Zobrazeno 1 - 10
of 1 002
pro vyhledávání: '"An, Gaoyun"'
Video Anomaly Detection (VAD), aiming to identify abnormalities within a specific context and timeframe, is crucial for intelligent Video Surveillance Systems. While recent deep learning-based VAD models have shown promising results by generating hig
Externí odkaz:
http://arxiv.org/abs/2403.19111
Autor:
Liu, Yang, Xia, Zhaoyang, Zhao, Mengyang, Wei, Donglai, Wang, Yuzheng, Siao, Liu, Ju, Bobo, Fang, Gaoyun, Liu, Jing, Song, Liang
Video anomaly detection is an essential yet challenging task in the multimedia community, with promising applications in smart cities and secure communities. Existing methods attempt to learn abstract representations of regular events with statistica
Externí odkaz:
http://arxiv.org/abs/2308.01537
Autor:
Lingzhi Long, Xiaoqing Dai, Tingting Yao, Xiangyu Zhang, Guoliang Jiang, Xiaoyun Cheng, Mao Jiang, Yijun He, Zhangzhe Peng, Gaoyun Hu, Lijian Tao, Jie Meng
Publikováno v:
Biomedicine & Pharmacotherapy, Vol 178, Iss , Pp 117216- (2024)
Aims: Silicosis is the most common and severe type of pneumoconiosis, imposing a substantial disease burden and economic loss on patients and society. The pathogenesis and key targets of silicosis are not yet clear, and there are currently no effecti
Externí odkaz:
https://doaj.org/article/6387855fe3eb44228f8c580478b953a5
Autor:
Mai Han, Bishan Huo, Gaoyun Hu, Xin Zhang, Gang Cui, Wei Wu, Na Mi, Shixi Zhang, Jiangli Jin, Xing Lu, Bidong Wu, Chunyan Xiao, Jing Wang, Zheng Bian, Jintong Li
Publikováno v:
Frontiers in Pharmacology, Vol 15 (2024)
BackgroundMefunidone is a novel synthetic compound and is better when compared to pirfenidone for the anti-fibrotic treatment of renal fibrosis in end-stage renal disease. We conducted this first-in-human, phase I clinical trial to determine the safe
Externí odkaz:
https://doaj.org/article/6d38864a099a4f61b53f25aa58f02dbc
In this paper, a novel approach via embedded tensor manifold regularization for 2D+3D facial expression recognition (FERETMR) is proposed. Firstly, 3D tensors are constructed from 2D face images and 3D face shape models to keep the structural informa
Externí odkaz:
http://arxiv.org/abs/2201.12506
Semantic segmentation methods can not directly identify abnormal objects in images. Anomaly Segmentation algorithm from this realistic setting can distinguish between in-distribution objects and Out-Of-Distribution (OOD) objects and output the anomal
Externí odkaz:
http://arxiv.org/abs/2201.05869
Autor:
Long, Lingzhi, Dai, Xiaoqing, Yao, Tingting, Zhang, Xiangyu, Jiang, Guoliang, Cheng, Xiaoyun, Jiang, Mao, He, Yijun, Peng, Zhangzhe, Hu, Gaoyun, Tao, Lijian, Meng, Jie
Publikováno v:
In Biomedicine & Pharmacotherapy September 2024 178
Publikováno v:
In Pattern Recognition September 2024 153
Autor:
Congke Zhao, Xiangyang Le, Mengqi Li, Yuanbo Hu, Xiaohui Li, Zhuo Chen, Gaoyun Hu, Liqing Hu, Qianbin Li
Publikováno v:
Respiratory Research, Vol 24, Iss 1, Pp 1-18 (2023)
Abstract Background Pulmonary arterial hypertension (PAH) is a progressive and devastating disease characterized by pulmonary vascular remodeling which is associated with the malignant phenotypes of pulmonary vascular cells. Recently, the effects of
Externí odkaz:
https://doaj.org/article/7f33916b5dfa459c8cff3a22fd4e3b1e
Autor:
Yang, Zhaoqilin, An, Gaoyun
The modeling, computational cost, and accuracy of traditional Spatio-temporal networks are the three most concentrated research topics in video action recognition. The traditional 2D convolution has a low computational cost, but it cannot capture the
Externí odkaz:
http://arxiv.org/abs/2112.02523