AI Paper Atlas

Research map / Benchmarks / UCF-Crime

UCF-Crime leaderboard

48 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on UCF-Crime. Best AUC: 91.58 (GS-MoE, ICCV 2025).

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.

UCF-Crime · AUC

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

#AUC ↑MethodPaperTopic
191.58GS-MoE
I3D
Mixture of Experts Guided by Gaussian Splatters Matters: A new Approach to Weakly-Supervised Video Anomaly Detection
ICCV 2025 · Table 1
Video segmentation and tracking
290.33π-VAD
I3D
Just Dance with pi! A Poly-modal Inductor for Weakly-supervised Video Anomaly Detection
CVPR 2025 · Table 1
Video segmentation and tracking
389.97LEC-VAD
CLIP
Learning Event Completeness for Weakly Supervised Video Anomaly Detection
ICML 2025 · Coarse-grained comparisons on
Video segmentation and tracking
489.57TargetVAU (Ours)TargetVAU: Multimodal Anomaly-Aware Reasoning for Target Behavior Understanding in Videos
AAAI 2026 · Table 4
Video-language understanding
589.47TLMA
VideoMAEv2 ViT-G/14
TLMA: Mitigating the Impact of Weakly Labeled Information for Video Anomaly Detection
CVPR 2026 · Table 1
Video segmentation and tracking
689.47CLUE-VAD (Ours)CLUE-VAD: Structured Semantic Clues for Understanding Explainable Events in Video Anomaly Detection
ECCV 2026 · Table 1
Video segmentation and tracking
788.96Holmes-VAU
InternVL2-2B
Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity
CVPR 2025 · Table 1
Video-language understanding
888.92RefineVAD
CLIP ViT-L/14
RefineVAD: Semantic-Guided Feature Recalibration for Weakly Supervised Video Anomaly Detection
AAAI 2026 · Table 1
Video segmentation and tracking
988.85PRISM (Qwen)
Qwen3-VL-Embedding-2B
PRISM: Training-Free Video Anomaly Detection via Intrinsic Statistical Modeling
ICML 2026 · Table 1
Video segmentation and tracking
1088.44ReactVAUReactVAU: A Slow-Fast Decoupled Framework for Streaming Video Anomaly Understanding
ECCV 2026 · Table 1
Video segmentation and tracking
28 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

UCF-Crime · frame-level AUC (%)

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

#frame-level AUC (%) ↑MethodPaperTopic
187.8UR-DMU + D2MIL
UR-DMU (I3D)
Learning from Noisy Supervision: A Denoising-Debiasing Framework for Weakly Supervised Video Anomaly Detection
CVPR 2026 · Table 2
Video segmentation and tracking
287.43SSRL
I3D-RGB
Scale-Aware Spatio-Temporal Relation Learning for Video Anomaly Detection
ECCV 2022 · Table 1
Video segmentation and tracking
387.15SteerVAD (Ours)
InternVL3
Steering and Rectifying Latent representation manifolds in Frozen Multi-modal LLMs for Video Anomaly Detection
ICLR 2026 · Table 1
Video segmentation and tracking
487.03HeadHunt-VAD
InternVL3
HeadHunt-VAD: Hunting Robust Anomaly-Sensitive Heads in MLLM for Tuning-Free Video Anomaly Detection
AAAI 2026 · Table 1
Video segmentation and tracking
584.91ALBAR features + MGFN
Swin-T finetuned on HMDB51
ALBAR: Adversarial Learning approach to mitigate Biases in Action Recognition
ICLR 2025 · Downstream task table
Action recognition
683.03CLAWS Net
C3D
CLAWS: Clustering Assisted Weakly Supervised Learning with Normalcy Suppression for Anomalous Event Detection
ECCV 2020 · Table 1
Video segmentation and tracking
782.5PA-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
882.12GCN cleaner + TSN RGB
TSN RGB
Graph Convolutional Label Noise Cleaner: Train a Plug-And-Play Action Classifier for Anomaly Detection
CVPR 2019 · Table: Quantitative comparison
Noisy labels
974.81TeD-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
1074.7FPDMFeature Prediction Diffusion Model for Video Anomaly Detection
ICCV 2023 · Table 1
Video segmentation and tracking

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