Matches in SemOpenAlex for { <https://semopenalex.org/work/W2991463725> ?p ?o ?g. }
- W2991463725 abstract "Surveillance video anomaly detection is to detect events that rarely or never happened in a certain scene. The generation error (GE)-based methods exhibit excellent performance on this task. They firstly train a generative neural network (GNN) to generate normal samples, then judge the samples with large GEs as anomalies. Almost all the GE-based methods utilize frame-level GEs to detect anomalies. However, anomalies generally occur in local areas, the frame-level GE introduces GEs of normal areas to anomaly discriminations, that brings two problems: i) The GE of normal areas reduces the anomaly saliency of the anomalous frame. ii) Different videos have different normal-GE-levels, thus it is hard to set a uniform threshold for all videos to detect anomalies. To address these problems, we propose a promotion method: utilize the maximum of block-level GEs on the frame to detect anomaly. Firstly, we calculate the block-level GEs at each position on the frame. Then, we utilize the maximum of the block-level GEs on the frame to detect anomalies. Based on the existed GNN models, experiments are carried out on multiple datasets. The results demonstrate the effectiveness of the proposed method and achieve state-of-the-art performance." @default.
- W2991463725 created "2019-12-05" @default.
- W2991463725 creator A5020864189 @default.
- W2991463725 creator A5041522926 @default.
- W2991463725 creator A5069796893 @default.
- W2991463725 date "2019-11-19" @default.
- W2991463725 modified "2023-09-27" @default.
- W2991463725 title "A Promotion Method for Generation Error Based Video Anomaly Detection" @default.
- W2991463725 cites W1967456674 @default.
- W2991463725 cites W2004149082 @default.
- W2991463725 cites W2007068391 @default.
- W2991463725 cites W2012931101 @default.
- W2991463725 cites W2021659075 @default.
- W2991463725 cites W2074076772 @default.
- W2991463725 cites W2074508921 @default.
- W2991463725 cites W2079023123 @default.
- W2991463725 cites W2110383222 @default.
- W2991463725 cites W2122361470 @default.
- W2991463725 cites W2125105611 @default.
- W2991463725 cites W2138092272 @default.
- W2991463725 cites W2163612318 @default.
- W2991463725 cites W2337453828 @default.
- W2991463725 cites W2341058432 @default.
- W2991463725 cites W2523332653 @default.
- W2991463725 cites W2531279268 @default.
- W2991463725 cites W2540481276 @default.
- W2991463725 cites W2559927751 @default.
- W2991463725 cites W2579718262 @default.
- W2991463725 cites W2665124875 @default.
- W2991463725 cites W2739846485 @default.
- W2991463725 cites W2743588686 @default.
- W2991463725 cites W2753526808 @default.
- W2991463725 cites W2766042539 @default.
- W2991463725 cites W2777288981 @default.
- W2991463725 cites W2777342313 @default.
- W2991463725 cites W2805132145 @default.
- W2991463725 cites W2807998075 @default.
- W2991463725 cites W2808699053 @default.
- W2991463725 cites W2889915804 @default.
- W2991463725 cites W2899116516 @default.
- W2991463725 cites W2910068345 @default.
- W2991463725 cites W2951206671 @default.
- W2991463725 cites W2963061824 @default.
- W2991463725 cites W2963215781 @default.
- W2991463725 cites W2963240734 @default.
- W2991463725 cites W2963610939 @default.
- W2991463725 cites W2963899855 @default.
- W2991463725 cites W2964032056 @default.
- W2991463725 cites W2964232409 @default.
- W2991463725 cites W2987146532 @default.
- W2991463725 cites W3015832418 @default.
- W2991463725 doi "https://doi.org/10.48550/arxiv.1911.08402" @default.
- W2991463725 hasPublicationYear "2019" @default.
- W2991463725 type Work @default.
- W2991463725 sameAs 2991463725 @default.
- W2991463725 citedByCount "0" @default.
- W2991463725 crossrefType "posted-content" @default.
- W2991463725 hasAuthorship W2991463725A5020864189 @default.
- W2991463725 hasAuthorship W2991463725A5041522926 @default.
- W2991463725 hasAuthorship W2991463725A5069796893 @default.
- W2991463725 hasBestOaLocation W29914637251 @default.
- W2991463725 hasConcept C10138342 @default.
- W2991463725 hasConcept C121332964 @default.
- W2991463725 hasConcept C126042441 @default.
- W2991463725 hasConcept C12997251 @default.
- W2991463725 hasConcept C153180895 @default.
- W2991463725 hasConcept C154945302 @default.
- W2991463725 hasConcept C162324750 @default.
- W2991463725 hasConcept C177264268 @default.
- W2991463725 hasConcept C198082294 @default.
- W2991463725 hasConcept C199360897 @default.
- W2991463725 hasConcept C2524010 @default.
- W2991463725 hasConcept C26873012 @default.
- W2991463725 hasConcept C2777210771 @default.
- W2991463725 hasConcept C31972630 @default.
- W2991463725 hasConcept C33923547 @default.
- W2991463725 hasConcept C39890363 @default.
- W2991463725 hasConcept C41008148 @default.
- W2991463725 hasConcept C739882 @default.
- W2991463725 hasConcept C76155785 @default.
- W2991463725 hasConceptScore W2991463725C10138342 @default.
- W2991463725 hasConceptScore W2991463725C121332964 @default.
- W2991463725 hasConceptScore W2991463725C126042441 @default.
- W2991463725 hasConceptScore W2991463725C12997251 @default.
- W2991463725 hasConceptScore W2991463725C153180895 @default.
- W2991463725 hasConceptScore W2991463725C154945302 @default.
- W2991463725 hasConceptScore W2991463725C162324750 @default.
- W2991463725 hasConceptScore W2991463725C177264268 @default.
- W2991463725 hasConceptScore W2991463725C198082294 @default.
- W2991463725 hasConceptScore W2991463725C199360897 @default.
- W2991463725 hasConceptScore W2991463725C2524010 @default.
- W2991463725 hasConceptScore W2991463725C26873012 @default.
- W2991463725 hasConceptScore W2991463725C2777210771 @default.
- W2991463725 hasConceptScore W2991463725C31972630 @default.
- W2991463725 hasConceptScore W2991463725C33923547 @default.
- W2991463725 hasConceptScore W2991463725C39890363 @default.
- W2991463725 hasConceptScore W2991463725C41008148 @default.
- W2991463725 hasConceptScore W2991463725C739882 @default.
- W2991463725 hasConceptScore W2991463725C76155785 @default.
- W2991463725 hasLocation W29914637251 @default.