Image-anomaly detection, which is widely used in industrial fields. Previous studies that attempted to address this problem often trained convolutional neural network-based models(e.g., autoencoders and generative adv...Image-anomaly detection, which is widely used in industrial fields. Previous studies that attempted to address this problem often trained convolutional neural network-based models(e.g., autoencoders and generative adversarial networks) to reconstruct covered parts of input images and calculate the difference between the input and reconstructed images. However, convolutional operations are effective at extracting local features, making it difficult to identify larger image anomalies. Method To this end, we propose a transformer architecture based on mutual attention for image-anomaly separation. This architecture can capture long-term dependencies and fuse local and global features to facilitate better image-anomaly detection. Result Our method was extensively evaluated on several benchmarks, and experimental results showed that it improved the detection capability by 3.1% and localization capability by 1.0% compared with state-of-the-art reconstruction-based methods.展开更多
This paper presents a multimedia streaming framework called peer-paired pyramid streaming (P3S) which is basically a hybrid client/server and peer-to-peer structure. In P3S, clients are hierarchically organized with t...This paper presents a multimedia streaming framework called peer-paired pyramid streaming (P3S) which is basically a hybrid client/server and peer-to-peer structure. In P3S, clients are hierarchically organized with those at the same level coupled as peer paris. P3S uses some controlled delay between packets that are vulnerable to shared losses to reduce the shared losses. The technique is verified by both theoretical and experimental results.展开更多
基金Supported by the National Natural Science Foundation of China (No. 61772327)State Grid Gansu Electric Power Company(No. H2019-275)Shanghai Engineering Research Center on Big Data Management System (No.H2020-216)。
文摘Image-anomaly detection, which is widely used in industrial fields. Previous studies that attempted to address this problem often trained convolutional neural network-based models(e.g., autoencoders and generative adversarial networks) to reconstruct covered parts of input images and calculate the difference between the input and reconstructed images. However, convolutional operations are effective at extracting local features, making it difficult to identify larger image anomalies. Method To this end, we propose a transformer architecture based on mutual attention for image-anomaly separation. This architecture can capture long-term dependencies and fuse local and global features to facilitate better image-anomaly detection. Result Our method was extensively evaluated on several benchmarks, and experimental results showed that it improved the detection capability by 3.1% and localization capability by 1.0% compared with state-of-the-art reconstruction-based methods.
基金Supported by the National Natural Science Foundation of China(No.G1999032700)
文摘This paper presents a multimedia streaming framework called peer-paired pyramid streaming (P3S) which is basically a hybrid client/server and peer-to-peer structure. In P3S, clients are hierarchically organized with those at the same level coupled as peer paris. P3S uses some controlled delay between packets that are vulnerable to shared losses to reduce the shared losses. The technique is verified by both theoretical and experimental results.
