32. 2021Coarse to Fine: Domain Adaptive Crowd Counting via Adversarial Scoring Networkcited by 10
  33. 2022Backdoor Attacks on Crowd Countingcited by 10
  34. 2021Spatiotemporal Dilated Convolution with Uncertain Matching for Video-based Crowd Estimationcited by 9
  35. 2022Forget Less, Count Better: A Domain-Incremental Self-Distillation Learning Benchmark for Lifelong Crowd Countingcited by 9
  36. 2023Zero-Shot Object Counting with Language-Vision Modelscited by 9
  37. 2021Rethinking Global Context in Crowd Countingcited by 8
  38. 2022CrowdFormer: Weakly-supervised Crowd counting with Improved Generalizabilitycited by 8

50 most cited of 150 All 150 (JSON)