相关论文: Towards Zero-Shot Anomaly Detection and Reasoning …

Video anomaly detection (VAD) aims to identify and ground anomalous behaviors or events in videos, serving as a core technology in the fields of intelligent surveillance and public safety. With the advancement of deep learning, the…

The recently introduced odd-one-out anomaly detection task involves identifying the odd-looking instances within a multi-object scene. This problem presents several challenges for modern deep learning models, demanding spatial reasoning…

Zero- and few-shot visual anomaly segmentation relies on powerful vision-language models that detect unseen anomalies using manually designed textual prompts. However, visual representations are inherently independent of language. In this…

Zero-shot industrial anomaly detection (ZSAD) methods typically yield coarse anomaly maps as vision transformers (ViTs) extract patch-level features only. To solve this, recent solutions attempt to predict finer anomalies using features…

Zero-shot object detection (ZSD), the task that extends conventional detection models to detecting objects from unseen categories, has emerged as a new challenge in computer vision. Most existing approaches tackle the ZSD task with a strict…

Time series anomaly detection (TSAD) has traditionally focused on binary classification and often lacks the fine-grained categorization and explanatory reasoning required for transparent decision-making. To address these limitations, we…

Anomaly detection (AD) is a crucial task in machine learning with various applications, such as detecting emerging diseases, identifying financial frauds, and detecting fake news. However, obtaining complete, accurate, and precise labels…

Anomaly detection (AD) is a fundamental task of critical importance across numerous domains. Current systems increasingly operate in rapidly evolving environments that generate diverse yet interconnected data modalities -- such as time…

Logical anomaly detection in industrial inspection remains challenging due to variations in visual appearance (e.g., background clutter, illumination shift, and blur), which often distract vision-centric detectors from identifying…

Zero-shot Learning(ZSL) attains knowledge transfer from seen classes to unseen classes by exploring auxiliary category information, which is a promising yet difficult research topic. In this field, Audio-Visual Generalized Zero-Shot…

Most existing anomaly detection (AD) methods require a dedicated model for each category. Such a paradigm, despite its promising results, is computationally expensive and inefficient, thereby failing to meet the requirements for realworld…

Most video-anomaly research stops at frame-wise detection, offering little insight into why an event is abnormal, typically outputting only frame-wise anomaly scores without spatial or semantic context. Recent video anomaly localization and…

Most cross-domain unsupervised Video Anomaly Detection (VAD) works assume that at least few task-relevant target domain training data are available for adaptation from the source to the target domain. However, this requires laborious…

Existing Video Anomaly Detection (VAD) methods typically rely on task-specific training, leading to strong domain dependency and high training costs. Moreover, most existing methods output only scalar anomaly scores, providing limited…

Visual Anomaly Detection (VAD) aims to identify abnormal samples in images that deviate from normal patterns, covering multiple domains, including industrial, logical, and medical fields. Due to the domain gaps between these fields,…

Training-free video anomaly detection (VAD) has recently emerged as a scalable alternative to supervised approaches, yet existing methods largely rely on static prompting and geometry-agnostic feature fusion. As a result, anomaly inference…

Video anomaly detection (VAD) aims to automatically identify events that deviate from normal patterns in untrimmed surveillance videos. Existing methods universally depend on large-scale annotations or task-specific training procedures,…

Oversight AI is an emerging concept in radiology where the AI forms a symbiosis with radiologists by continuously supporting radiologists in their decision-making. Recent advances in vision-language models sheds a light on the long-standing…

This paper explores the potential of Large Language Models(LLMs) in zero-shot anomaly detection for safe visual navigation. With the assistance of the state-of-the-art real-time open-world object detection model Yolo-World and specialized…

While Vision-Language Models (VLMs) have shown promising progress in general multimodal tasks, they often struggle in industrial anomaly detection and reasoning, particularly in delivering interpretable explanations and generalizing to…