AI Paper Atlas

Research map / Benchmarks / UCSD Ped2

UCSD Ped2 leaderboard

20 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on UCSD Ped2. Best AUC: 99.1 (Ours (object level), CVPR 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.

UCSD Ped2 · AUC

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

#AUC ↑MethodPaperTopic
199.1Ours (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
298.6RTFM
I3D-RGB
Weakly-Supervised Video Anomaly Detection With Robust Temporal Feature Magnitude Learning
ICCV 2021 · Table 4
Video segmentation and tracking
398.3MSE + LAPComprehensive Regularization in a Bi-directional Predictive Network for Video Anomaly Detection
AAAI 2022 · Table 3
Video segmentation and tracking
498.1HSCHierarchical Semantic Contrast for Scene-Aware Video Anomaly Detection
CVPR 2023 · Comparison to State-of-the-Art
Video segmentation and tracking
597.9AnomalyRuler
CogVLM-17B + Mistral-7B
Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Models
ECCV 2024 · Table 3
Video segmentation and tracking
697Ours-P w/ Mem.Learning Memory-Guided Normality for Anomaly Detection
CVPR 2020 · Table 1
Video segmentation and tracking
796.9Ours w DPU
AE
Learning Normal Dynamics in Videos With Meta Prototype Network
CVPR 2021 · Table 1
Video segmentation and tracking
896.6AMMC-Net with memory consistencyAppearance-Motion Memory Consistency Network for Video Anomaly Detection
AAAI 2021 · Table 2
Video segmentation and tracking
994.1MemAEMemorizing Normality to Detect Anomaly: Memory-Augmented Deep Autoencoder for Unsupervised Anomaly Detection
ICCV 2019 · Table 2
OOD and anomaly detection
1093.6OursDeep Learning in Latent Space for Video Prediction and Compression
CVPR 2021 · Table 1
Video segmentation and tracking
1 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

UCSD Ped2 · frame-level AUC

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

1 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.