Datasets › ShanghaiTech

ShanghaiTech

Introduced by Yingying Zhang et al. in Single-Image Crowd Counting via Multi-Column Convolutional Neural Network1 Jan 2016 archive 2025-07-28

The Shanghaitech dataset is a large-scale crowd counting dataset. It consists of 1198 annotated crowd images. The dataset is divided into two parts, Part-A containing 482 images and Part-B containing 716 images. Part-A is split into train and test subsets consisting of 300 and 182 images, respectively. Part-B is split into train and test subsets consisting of 400 and 316 images. Each person in a crowd image is annotated with one point close to the center of the head. In total, the dataset consists of 330,165 annotated people. Images from Part-A were collected from the Internet, while images from Part-B were collected on the busy streets of Shanghai.

Source: Iterative Crowd Counting

Image Source: Li et al

Benchmarks archive 2025-07-28

All 5 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

Papers archive 2025-07-28

30 shown of 61 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 277. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
EBC-ZIP: Improving Blockwise Crowd Counting with Zero-Inflated Poisson Regression 1 2 24 Jun 2025 not harvested
AnyAnomaly: Zero-Shot Customizable Video Anomaly Detection with LVLM 1 1 6 Mar 2025 not harvested
VideoPatchCore: An Effective Method to Memorize Normality for Video Anomaly Detection 1 2 24 Sep 2024 not harvested
Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Models 1 2 14 Jul 2024 ran 2 of 2 samples (0 unverified)
Bounding Boxes and Probabilistic Graphical Models: Video Anomaly Detection Simplified 1 2 8 Jul 2024 not harvested
Improving Point-based Crowd Counting and Localization Based on Auxiliary Point Guidance 1 2 17 May 2024 not harvested
Crowd Counting and Individual Localization Using Pseudo Square Label 0 2 13 May 2024 not harvested
VMambaCC: A Visual State Space Model for Crowd Counting 0 1 7 May 2024 not harvested
An Exploratory Study on Human-Centric Video Anomaly Detection through Variational Autoencoders and Trajectory Prediction 1 2 29 Apr 2024 not harvested
MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection 1 4 21 Mar 2024 ran 1 of 1 samples (0 unverified; 1 pointer-only for licence)
CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise Classification 1 9 14 Mar 2024 not harvested
Making Anomalies More Anomalous: Video Anomaly Detection Using a Novel Generator and Destroyer 1 1 26 Feb 2024 not harvested
FGENet: Fine-Grained Extraction Network for Congested Crowd Counting 0 1 2 Jan 2024 not harvested
Divide and Conquer in Video Anomaly Detection: A Comprehensive Review and New Approach 1 1 26 Sep 2023 not harvested
Diversity-Measurable Anomaly Detection 1 1 9 Mar 2023 ran 6 of 11 samples (5 unverified; 11 pointer-only for licence)
Improving Deep Regression with Ordinal Entropy 1 2 21 Jan 2023 ran 4 of 5 samples (1 unverified; 5 pointer-only for licence)
EVAL: Explainable Video Anomaly Localization 0 1 15 Dec 2022 not harvested
An Attribute-based Method for Video Anomaly Detection 4 1 1 Dec 2022 ran 2 of 3 samples (1 unverified; 3 pointer-only for licence)
Normalizing Flows for Human Pose Anomaly Detection 1 1 20 Nov 2022 not harvested
Spatio-temporal predictive tasks for abnormal event detection in videos 0 1 27 Oct 2022 not harvested
Improving Local Features with Relevant Spatial Information by Vision Transformer for Crowd Counting 1 1 30 Sep 2022 not harvested
Self-Supervised Masked Convolutional Transformer Block for Anomaly Detection 1 1 25 Sep 2022 not harvested
Context Recovery and Knowledge Retrieval: A Novel Two-Stream Framework for Video Anomaly Detection 1 1 7 Sep 2022 not harvested
Video Anomaly Detection by Solving Decoupled Spatio-Temporal Jigsaw Puzzles 1 1 20 Jul 2022 not harvested
SSMTL++: Revisiting Self-Supervised Multi-Task Learning for Video Anomaly Detection 0 2 16 Jul 2022 not harvested
Rethinking Spatial Invariance of Convolutional Networks for Object Counting 1 2 10 Jun 2022 not harvested
Attention-based residual autoencoder for video anomaly detection 1 1 25 May 2022 not harvested
FusionCount: Efficient Crowd Counting via Multiscale Feature Fusion 1 2 28 Feb 2022 not harvested
Few-shot Object Counting with Similarity-Aware Feature Enhancement 1 2 22 Jan 2022 not harvested
Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection 1 1 7 Dec 2021 not harvested

The full list of 61 is in the JSON twin.

Dataset loaders archive 2025-07-28

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

Unknown

Modalities archive 2025-07-28

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • ShanghaiTech
  • ShanghaiTech A
  • ShanghaiTech B

3 variant names, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections