mlsanityData to 14 Oct 2026

Rethinking Global Context in Crowd Counting

arXiv 2105.10926 ↗First posted 23 May 2021cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

This paper investigates the role of global context for crowd counting. Specifically, a pure transformer is used to extract features with global information from overlapping image patches. Inspired by classification, we add a context token to the input sequence, to facilitate information exchange with tokens corresponding to image patches throughout transformer layers. Due to the fact that transformers do not explicitly model the tried-and-true channel-wise interactions, we propose a token-attention module (TAM) to recalibrate encoded features through channel-wise attention informed by the context token. Beyond that, it is adopted to predict the total person count of the image through regression-token module (RTM). Extensive experiments on various datasets, including ShanghaiTech, UCF-QNRF, JHU-CROWD++ and NWPU, demonstrate that the proposed context extraction techniques can significantly improve the performance over the baselines.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 40 of its 68 references that are in the map. First posted on arXiv 23 May 2021.

Builds on

40 of 68 references.

References · 40

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  5. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  6. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  7. 2020End-to-End Object Detection with Transformerscited by 7,414
  8. 2017Squeeze-and-Excitation Networkscited by 4,789
  9. 2018CBAM: Convolutional Block Attention Modulecited by 2,477
  10. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,591
  11. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,369
  12. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,101
28 more
  1. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 565
  2. 2020Conditional Convolutions for Instance Segmentationcited by 314
  3. 2018CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenescited by 267
  4. 2018Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowdscited by 186
  5. 2019Bayesian Loss for Crowd Count Estimation with Point Supervisioncited by 162
  6. 2020NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localizationcited by 151
  7. 2018Context-Aware Crowd Countingcited by 150
  8. 2019Learning from Synthetic Data for Crowd Counting in the Wildcited by 148
  9. 2020Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentationcited by 144
  10. 2020Distribution Matching for Crowd Countingcited by 143
  11. 2020JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Methodcited by 109
  12. 2017Switching Convolutional Neural Network for Crowd Countingcited by 93
  13. 2021TransCrowd: weakly-supervised crowd counting with transformerscited by 61
  14. 2019Crowd Counting and Density Estimation by Trellis Encoder-Decoder Networkcited by 56
  15. 2019Perspective-Guided Convolution Networks for Crowd Countingcited by 54
  16. 2019Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rankcited by 52
  17. 2018Revisiting Perspective Information for Efficient Crowd Countingcited by 49
  18. 2018Iterative Crowd Countingcited by 48
  19. 2019From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquercited by 48
  20. 2019Crowd Counting with Deep Structured Scale Integration Networkcited by 46
  21. 2020Learning Stereo from Single Imagescited by 45
  22. 2017CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Countingcited by 41
  23. 2019Multi-Level Bottom-Top and Top-Bottom Feature Fusion for Crowd Countingcited by 36
  24. 2020NAS-Count: Counting-by-Density with Neural Architecture Searchcited by 36
  25. 2019Counting with Focus for Freecited by 33
  26. 2020Towards Using Count-level Weak Supervision for Crowd Countingcited by 33
  27. 2020Weighing Counts: Sequential Crowd Counting by Reinforcement Learningcited by 30
  28. 2018Divide and Grow: Capturing Huge Diversity in Crowd Images with Incrementally Growing CNNcited by 19

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 5; 2024: 0; 2025: 0; 2026: 2.

8 papers.

  1. 2023Point-Query Quadtree for Crowd Counting, Localization, and Morecited by 40
  2. 2022Learning Local and Global Temporal Contexts for Video Semantic Segmentationcited by 24
  3. 2023Counting Crowds in Bad Weathercited by 14
  4. 2023Revisiting Computer-Aided Tuberculosis Diagnosiscited by 6
  5. 2023Semi-Supervised Crowd Counting with Contextual Modeling: Facilitating Holistic Understanding of Crowd Scenescited by 6
  6. 2023SQLNet: Scale-Modulated Query and Localization Network for Few-Shot Class-Agnostic Countingcited by 5
  7. 2026VLM-Loc: Localization in Point Cloud Maps via Vision-Language Modelscited by 4
  8. 2026Amped: Adaptive Multi-stage Non-edge Pruning for Edge Detectioncited by 0