Search

Your search keyword '"Lv, Hui"' showing total 2,626 results
Start Over Author "Lv, Hui"
2,626 results on '"Lv, Hui"'

1. Video Anomaly Detection and Explanation via Large Language Models

Author

Lv, Hui and Sun, Qianru

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

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

Published
2024

11. Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detection

Author

Lv, Hui, Yue, Zhongqi, Sun, Qianru, Luo, Bin, Cui, Zhen, and Zhang, Hanwang

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Weakly Supervised Video Anomaly Detection (WSVAD) is challenging because the binary anomaly label is only given on the video level, but the output requires snippet-level predictions. So, Multiple Instance Learning (MIL) is prevailing in WSVAD. However, MIL is notoriously known to suffer from many false alarms because the snippet-level detector is easily biased towards the abnormal snippets with simple context, confused by the normality with the same bias, and missing the anomaly with a different pattern. To this end, we propose a new MIL framework: Unbiased MIL (UMIL), to learn unbiased anomaly features that improve WSVAD. At each MIL training iteration, we use the current detector to divide the samples into two groups with different context biases: the most confident abnormal/normal snippets and the rest ambiguous ones. Then, by seeking the invariant features across the two sample groups, we can remove the variant context biases. Extensive experiments on benchmarks UCF-Crime and TAD demonstrate the effectiveness of our UMIL. Our code is provided at https://github.com/ktr-hubrt/UMIL., Comment: 11 pages,10 figures

Published
2023

12. Signed Average Consensus of Signed Networks Under Directed Communication Topologies

Author

Du, Mingjun, Li, Jinchao, Pang, Pengshao, Lv, Hui, Ji, Peng, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Hirche, Sandra, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Li, Yong, Series Editor, Liang, Qilian, Series Editor, Martín, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Oneto, Luca, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zamboni, Walter, Series Editor, Tan, Kay Chen, Series Editor, Wang, Qing, editor, Dong, Xiwang, editor, and Song, Peng, editor

Published
2024
Full Text
View/download PDF

13. Formation Tracking for Autonomous Surface Vessels Based on an Improved Reaching Law

Author

Han, Andong, Lv, Hui, Zhu, Baolong, Li, Shibo, Chen, Yadong, Du, Mingjun, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Hirche, Sandra, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Li, Yong, Series Editor, Liang, Qilian, Series Editor, Martín, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Oneto, Luca, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zamboni, Walter, Series Editor, Tan, Kay Chen, Series Editor, Wang, Qing, editor, Dong, Xiwang, editor, and Song, Peng, editor

Published
2024
Full Text
View/download PDF

14. A New Comparison Function Based Direct Multisearch Method for Derivative-Free Multi-objective Optimization Problems

Author

Zhao, Fuyu, Lv, Hui, Liu, Yongxia, Liu, Dandan, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Hirche, Sandra, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Li, Yong, Series Editor, Liang, Qilian, Series Editor, Martín, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Oneto, Luca, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zamboni, Walter, Series Editor, Tan, Kay Chen, Series Editor, Hua, Yongzhao, editor, Liu, Yishi, editor, and Han, Liang, editor

Published
2024
Full Text
View/download PDF

15. AGST-LSTM: The ConvLSTM Model Combines Attention and Gate Structure for Spatiotemporal Sequence Prediction Learning

Author

Wang, Xuechang, Lv, Hui, Chen, Jiawei, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Liu, Qingshan, editor, Wang, Hanzi, editor, Ma, Zhanyu, editor, Zheng, Weishi, editor, Zha, Hongbin, editor, Chen, Xilin, editor, Wang, Liang, editor, and Ji, Rongrong, editor

Published
2024
Full Text
View/download PDF

21. Effective protective agents against the organ toxicity of T-2 toxin and corresponding detoxification mechanisms: A narrative review

Author

Pengju Wang, Lv-hui Sun, Xu Wang, Qinghua Wu, and Aimei Liu

Subjects
T-2 toxin, Organ toxicity, Protective agent, Detoxification mechanism, Animal culture, SF1-1100
Abstract

T-2 toxin is one of the most widespread and toxic fungal toxins in food and feed. It can cause gastrointestinal toxicity, hepatotoxicity, immunotoxicity, reproductive toxicity, neurotoxicity, and nephrotoxicity in humans and animals. T-2 toxin is physicochemically stable and does not readily degrade during food and feed processing. Therefore, suppressing T-2 toxin-induced organ toxicity through antidotes is an urgent issue. Protective agents against the organ toxicity of T-2 toxin have been recorded widely in the literature, but these protective agents and their molecular mechanisms of detoxification have not been comprehensively summarized. In this review, we provide an overview of the various protective agents to T-2 toxin and the molecular mechanisms underlying the detoxification effects. Targeting appropriate targets to antagonize T-2 toxin toxicity is also an important option. This review will provide essential guidance and strategies for the better application and development of T-2 toxin antidotes specific for organ toxicity in the future.

Published
2024
Full Text
View/download PDF

23. Spatio-Temporal Relation Learning for Video Anomaly Detection

Author

Lv, Hui, Cui, Zhen, Wang, Biao, and Yang, Jian

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Anomaly identification is highly dependent on the relationship between the object and the scene, as different/same object actions in same/different scenes may lead to various degrees of normality and anomaly. Therefore, object-scene relation actually plays a crucial role in anomaly detection but is inadequately explored in previous works. In this paper, we propose a Spatial-Temporal Relation Learning (STRL) framework to tackle the video anomaly detection task. First, considering dynamic characteristics of the objects as well as scene areas, we construct a Spatio-Temporal Auto-Encoder (STAE) to jointly exploit spatial and temporal evolution patterns for representation learning. For better pattern extraction, two decoding branches are designed in the STAE module, i.e. an appearance branch capturing spatial cues by directly predicting the next frame, and a motion branch focusing on modeling the dynamics via optical flow prediction. Then, to well concretize the object-scene relation, a Relation Learning (RL) module is devised to analyze and summarize the normal relations by introducing the Knowledge Graph Embedding methodology. Specifically in this process, the plausibility of object-scene relation is measured by jointly modeling object/scene features and optimizable object-scene relation maps. Extensive experiments are conducted on three public datasets, and the superior performance over the state-of-the-art methods demonstrates the effectiveness of our method., Comment: 8 pages, 5 figures,Journal

Published
2022

26. Structural heterogeneity and plasticity of a Zr-based metallic glass modulated by high-temperature deformation.

Author

Lu, Wenting, Huang, Bo, Liao, Shansi, Liu, Penghua, Lv, Hui, Wu, Jiayi, Yi, Jun, Wang, Qing, and Wang, Gang

Subjects
METALLIC glasses, GLASS transition temperature, YOUNG'S modulus, HETEROGENEITY, DEFORMATIONS (Mechanics)
Abstract

Metallic glasses (MGs) are of high strength but limited plasticity at room temperature (RT) due to localized shear in the intrinsically heterogeneous structure. Here, we investigate the variation of structural heterogeneity and plasticity of a Zr-based MG after high-temperature (T) tension under different stresses (σ) at 579 K (0.9Tg, where Tg is the glass transition temperature). The correlation length (ξ) of the heterogeneous structure and the average Young's modulus ( E ¯ ) increase with σ when σ is below 160 MPa; when σ exceeds 160 MPa, both ξ and E ¯ decrease with σ, leading to the improvement of the plasticity. This research could be enlightening for improving the plasticity of MGs at RT through tuning their structural heterogeneity with high-T deformation. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results