Documentdetail
ID kaart
oai:arXiv.org:2401.05702
Onderwerp
Computer Science - Computer Vision...Auteur
Lv, Hui Sun, QianruCategorie
Computer Science
Jaar
2024
vermelding datum
17-01-2024
Trefwoorden
detection vllms anomalyBeschrijving
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 explanability of detection results.
In this paper, we conduct pioneer research on equipping video-based large language models (VLLMs) in the framework of VAD, making the VAD model free from thresholds and able to explain the reasons for the detected anomalies.
We introduce a novel network module Long-Term Context (LTC) to mitigate the incapability of VLLMs in long-range context modeling.
We design a three-phase training method to improve the efficiency of fine-tuning VLLMs by substantially minimizing the requirements for VAD data and lowering the costs of annotating instruction-tuning data.
Our trained model achieves the top performance on the anomaly videos of the UCF-Crime and TAD benchmarks, with the AUC improvements of +3.86\% and +4.96\%, respectively.
More impressively, our approach can provide textual explanations for detected anomalies.
;Comment: 9 pages, 6 figures
Lv, Hui,Sun, Qianru, 2024, Video Anomaly Detection and Explanation via Large Language Models
Optimal Sensing of Momentum Kicks with a Feedback-Controlled Nanomechanical Resonator
sensing momentum kicks resonator
Shared genetic aetiology of Alzheimer’s disease and age-related macular degeneration by APOC1 and APOE genes
gene diagnostic based analysis amd ad apoe apoc1 identified genes pleiotropy
