FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3143609527> ?p ?o ?g. }

• W3143609527 abstract "Weakly supervised video anomaly detection (WS-VAD) is to distinguish anomalies from normal events based on discriminative representations. Most existing works are limited in insufficient video representations. In this work, we develop a multiple instance self-training framework (MIST)to efficiently refine task-specific discriminative representations with only video-level annotations. In particular, MIST is composed of 1) a multiple instance pseudo label generator, which adapts a sparse continuous sampling strategy to produce more reliable clip-level pseudo labels, and 2) a self-guided attention boosted feature encoder that aims to automatically focus on anomalous regions in frames while extracting task-specific representations. Moreover, we adopt a self-training scheme to optimize both components and finally obtain a task-specific feature encoder. Extensive experiments on two public datasets demonstrate the efficacy of our method, and our method performs comparably to or even better than existing supervised and weakly supervised methods, specifically obtaining a frame-level AUC 94.83% on ShanghaiTech." @default.
• W3143609527 created "2021-04-13" @default.
• W3143609527 creator A5074327829 @default.
• W3143609527 creator A5082605318 @default.
• W3143609527 creator A5089744902 @default.
• W3143609527 date "2021-04-04" @default.
• W3143609527 modified "2023-09-23" @default.
• W3143609527 title "MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection" @default.
• W3143609527 cites W1522734439 @default.
• W3143609527 cites W2016053056 @default.
• W3143609527 cites W2021659075 @default.
• W3143609527 cites W2106401878 @default.
• W3143609527 cites W2145494108 @default.
• W3143609527 cites W2163612318 @default.
• W3143609527 cites W2187089797 @default.
• W3143609527 cites W2341058432 @default.
• W3143609527 cites W2539222059 @default.
• W3143609527 cites W2618574054 @default.
• W3143609527 cites W2619947201 @default.
• W3143609527 cites W2766042539 @default.
• W3143609527 cites W2777342313 @default.
• W3143609527 cites W2798503473 @default.
• W3143609527 cites W2895281799 @default.
• W3143609527 cites W2915683453 @default.
• W3143609527 cites W2921491036 @default.
• W3143609527 cites W2933801392 @default.
• W3143609527 cites W2962709777 @default.
• W3143609527 cites W2962858109 @default.
• W3143609527 cites W2963315828 @default.
• W3143609527 cites W2963524571 @default.
• W3143609527 cites W2963610939 @default.
• W3143609527 cites W2963795951 @default.
• W3143609527 cites W2966277378 @default.
• W3143609527 cites W2970271202 @default.
• W3143609527 cites W2982190919 @default.
• W3143609527 cites W2985406498 @default.
• W3143609527 cites W2991133498 @default.
• W3143609527 cites W3009803092 @default.
• W3143609527 cites W3015115644 @default.
• W3143609527 cites W3021284621 @default.
• W3143609527 cites W3035699237 @default.
• W3143609527 cites W3077420696 @default.
• W3143609527 cites W3089682612 @default.
• W3143609527 cites W3109316002 @default.
• W3143609527 cites W38936090 @default.
• W3143609527 doi "https://doi.org/10.48550/arxiv.2104.01633" @default.
• W3143609527 hasPublicationYear "2021" @default.
• W3143609527 type Work @default.
• W3143609527 sameAs 3143609527 @default.
• W3143609527 citedByCount "2" @default.
• W3143609527 countsByYear W31436095272021 @default.
• W3143609527 crossrefType "posted-content" @default.
• W3143609527 hasAuthorship W3143609527A5074327829 @default.
• W3143609527 hasAuthorship W3143609527A5082605318 @default.
• W3143609527 hasAuthorship W3143609527A5089744902 @default.
• W3143609527 hasBestOaLocation W31436095271 @default.
• W3143609527 hasConcept C111919701 @default.
• W3143609527 hasConcept C118505674 @default.
• W3143609527 hasConcept C119857082 @default.
• W3143609527 hasConcept C120665830 @default.
• W3143609527 hasConcept C121332964 @default.
• W3143609527 hasConcept C126042441 @default.
• W3143609527 hasConcept C138885662 @default.
• W3143609527 hasConcept C153180895 @default.
• W3143609527 hasConcept C153294291 @default.
• W3143609527 hasConcept C154945302 @default.
• W3143609527 hasConcept C162324750 @default.
• W3143609527 hasConcept C163258240 @default.
• W3143609527 hasConcept C187736073 @default.
• W3143609527 hasConcept C192209626 @default.
• W3143609527 hasConcept C2776401178 @default.
• W3143609527 hasConcept C2780451532 @default.
• W3143609527 hasConcept C2780992000 @default.
• W3143609527 hasConcept C41008148 @default.
• W3143609527 hasConcept C41895202 @default.
• W3143609527 hasConcept C62520636 @default.
• W3143609527 hasConcept C6831451 @default.
• W3143609527 hasConcept C739882 @default.
• W3143609527 hasConcept C76155785 @default.
• W3143609527 hasConcept C97931131 @default.
• W3143609527 hasConceptScore W3143609527C111919701 @default.
• W3143609527 hasConceptScore W3143609527C118505674 @default.
• W3143609527 hasConceptScore W3143609527C119857082 @default.
• W3143609527 hasConceptScore W3143609527C120665830 @default.
• W3143609527 hasConceptScore W3143609527C121332964 @default.
• W3143609527 hasConceptScore W3143609527C126042441 @default.
• W3143609527 hasConceptScore W3143609527C138885662 @default.
• W3143609527 hasConceptScore W3143609527C153180895 @default.
• W3143609527 hasConceptScore W3143609527C153294291 @default.
• W3143609527 hasConceptScore W3143609527C154945302 @default.
• W3143609527 hasConceptScore W3143609527C162324750 @default.
• W3143609527 hasConceptScore W3143609527C163258240 @default.
• W3143609527 hasConceptScore W3143609527C187736073 @default.
• W3143609527 hasConceptScore W3143609527C192209626 @default.
• W3143609527 hasConceptScore W3143609527C2776401178 @default.
• W3143609527 hasConceptScore W3143609527C2780451532 @default.
• W3143609527 hasConceptScore W3143609527C2780992000 @default.
• W3143609527 hasConceptScore W3143609527C41008148 @default.
• W3143609527 hasConceptScore W3143609527C41895202 @default.
• W3143609527 hasConceptScore W3143609527C62520636 @default.

• next