AI Paper Atlas

Research map / Benchmarks / ShanghaiTech

ShanghaiTech leaderboard

29 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on ShanghaiTech. Best AUC: 98.35 (PE-MIL, CVPR 2024).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

ShanghaiTech · AUC

18 papers, each with its best reported number for its own method; higher is better.

#AUC ↑MethodPaperTopic
198.35PE-MIL
I3D RGB
Prompt-Enhanced Multiple Instance Learning for Weakly Supervised Video Anomaly Detection
CVPR 2024 · Table 2
Video segmentation and tracking
297.6Ours
Inception-v1 I3D
Look Around for Anomalies: Weakly-Supervised Anomaly Detection via Context-Motion Relational Learning
CVPR 2023 · Table 1
Video segmentation and tracking
397.32Ours
VideoSwin-RGB
Self-Training Multi-Sequence Learning with Transformer for Weakly Supervised Video Anomaly Detection
AAAI 2022 · Table 1
Video segmentation and tracking
497.26EGOLearnable Expansion of Graph Operators for Multi-Modal Feature Fusion
ICLR 2025 · Table: Experimental results on
Cross-modal learning
596.85Ours (self-attention CRF)Dance With Self-Attention: A New Look of Conditional Random Fields on Anomaly Detection in Videos
ICCV 2021 · Table 4
Video segmentation and tracking
696BN-SVP
C3D
Bayesian Nonparametric Submodular Video Partition for Robust Anomaly Detection
CVPR 2022 · Table: Comparison with Other M
Video segmentation and tracking
794.83MIST
I3D
MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection
CVPR 2021 · Table 2
Video segmentation and tracking
890.59TeD-SPAD (Ours)
I3D + MGFN
TeD-SPAD: Temporal Distinctiveness for Self-Supervised Privacy-Preservation for Video Anomaly Detection
ICCV 2023 · Supp. Table
Video segmentation and tracking
986Ours (object level)Noise-Resistant Video Anomaly Detection via RGB Error-Guided Multiscale Predictive Coding and Dynamic Memory
CVPR 2025 · Table 4
Video segmentation and tracking
1083.4HSC w/ MA⁻,⁺Hierarchical Semantic Contrast for Scene-Aware Video Anomaly Detection
CVPR 2023 · Comparison to State-of-the-Art
Video segmentation and tracking
8 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

ShanghaiTech · frame-level AUC (%)

12 papers, each with its best reported number for its own method; higher is better.

#frame-level AUC (%) ↑MethodPaperTopic
198.2PA-VAD (DARM)
Qwen2.5-VL features
PA-VAD: Diffusion-Based Pseudo-Only Video Anomaly Detection via Domain-Aligned Memory Updates
ECCV 2026 · Table 3
Video segmentation and tracking
298.13TEVAD + D2MIL
TEVAD (I3D + Text)
Learning from Noisy Supervision: A Denoising-Debiasing Framework for Weakly Supervised Video Anomaly Detection
CVPR 2026 · Table 1
Video segmentation and tracking
390.2Ours (late fusion)Anomaly Detection in Video via Self-Supervised and Multi-Task Learning
CVPR 2021 · Table: frame-level AUC scores
Open-set and few-shot detection
489.67CLAWS Net
C3D
CLAWS: Clustering Assisted Weakly Supervised Learning with Normalcy Suppression for Anomalous Event Detection
ECCV 2020 · Table 2
Video segmentation and tracking
584.9OursObject-Centric Auto-Encoders and Dummy Anomalies for Abnormal Event Detection in Video
CVPR 2019 · Table 1
Open-set and few-shot detection
684.44GCN cleaner + TSN RGB, Step-3
TSN RGB
Graph Convolutional Label Noise Cleaner: Train a Plug-And-Play Action Classifier for Anomaly Detection
CVPR 2019 · Table: Step-wise AUC on Shangh
Noisy labels
778.6FPDMFeature Prediction Diffusion Model for Video Anomaly Detection
ICCV 2023 · Table 1
Video segmentation and tracking
878.1OursComprehensive Regularization in a Bi-directional Predictive Network for Video Anomaly Detection
AAAI 2022 · Table 5
Video segmentation and tracking
974.7DLAN-ACDynamic Local Aggregation Network with Adaptive Clusterer for Anomaly Detection
ECCV 2022 · Table 1
OOD and anomaly detection
1073.7AMMC-NetAppearance-Motion Memory Consistency Network for Video Anomaly Detection
AAAI 2021 · Table 1
Video segmentation and tracking
2 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.