Matches in SemOpenAlex for { <https://semopenalex.org/work/W4225624178> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4225624178 endingPage "15" @default.
- W4225624178 startingPage "1" @default.
- W4225624178 abstract "Video anomaly detection (VAD) refers to the discrimination of unexpected events in videos. The deep generative model (DGM)-based method learns the regular patterns on normal videos and expects the learned model to yield larger generative errors for abnormal frames. However, DGM cannot always do so, since it usually captures the shared patterns between normal and abnormal events, which results in similar generative errors for them. In this article, we propose a novel self-supervised framework for unsupervised VAD to tackle the above-mentioned problem. To this end, we design a novel self-supervised attentive generative adversarial network (SSAGAN), which is composed of the self-attentive predictor, the vanilla discriminator, and the self-supervised discriminator. On the one hand, the self-attentive predictor can capture the long-term dependences for improving the prediction qualities of normal frames. On the other hand, the predicted frames are fed to the vanilla discriminator and self-supervised discriminator for performing true-false discrimination and self-supervised rotation detection, respectively. Essentially, the role of the self-supervised task is to enable the predictor to encode semantic information into the predicted normal frames via adversarial training, in order for the angles of rotated normal frames can be detected. As a result, our self-supervised framework lessens the generalization ability of the model to abnormal frames, resulting in larger detection errors for abnormal frames. Extensive experimental results indicate that SSAGAN outperforms other state-of-the-art methods, which demonstrates the validity and advancement of SSAGAN." @default.
- W4225624178 created "2022-05-05" @default.
- W4225624178 creator A5000581688 @default.
- W4225624178 creator A5004565086 @default.
- W4225624178 creator A5006594763 @default.
- W4225624178 creator A5017617923 @default.
- W4225624178 creator A5026662451 @default.
- W4225624178 creator A5030589675 @default.
- W4225624178 creator A5071466291 @default.
- W4225624178 date "2022-01-01" @default.
- W4225624178 modified "2023-10-03" @default.
- W4225624178 title "Self-Supervised Attentive Generative Adversarial Networks for Video Anomaly Detection" @default.
- W4225624178 doi "https://doi.org/10.1109/tnnls.2022.3159538" @default.
- W4225624178 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35380972" @default.
- W4225624178 hasPublicationYear "2022" @default.
- W4225624178 type Work @default.
- W4225624178 citedByCount "14" @default.
- W4225624178 countsByYear W42256241782022 @default.
- W4225624178 countsByYear W42256241782023 @default.
- W4225624178 crossrefType "journal-article" @default.
- W4225624178 hasAuthorship W4225624178A5000581688 @default.
- W4225624178 hasAuthorship W4225624178A5004565086 @default.
- W4225624178 hasAuthorship W4225624178A5006594763 @default.
- W4225624178 hasAuthorship W4225624178A5017617923 @default.
- W4225624178 hasAuthorship W4225624178A5026662451 @default.
- W4225624178 hasAuthorship W4225624178A5030589675 @default.
- W4225624178 hasAuthorship W4225624178A5071466291 @default.
- W4225624178 hasConcept C119857082 @default.
- W4225624178 hasConcept C134306372 @default.
- W4225624178 hasConcept C153180895 @default.
- W4225624178 hasConcept C154945302 @default.
- W4225624178 hasConcept C162324750 @default.
- W4225624178 hasConcept C177148314 @default.
- W4225624178 hasConcept C187736073 @default.
- W4225624178 hasConcept C199360897 @default.
- W4225624178 hasConcept C2779803651 @default.
- W4225624178 hasConcept C2780451532 @default.
- W4225624178 hasConcept C2780801425 @default.
- W4225624178 hasConcept C33923547 @default.
- W4225624178 hasConcept C39890363 @default.
- W4225624178 hasConcept C41008148 @default.
- W4225624178 hasConcept C739882 @default.
- W4225624178 hasConcept C76155785 @default.
- W4225624178 hasConcept C94915269 @default.
- W4225624178 hasConceptScore W4225624178C119857082 @default.
- W4225624178 hasConceptScore W4225624178C134306372 @default.
- W4225624178 hasConceptScore W4225624178C153180895 @default.
- W4225624178 hasConceptScore W4225624178C154945302 @default.
- W4225624178 hasConceptScore W4225624178C162324750 @default.
- W4225624178 hasConceptScore W4225624178C177148314 @default.
- W4225624178 hasConceptScore W4225624178C187736073 @default.
- W4225624178 hasConceptScore W4225624178C199360897 @default.
- W4225624178 hasConceptScore W4225624178C2779803651 @default.
- W4225624178 hasConceptScore W4225624178C2780451532 @default.
- W4225624178 hasConceptScore W4225624178C2780801425 @default.
- W4225624178 hasConceptScore W4225624178C33923547 @default.
- W4225624178 hasConceptScore W4225624178C39890363 @default.
- W4225624178 hasConceptScore W4225624178C41008148 @default.
- W4225624178 hasConceptScore W4225624178C739882 @default.
- W4225624178 hasConceptScore W4225624178C76155785 @default.
- W4225624178 hasConceptScore W4225624178C94915269 @default.
- W4225624178 hasFunder F4320335803 @default.
- W4225624178 hasLocation W42256241781 @default.
- W4225624178 hasLocation W42256241782 @default.
- W4225624178 hasOpenAccess W4225624178 @default.
- W4225624178 hasPrimaryLocation W42256241781 @default.
- W4225624178 hasRelatedWork W2076520961 @default.
- W4225624178 hasRelatedWork W2896600774 @default.
- W4225624178 hasRelatedWork W2906643110 @default.
- W4225624178 hasRelatedWork W2951337574 @default.
- W4225624178 hasRelatedWork W2975513049 @default.
- W4225624178 hasRelatedWork W3003955104 @default.
- W4225624178 hasRelatedWork W3033268347 @default.
- W4225624178 hasRelatedWork W3040099731 @default.
- W4225624178 hasRelatedWork W4280544492 @default.
- W4225624178 hasRelatedWork W4289406342 @default.
- W4225624178 isParatext "false" @default.
- W4225624178 isRetracted "false" @default.
- W4225624178 workType "article" @default.