中文
相关论文

相关论文: Track Any Anomalous Object: A Granular Video Anoma…

200 篇论文

Visual object tracking is a fundamental video task in computer vision. Recently, the notably increasing power of perception algorithms allows the unification of single/multiobject and box/mask-based tracking. Among them, the Segment…

计算机视觉与模式识别 · 计算机科学 2023-07-27 Jiawen Zhu , Zhenyu Chen , Zeqi Hao , Shijie Chang , Lu Zhang , Dong Wang , Huchuan Lu , Bin Luo , Jun-Yan He , Jin-Peng Lan , Hanyuan Chen , Chenyang Li

The current concept of Smart Cities influences urban planners and researchers to provide modern, secured and sustainable infrastructure and give a decent quality of life to its residents. To fulfill this need video surveillance cameras have…

计算机视觉与模式识别 · 计算机科学 2021-08-10 Devashree R. Patrikar , Mayur Rajram Parate

As robotic systems execute increasingly difficult task sequences, so does the number of ways in which they can fail. Video Anomaly Detection (VAD) frameworks typically focus on singular, low-level kinematic or action failures, struggling to…

机器人学 · 计算机科学 2026-03-11 Nerea Gallego , Fernando Salanova , Claudio Mannarano , Cristian Mahulea , Eduardo Montijano

Video segmentation is essential for advancing robotics and autonomous driving, particularly in open-world settings where continuous perception and object association across video frames are critical. While the Segment Anything Model (SAM)…

计算机视觉与模式识别 · 计算机科学 2024-10-14 Pinxue Guo , Zixu Zhao , Jianxiong Gao , Chongruo Wu , Tong He , Zheng Zhang , Tianjun Xiao , Wenqiang Zhang

Anomaly segmentation is a critical task for driving applications, and it is approached traditionally as a per-pixel classification problem. However, reasoning individually about each pixel without considering their contextual semantics…

计算机视觉与模式识别 · 计算机科学 2023-07-26 Shyam Nandan Rai , Fabio Cermelli , Dario Fontanel , Carlo Masone , Barbara Caputo

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…

计算机视觉与模式识别 · 计算机科学 2025-06-17 Xinyi Zhao , Congjing Zhang , Pei Guo , Wei Li , Lin Chen , Chaoyue Zhao , Shuai Huang

Compared with still image object detection, video object detection (VOD) needs to particularly concern the high across-frame variation in object appearance, and the diverse deterioration in some frames. In principle, the detection in a…

计算机视觉与模式识别 · 计算机科学 2024-07-30 Yuheng Shi , Tong Zhang , Xiaojie Guo

Most models for weakly supervised video anomaly detection (WS-VAD) rely on multiple instance learning, aiming to distinguish normal and abnormal snippets without specifying the type of anomaly. However, the ambiguous nature of anomaly…

计算机视觉与模式识别 · 计算机科学 2024-09-04 Chenchen Tao , Xiaohao Peng , Chong Wang , Jiafei Wu , Puning Zhao , Jun Wang , Jiangbo Qian

We propose a lightweight and accurate method for detecting anomalies in videos. Existing methods used multiple-instance learning (MIL) to determine the normal/abnormal status of each segment of the video. Recent successful researches argue…

计算机视觉与模式识别 · 计算机科学 2022-09-15 Yudai Watanabe , Makoto Okabe , Yasunori Harada , Naoji Kashima

In modern manufacturing, Visual Anomaly Detection (VAD) is essential for automated inspection and consistent product quality. Yet, increasingly dynamic and flexible production environments introduce key challenges: First, frequent product…

机器学习 · 计算机科学 2025-12-16 Haoyu Ren , Kay Koehle , Kirill Dorofeev , Darko Anicic

Deep neural networks (DNNs), while increasingly deployed in many applications, struggle with robustness against anomalous and out-of-distribution (OOD) data. Current OOD benchmarks often oversimplify, focusing on single-object tasks and not…

计算机视觉与模式识别 · 计算机科学 2024-09-30 Debargha Ganguly , Debayan Gupta , Vipin Chaudhary

Humans detect real-world object anomalies by perceiving, interacting, and reasoning based on object-conditioned physical knowledge. The long-term goal of Industrial Anomaly Detection (IAD) is to enable machines to autonomously replicate…

计算机视觉与模式识别 · 计算机科学 2025-03-27 Wenqiao Li , Yao Gu , Xintao Chen , Xiaohao Xu , Ming Hu , Xiaonan Huang , Yingna Wu

Traffic anomaly detection has played a crucial role in Intelligent Transportation System (ITS). The main challenges of this task lie in the highly diversified anomaly scenes and variational lighting conditions. Although much work has…

计算机视觉与模式识别 · 计算机科学 2021-06-10 Jingyuan Chen , Guanchen Ding , Yuchen Yang , Wenwei Han , Kangmin Xu , Tianyi Gao , Zhe Zhang , Wanping Ouyang , Hao Cai , Zhenzhong Chen

Video anomaly detection (VAD) systems are increasingly deployed in safety critical environments and require a large amount of data for accurate detection. However, such data may contain personally identifiable information (PII), including…

计算机视觉与模式识别 · 计算机科学 2026-03-30 Nazia Aslam , Abhisek Ray , Thomas B. Moeslund , Kamal Nasrollahi

A novel approach to detect road surface anomalies by visual tracking of a preceding vehicle is proposed. The method is versatile, predicting any kind of road anomalies, such as potholes, bumps, debris, etc., unlike direct observation…

计算机视觉与模式识别 · 计算机科学 2025-05-08 Petr Jahoda , Jan Cech

Time series anomaly detection (TSAD) is essential for maintaining the reliability and security of IoT-enabled service systems. Existing methods require training one specific model for each dataset, which exhibits limited generalization…

机器学习 · 计算机科学 2026-04-23 PengYu Chen , Shang Wan , Xiaohou Shi , Yuan Chang , Yan Sun , Sajal K. Das

Video anomaly detection is a challenging task not only because it involves solving many sub-tasks such as motion representation, object localization and action recognition, but also because it is commonly considered as an unsupervised…

计算机视觉与模式识别 · 计算机科学 2020-12-04 Yuqi Ouyang , Victor Sanchez

Video Anomaly Detection (VAD) systems can autonomously monitor and identify disturbances, reducing the need for manual labor and associated costs. However, current VAD systems are often limited by their superficial semantic understanding of…

计算机视觉与模式识别 · 计算机科学 2024-05-28 Jiaqi Tang , Hao Lu , Ruizheng Wu , Xiaogang Xu , Ke Ma , Cheng Fang , Bin Guo , Jiangbo Lu , Qifeng Chen , Ying-Cong Chen

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…

计算机视觉与模式识别 · 计算机科学 2024-07-23 Yuchen Yang , Kwonjoon Lee , Behzad Dariush , Yinzhi Cao , Shao-Yuan Lo

Tracking and detecting any object, including ones never-seen-before during model training, is a crucial but elusive capability of autonomous systems. An autonomous agent that is blind to never-seen-before objects poses a safety hazard when…

计算机视觉与模式识别 · 计算机科学 2022-03-30 Yang Liu , Idil Esen Zulfikar , Jonathon Luiten , Achal Dave , Deva Ramanan , Bastian Leibe , Aljoša Ošep , Laura Leal-Taixé