Enregistré dans:
Détails bibliographiques
Auteurs principaux: Du, Hang, Zhang, Sicheng, Xie, Binzhu, Nan, Guoshun, Zhang, Jiayang, Xu, Junrui, Liu, Hangyu, Leng, Sicong, Liu, Jiangming, Fan, Hehe, Huang, Dajiu, Feng, Jing, Chen, Linli, Zhang, Can, Li, Xuhuan, Zhang, Hao, Chen, Jianhang, Cui, Qimei, Tao, Xiaofeng
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2405.00181
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917363728777216
author Du, Hang
Zhang, Sicheng
Xie, Binzhu
Nan, Guoshun
Zhang, Jiayang
Xu, Junrui
Liu, Hangyu
Leng, Sicong
Liu, Jiangming
Fan, Hehe
Huang, Dajiu
Feng, Jing
Chen, Linli
Zhang, Can
Li, Xuhuan
Zhang, Hao
Chen, Jianhang
Cui, Qimei
Tao, Xiaofeng
author_facet Du, Hang
Zhang, Sicheng
Xie, Binzhu
Nan, Guoshun
Zhang, Jiayang
Xu, Junrui
Liu, Hangyu
Leng, Sicong
Liu, Jiangming
Fan, Hehe
Huang, Dajiu
Feng, Jing
Chen, Linli
Zhang, Can
Li, Xuhuan
Zhang, Hao
Chen, Jianhang
Cui, Qimei
Tao, Xiaofeng
contents Video anomaly understanding (VAU) aims to automatically comprehend unusual occurrences in videos, thereby enabling various applications such as traffic surveillance and industrial manufacturing. While existing VAU benchmarks primarily concentrate on anomaly detection and localization, our focus is on more practicality, prompting us to raise the following crucial questions: "what anomaly occurred?", "why did it happen?", and "how severe is this abnormal event?". In pursuit of these answers, we present a comprehensive benchmark for Causation Understanding of Video Anomaly (CUVA). Specifically, each instance of the proposed benchmark involves three sets of human annotations to indicate the "what", "why" and "how" of an anomaly, including 1) anomaly type, start and end times, and event descriptions, 2) natural language explanations for the cause of an anomaly, and 3) free text reflecting the effect of the abnormality. In addition, we also introduce MMEval, a novel evaluation metric designed to better align with human preferences for CUVA, facilitating the measurement of existing LLMs in comprehending the underlying cause and corresponding effect of video anomalies. Finally, we propose a novel prompt-based method that can serve as a baseline approach for the challenging CUVA. We conduct extensive experiments to show the superiority of our evaluation metric and the prompt-based approach. Our code and dataset are available at https://github.com/fesvhtr/CUVA.
format Preprint
id arxiv_https___arxiv_org_abs_2405_00181
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Uncovering What, Why and How: A Comprehensive Benchmark for Causation Understanding of Video Anomaly
Du, Hang
Zhang, Sicheng
Xie, Binzhu
Nan, Guoshun
Zhang, Jiayang
Xu, Junrui
Liu, Hangyu
Leng, Sicong
Liu, Jiangming
Fan, Hehe
Huang, Dajiu
Feng, Jing
Chen, Linli
Zhang, Can
Li, Xuhuan
Zhang, Hao
Chen, Jianhang
Cui, Qimei
Tao, Xiaofeng
Computer Vision and Pattern Recognition
Artificial Intelligence
Video anomaly understanding (VAU) aims to automatically comprehend unusual occurrences in videos, thereby enabling various applications such as traffic surveillance and industrial manufacturing. While existing VAU benchmarks primarily concentrate on anomaly detection and localization, our focus is on more practicality, prompting us to raise the following crucial questions: "what anomaly occurred?", "why did it happen?", and "how severe is this abnormal event?". In pursuit of these answers, we present a comprehensive benchmark for Causation Understanding of Video Anomaly (CUVA). Specifically, each instance of the proposed benchmark involves three sets of human annotations to indicate the "what", "why" and "how" of an anomaly, including 1) anomaly type, start and end times, and event descriptions, 2) natural language explanations for the cause of an anomaly, and 3) free text reflecting the effect of the abnormality. In addition, we also introduce MMEval, a novel evaluation metric designed to better align with human preferences for CUVA, facilitating the measurement of existing LLMs in comprehending the underlying cause and corresponding effect of video anomalies. Finally, we propose a novel prompt-based method that can serve as a baseline approach for the challenging CUVA. We conduct extensive experiments to show the superiority of our evaluation metric and the prompt-based approach. Our code and dataset are available at https://github.com/fesvhtr/CUVA.
title Uncovering What, Why and How: A Comprehensive Benchmark for Causation Understanding of Video Anomaly
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2405.00181