A survey on video diffusion models
The recent wave of AI-generated content (AIGC) has witnessed substantial success in
computer vision, with the diffusion model playing a crucial role in this achievement. Due to …
computer vision, with the diffusion model playing a crucial role in this achievement. Due to …
Harnessing Large Language Models for Training-free Video Anomaly Detection
Video anomaly detection (VAD) aims to temporally locate abnormal events in a video.
Existing works mostly rely on training deep models to learn the distribution of normality with …
Existing works mostly rely on training deep models to learn the distribution of normality with …
Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation: A Unified Approach
Abstract Video Anomaly Detection (VAD) is an open-set recognition task which is usually
formulated as a one-class classification (OCC) problem where training data is comprised of …
formulated as a one-class classification (OCC) problem where training data is comprised of …
[HTML][HTML] Trajectory-based fish event classification through pre-training with diffusion models
N Canovi, BA Ellis, TK Sørdalen, V Allken… - Ecological …, 2024 - Elsevier
This study contributes to advancing the field of automatic fish event recognition in natural
underwater videos, addressing the current gap in studying fish interaction and competition …
underwater videos, addressing the current gap in studying fish interaction and competition …
Learning Anomalies with Normality Prior for Unsupervised Video Anomaly Detection
Unsupervised video anomaly detection (UVAD) aims to detect abnormal events in videos
without any annotations. It remains challenging because anomalies are rare, diverse, and …
without any annotations. It remains challenging because anomalies are rare, diverse, and …
Vera: Explainable video anomaly detection via verbalized learning of vision-language models
The rapid advancement of vision-language models (VLMs) has established a new paradigm
in video anomaly detection (VAD): leveraging VLMs to simultaneously detect anomalies and …
in video anomaly detection (VAD): leveraging VLMs to simultaneously detect anomalies and …
Unsupervised, Online and On-The-Fly Anomaly Detection for Non-stationary Image Distributions
D McIntosh, AB Albu - European Conference on Computer Vision, 2025 - Springer
Abstract We propose Online-InReaCh, the first fully unsupervised online method for
detecting and localizing anomalies on-the-fly in image sequences while following non …
detecting and localizing anomalies on-the-fly in image sequences while following non …
[PDF][PDF] Conditional Video Generation Guided by Multimodal Inputs: A Comprehensive Survey
The field of video generation is rapidly evolving, driven by advancements in generative
models. This survey provides a comprehensive analysis of the diverse methodologies …
models. This survey provides a comprehensive analysis of the diverse methodologies …
Multiscale Recovery Diffusion Model With Unsupervised Learning for Video Anomaly Detection System
B Li, H Ge, Y Liu, G Tang - IEEE Transactions on Industrial …, 2024 - ieeexplore.ieee.org
The rapid development of intelligent industry and smart city increases the number of
surveillance devices, greatly enhancing the need for unsupervised automatic anomaly …
surveillance devices, greatly enhancing the need for unsupervised automatic anomaly …
EOGT: Video Anomaly Detection with Enhanced Object Information and Global Temporal Dependency
Video anomaly detection (VAD) aims to identify events or scenes in videos that deviate from
typical patterns. Existing approaches primarily focus on reconstructing or predicting frames …
typical patterns. Existing approaches primarily focus on reconstructing or predicting frames …