paper-with-me

Video Anomaly Detection

14개 벤치마크 · 논문 344편 · 이 태스크의 논문 보기 →

Benchmarks

HR-ShanghaiTech

결과 42개

HR-Avenue

결과 33개

HR-UBnormal

결과 24개

ShanghaiTech

결과 22개

CUHK Avenue

결과 21개

UBnormal

결과 13개

ShanghaiTech Campus

결과 12개

UCF-Crime

결과 10개

UCSD Ped2

결과 9개

Ped2

결과 4개

CHAD

결과 3개

CHUK Avenue

결과 3개

IITB Corridor

결과 3개

Street Scene

결과 3개

Most implemented

Papers

Adaptive Multi-Granularity Temporal Modeling for Weakly Supervised Video Anomaly Detection

2026-09-04 · Changyi Li, Yu Xiao arxiv

As the scale of video surveillance data outpaces manual annotation capacities, weakly supervised video anomaly detection (WSVAD) has emerged as a critical research frontier. Most existing approaches formulate WSVAD withi…

Multiple Instance LearningVideo Anomaly DetectionEvent Segmentation

A VLM Answer Is Not an Anomaly Score: Rank Compression Across Image and Video Anomaly Detection

2026-08-21 · Inpyo Song, Jangwon Lee arxiv

Anomaly detection aims to identify observations that deviate from normal patterns. Recent work uses pretrained vision-language models (VLMs) for training-free image and video anomaly detection without task-specific retra…

Video Anomaly Detection

STEP: Score-Based Temporal Energy for Human Pose Video Anomaly Detection

2026-08-20 · Jakub Micorek, Mateusz Koziński, Horst Possegger arxiv

Skeleton-based Video Anomaly Detection (VAD) offers a robust, privacy-preserving solution for identifying abnormal behaviors. To model the distribution of normal static and moving poses, recent methods train Energy-Based…

Computational EfficiencyVideo Anomaly DetectionPose Estimation

Rethinking Open-World Video Anomaly Detection: Diagnosing Definition Blindness

2026-07-22 · Inpyo Song, Jangwon Lee arxiv

Open-world video anomaly detection (OWVAD) is expected to detect events that match a user-specified definition of abnormality. This requirement is stronger than generic anomaly localization: in the same video, changing t…

Video Anomaly Detection

O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning

2026-07-20 · Mei Yuan, Qi Long, Qifeng Wu, Zhenyang Li 외 hf

Industrial Video Anomaly Detection (IVAD) aims to identify anomalous objects and events in an industrial process, which is crucial for modern manufacturing and quality control systems. Existing VLM-based anomaly reasonin…

Video Anomaly Detection

Structured Evidence Selection for Weakly Supervised Video Anomaly Detection

2026-07-11 · Chenglizhao Chen, Tianxiang Nan, Wen Li, Xinyu Liu 외 arxiv

Weakly supervised video anomaly detection relies solely on video-level labels for training, making it difficult to accurately localize anomalous events in complex scenes. In real-world videos, anomalous behaviors exhibit…

Computational EfficiencyVideo Anomaly Detection

전체 344편 보기 →