Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204017462> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W3204017462 endingPage "2141" @default.
- W3204017462 startingPage "2137" @default.
- W3204017462 abstract "Weakly Supervised Anomaly Detection (WSAD) in surveillance videos is a complex task since usually only video-level annotations are available. Previous work treated it as a regression problem by giving different scores on normal and anomaly events. However, the widely used mini-batch training strategy may suffer from the data imbalance between these two types of events, which limits the model's performance. In this work, a cross-epoch learning (XEL) strategy associated with a hard instance bank (HIB) is proposed to introduce additional information from previous training epochs. Two new losses are proposed for XEL to achieve a higher detection rate as well as a lower false alarm rate of anomaly events. Moreover, the proposed XEL can be directly integrated into any existing WSAD framework. Experimental results of three XEL embedded models have shown promising AUC improvement (3%∼7%) on two public datasets, surpassing the state-of-the-art methods. Our code is available at: https://github.com/sdjsngs/XEL-WSAD ." @default.
- W3204017462 created "2021-10-11" @default.
- W3204017462 creator A5007803202 @default.
- W3204017462 creator A5022066800 @default.
- W3204017462 creator A5030616168 @default.
- W3204017462 creator A5046447372 @default.
- W3204017462 creator A5053192405 @default.
- W3204017462 date "2021-01-01" @default.
- W3204017462 modified "2023-09-29" @default.
- W3204017462 title "Cross-Epoch Learning for Weakly Supervised Anomaly Detection in Surveillance Videos" @default.
- W3204017462 cites W1522734439 @default.
- W3204017462 cites W2015468740 @default.
- W3204017462 cites W2163612318 @default.
- W3204017462 cites W2341058432 @default.
- W3204017462 cites W2777342313 @default.
- W3204017462 cites W2798991696 @default.
- W3204017462 cites W2962859295 @default.
- W3204017462 cites W2963061824 @default.
- W3204017462 cites W2963351448 @default.
- W3204017462 cites W2963795951 @default.
- W3204017462 cites W2981741013 @default.
- W3204017462 cites W2987228832 @default.
- W3204017462 cites W3010937474 @default.
- W3204017462 cites W3034523015 @default.
- W3204017462 cites W3035014997 @default.
- W3204017462 cites W3035021504 @default.
- W3204017462 cites W3080722105 @default.
- W3204017462 cites W3110145754 @default.
- W3204017462 doi "https://doi.org/10.1109/lsp.2021.3117737" @default.
- W3204017462 hasPublicationYear "2021" @default.
- W3204017462 type Work @default.
- W3204017462 sameAs 3204017462 @default.
- W3204017462 citedByCount "12" @default.
- W3204017462 countsByYear W32040174622022 @default.
- W3204017462 countsByYear W32040174622023 @default.
- W3204017462 crossrefType "journal-article" @default.
- W3204017462 hasAuthorship W3204017462A5007803202 @default.
- W3204017462 hasAuthorship W3204017462A5022066800 @default.
- W3204017462 hasAuthorship W3204017462A5030616168 @default.
- W3204017462 hasAuthorship W3204017462A5046447372 @default.
- W3204017462 hasAuthorship W3204017462A5053192405 @default.
- W3204017462 hasBestOaLocation W32040174621 @default.
- W3204017462 hasConcept C150846664 @default.
- W3204017462 hasConcept C153180895 @default.
- W3204017462 hasConcept C154945302 @default.
- W3204017462 hasConcept C2776151529 @default.
- W3204017462 hasConcept C2780317896 @default.
- W3204017462 hasConcept C31972630 @default.
- W3204017462 hasConcept C41008148 @default.
- W3204017462 hasConcept C739882 @default.
- W3204017462 hasConceptScore W3204017462C150846664 @default.
- W3204017462 hasConceptScore W3204017462C153180895 @default.
- W3204017462 hasConceptScore W3204017462C154945302 @default.
- W3204017462 hasConceptScore W3204017462C2776151529 @default.
- W3204017462 hasConceptScore W3204017462C2780317896 @default.
- W3204017462 hasConceptScore W3204017462C31972630 @default.
- W3204017462 hasConceptScore W3204017462C41008148 @default.
- W3204017462 hasConceptScore W3204017462C739882 @default.
- W3204017462 hasFunder F4320321001 @default.
- W3204017462 hasLocation W32040174621 @default.
- W3204017462 hasOpenAccess W3204017462 @default.
- W3204017462 hasPrimaryLocation W32040174621 @default.
- W3204017462 hasRelatedWork W1497101000 @default.
- W3204017462 hasRelatedWork W2145985110 @default.
- W3204017462 hasRelatedWork W2533071668 @default.
- W3204017462 hasRelatedWork W2547934522 @default.
- W3204017462 hasRelatedWork W2782964878 @default.
- W3204017462 hasRelatedWork W2922421953 @default.
- W3204017462 hasRelatedWork W2980691083 @default.
- W3204017462 hasRelatedWork W3002270006 @default.
- W3204017462 hasRelatedWork W4281560450 @default.
- W3204017462 hasRelatedWork W4285602384 @default.
- W3204017462 hasVolume "28" @default.
- W3204017462 isParatext "false" @default.
- W3204017462 isRetracted "false" @default.
- W3204017462 magId "3204017462" @default.
- W3204017462 workType "article" @default.