Crowd Counting

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

13 leaderboard tables shown for this task, 13 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 13 until expanded.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

23 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 154 papers with code (371 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Densely Connected Convolutional Networks
  25 Aug 2016 146 repositories listed Syntology ran 18 of 71 samples · 53 unverified · 7 pointer-only (licence)
  Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output.
• SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
  2 Nov 2015 74 repositories listed Syntology ran 9 of 44 samples · 35 unverified · 10 pointer-only (licence)
  We show that SegNet provides good performance with competitive inference time and more efficient inference memory-wise as compared to other architectures.
• CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes
  27 Feb 2018 11 repositories listed Syntology ran 5 of 15 samples · 10 unverified · 5 pointer-only (licence)
  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.
• From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquer
  15 Aug 2019 5 repositories listed Syntology ran 3 of 8 samples · 5 unverified · 3 pointer-only (licence)
  A dense region can always be divided until sub-region counts are within the previously observed closed set.
• NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization
  10 Jan 2020 4 repositories listed Syntology ran 5 of 10 samples · 5 unverified
  In the last decade, crowd counting and localization attract much attention of researchers due to its wide-spread applications, including crowd monitoring, public safety, space design, etc.
• Single-Image Crowd Counting via Multi-Column Convolutional Neural Network
  1 Jan 2016 4 repositories listed
  To this end, we have proposed a simple but effective Multi-column Convolutional Neural Network (MCNN) architecture to map the image to its crowd density map.
• Inception-Based Crowd Counting -- Being Fast while Remaining Accurate
  18 Oct 2022 3 repositories listed
  Recent sophisticated CNN-based algorithms have demonstrated their extraordinary ability to automate counting crowds from images, thanks to their structures which are designed to address the issue of various head scales.
• Uniformity in Heterogeneity:Diving Deep into Count Interval Partition for Crowd Counting
  27 Jul 2021 3 repositories listed
  Therefore, we propose a novel count interval partition criterion called Uniform Error Partition (UEP), which always keeps the expected counting error contributions equal for all intervals to minimize the prediction risk.
• Rethinking Counting and Localization in Crowds:A Purely Point-Based Framework
  27 Jul 2021 3 repositories listed
  In this paper, we propose a purely point-based framework for joint crowd counting and individual localization.
• Focal Inverse Distance Transform Maps for Crowd Localization
  16 Feb 2021 3 repositories listed
  Most regression-based methods utilize convolution neural networks (CNN) to regress a density map, which can not accurately locate the instance in the extremely dense scene, attributed to two crucial reasons: 1) the…
• CNN-based Density Estimation and Crowd Counting: A Survey
  28 Mar 2020 3 repositories listed
  Through our analysis, we expect to make reasonable inference and prediction for the future development of crowd counting, and meanwhile, it can also provide feasible solutions for the problem of object counting in other…
• C^3 Framework: An Open-source PyTorch Code for Crowd Counting
  5 Jul 2019 3 repositories listed
  This technical report attempts to provide efficient and solid kits addressed on the field of crowd counting, which is denoted as Crowd Counting Code Framework (C³F).
• Context-Aware Crowd Counting
  26 Nov 2018 3 repositories listed Syntology ran 1 of 2 samples · 1 unverified
  State-of-the-art methods for counting people in crowded scenes rely on deep networks to estimate crowd density.
• CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model
  9 Apr 2023 2 repositories listed Syntology ran 0 of 1 samples · 1 unverified · 1 pointer-only (licence)
  To the best of our knowledge, CrowdCLIP is the first to investigate the vision language knowledge to solve the counting problem.
• DR.VIC: Decomposition and Reasoning for Video Individual Counting
  23 Mar 2022 2 repositories listed Syntology ran 6 of 11 samples · 5 unverified · 11 pointer-only (licence)
  Instead of relying on the Multiple Object Tracking (MOT) techniques, we propose to solve the problem by decomposing all pedestrians into the initial pedestrians who existed in the first frame and the new pedestrians…
• Deep Rank-Consistent Pyramid Model for Enhanced Crowd Counting
  13 Jan 2022 2 repositories listed
  Specifically, we propose a Deep Rank-consistEnt pyrAmid Model (DREAM), which makes full use of rank consistency across coarse-to-fine pyramid features in latent spaces for enhanced crowd counting with massive unlabeled…
• CCTrans: Simplifying and Improving Crowd Counting with Transformer
  29 Sep 2021 2 repositories listed Syntology ran 2 of 6 samples · 4 unverified · 2 pointer-only (licence)
  However, the transformer can model the global context easily.
• A Self-Training Approach for Point-Supervised Object Detection and Counting in Crowds
  25 Jul 2020 2 repositories listed
  In this paper, we propose a novel self-training approach named Crowd-SDNet that enables a typical object detector trained only with point-level annotations (i.
• Exploit the potential of Multi-column architecture for Crowd Counting
  11 Jul 2020 2 repositories listed
  To the best of our knowledge, PSNet is the first work to explicitly address scale limitation and feature similarity in multi-column design.
• Efficient Crowd Counting via Structured Knowledge Transfer
  23 Mar 2020 2 repositories listed
  Crowd counting is an application-oriented task and its inference efficiency is crucial for real-world applications.
• Encoder-Decoder Based Convolutional Neural Networks with Multi-Scale-Aware Modules for Crowd Counting
  12 Mar 2020 2 repositories listed
  Inspired by SFANet, the first model, which is named M-SFANet, is attached with atrous spatial pyramid pooling (ASPP) and context-aware module (CAN).
• AutoScale: Learning to Scale for Crowd Counting and Localization
  20 Dec 2019 2 repositories listed
  A major issue is that the density map on dense regions usually accumulates density values from a number of nearby Gaussian blobs, yielding different large density values on a small set of pixels.
• Bayesian Loss for Crowd Count Estimation with Point Supervision
  10 Aug 2019 2 repositories listed
  In crowd counting datasets, each person is annotated by a point, which is usually the center of the head.
• Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detection
  18 Jun 2019 2 repositories listed Syntology ran 1 of 12 samples · 11 unverified
  We introduce a detection framework for dense crowd counting and eliminate the need for the prevalent density regression paradigm.
• Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank
  17 Feb 2019 2 repositories listed Syntology ran 0 of 2 samples · 2 unverified
  Our results show that networks trained to regress to the ground truth targets for labeled data and to simultaneously learn to rank unlabeled data obtain significantly better, state-of-the-art results for both IQA and…
• Dual Path Multi-Scale Fusion Networks with Attention for Crowd Counting
  4 Feb 2019 2 repositories listed
  The task of crowd counting in varying density scenes is an extremely difficult challenge due to large scale variations.
• Improving Object Counting with Heatmap Regulation
  14 Mar 2018 2 repositories listed
  Adding HR to a simple VGG front-end improves performance on all these benchmarks compared to a simple one-look baseline model and results in state-of-the-art performance for car counting.
• CrowdNet: A Deep Convolutional Network for Dense Crowd Counting
  22 Aug 2016 2 repositories listed
  Our work proposes a novel deep learning framework for estimating crowd density from static images of highly dense crowds.
• Car Object Counting and Position Estimation via Extension of the CLIP-EBC Framework
  11 Jul 2025 1 repository listed
  In this paper, we investigate the applicability of the CLIP-EBC framework, originally designed for crowd counting, to car object counting using the CARPK dataset.
• EBC-ZIP: Improving Blockwise Crowd Counting with Zero-Inflated Poisson Regression
  24 Jun 2025 1 repository listed
  Density map estimation has become the mainstream paradigm in crowd counting.

Syntology lines on 11 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.