相关论文: Are Multimodal LLMs Ready for Surveillance? A Real…

Video Anomaly Detection (VAD) aims to localize abnormal events on the timeline of long-range surveillance videos. Anomaly-scoring-based methods have been prevailing for years but suffer from the high complexity of thresholding and low…

Video anomaly detection (VAD) has witnessed significant advancements through the integration of large language models (LLMs) and vision-language models (VLMs), addressing critical challenges such as interpretability, temporal reasoning, and…

Existing semi-supervised video anomaly detection (VAD) methods often struggle with detecting complex anomalies involving object interactions and generally lack explainability. To overcome these limitations, we propose a novel VAD framework…

Video anomaly detection (VAD) is essential for enhancing safety and security by identifying unusual events across different environments. Existing VAD benchmarks, however, are primarily designed for general-purpose scenarios, neglecting the…

Large vision-language models (LVLMs) are markedly proficient in deriving visual representations guided by natural language. Recent explorations have utilized LVLMs to tackle zero-shot visual anomaly detection (VAD) challenges by pairing…

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 either video-level supervision, one-class supervision, or in…

Recent video anomaly detection research has expanded rapidly with an emphasis on general models of normality intended to work across many different scenes. While this focus has led to improvements in scalability and multi-scene…

Zero-shot anomaly detection (ZSAD) recognizes and localizes anomalies in previously unseen objects by establishing feature mapping between textual prompts and inspection images, demonstrating excellent research value in flexible industrial…

Anomaly analysis in surveillance videos is a crucial topic in computer vision. In recent years, multimodal large language models (MLLMs) have outperformed task-specific models in various domains. Although MLLMs are particularly versatile,…

Video Anomaly Detection (VAD) aims to locate events that deviate from normal patterns in videos. Traditional approaches often rely on extensive labeled data and incur high computational costs. Recent tuning-free methods based on Multimodal…

In the field of industrial inspection, Multimodal Large Language Models (MLLMs) have a high potential to renew the paradigms in practical applications due to their robust language capabilities and generalization abilities. However, despite…

The collection and detection of video anomaly data has long been a challenging problem due to its rare occurrence and spatio-temporal scarcity. Existing video anomaly detection (VAD) methods under perform in open-world scenarios. Key…

Video Anomaly Detection (VAD) is crucial for applications such as security surveillance and autonomous driving. However, existing VAD methods provide little rationale behind detection, hindering public trust in real-world deployments. In…

The widespread use of cameras in our society has created an overwhelming amount of video data, far exceeding the capacity for human monitoring. This presents a critical challenge for public safety and security, as the timely detection of…

Zero-Shot Anomaly Detection (ZSAD) is an emerging AD paradigm. Unlike the traditional unsupervised AD setting that requires a large number of normal samples to train a model, ZSAD is more practical for handling data-restricted real-world…

Multimodal Large Language Models (MLLMs) have achieved significant advancements in tasks like Visual Question Answering (VQA) by leveraging foundational Large Language Models (LLMs). However, their abilities in specific areas such as visual…

Towards open-ended Video Anomaly Detection (VAD), existing methods often exhibit biased detection when faced with challenging or unseen events and lack interpretability. To address these drawbacks, we propose Holmes-VAD, a novel framework…

Multimodal Large Language Models (MLLM) classification performance depends critically on evaluation protocol and ground truth quality. Studies comparing MLLMs with supervised and vision-language models report conflicting conclusions, and we…

Traditional approaches to safety event analysis in autonomous systems have relied on complex machine learning models and extensive datasets for high accuracy and reliability. However, the advent of Multimodal Large Language Models (MLLMs)…

In industrial settings, the accurate detection of anomalies is essential for maintaining product quality and ensuring operational safety. Traditional industrial anomaly detection (IAD) models often struggle with flexibility and…