Matches in SemOpenAlex for { <https://semopenalex.org/work/W3109173645> ?p ?o ?g. }
- W3109173645 endingPage "87" @default.
- W3109173645 startingPage "71" @default.
- W3109173645 abstract "Understanding interaction is an essential part of video action detection. We propose the Asynchronous Interaction Aggregation network (AIA) that leverages different interactions to boost action detection. There are two key designs in it: one is the Interaction Aggregation structure (IA) adopting a uniform paradigm to model and integrate multiple types of interaction; the other is the Asynchronous Memory Update algorithm (AMU) that enables us to achieve better performance by modeling very long-term interaction dynamically without huge computation cost. We provide empirical evidence to show that our network can gain notable accuracy from the integrative interactions and is easy to train end-to-end. Our method reports the new state-of-the-art performance on AVA dataset, with 3.7 mAP gain ( $$12.6%$$ relative improvement) on validation split comparing to our strong baseline. The results on datasets UCF101-24 and EPIC-Kitchens further illustrate the effectiveness of our approach. Source code will be made public at: https://github.com/MVIG-SJTU/AlphAction ." @default.
- W3109173645 created "2020-12-07" @default.
- W3109173645 creator A5008802390 @default.
- W3109173645 creator A5010726528 @default.
- W3109173645 creator A5053615892 @default.
- W3109173645 creator A5058655480 @default.
- W3109173645 creator A5068160937 @default.
- W3109173645 date "2020-01-01" @default.
- W3109173645 modified "2023-09-30" @default.
- W3109173645 title "Asynchronous Interaction Aggregation for Action Detection" @default.
- W3109173645 cites W1536680647 @default.
- W3109173645 cites W1586730761 @default.
- W3109173645 cites W1861492603 @default.
- W3109173645 cites W1927052826 @default.
- W3109173645 cites W1983364832 @default.
- W3109173645 cites W2108598243 @default.
- W3109173645 cites W2235034809 @default.
- W3109173645 cites W2342662179 @default.
- W3109173645 cites W2549139847 @default.
- W3109173645 cites W2565639579 @default.
- W3109173645 cites W2583815496 @default.
- W3109173645 cites W2611596598 @default.
- W3109173645 cites W2618799552 @default.
- W3109173645 cites W2770804203 @default.
- W3109173645 cites W2806331055 @default.
- W3109173645 cites W2809562466 @default.
- W3109173645 cites W2951702519 @default.
- W3109173645 cites W2955874753 @default.
- W3109173645 cites W2962688385 @default.
- W3109173645 cites W2962722947 @default.
- W3109173645 cites W2962790054 @default.
- W3109173645 cites W2963091558 @default.
- W3109173645 cites W2963097937 @default.
- W3109173645 cites W2963150697 @default.
- W3109173645 cites W2963155035 @default.
- W3109173645 cites W2963351448 @default.
- W3109173645 cites W2963524571 @default.
- W3109173645 cites W2963529931 @default.
- W3109173645 cites W2963563276 @default.
- W3109173645 cites W2963820951 @default.
- W3109173645 cites W2964110616 @default.
- W3109173645 cites W2964242760 @default.
- W3109173645 cites W2990503944 @default.
- W3109173645 doi "https://doi.org/10.1007/978-3-030-58555-6_5" @default.
- W3109173645 hasPublicationYear "2020" @default.
- W3109173645 type Work @default.
- W3109173645 sameAs 3109173645 @default.
- W3109173645 citedByCount "32" @default.
- W3109173645 countsByYear W31091736452021 @default.
- W3109173645 countsByYear W31091736452022 @default.
- W3109173645 countsByYear W31091736452023 @default.
- W3109173645 crossrefType "book-chapter" @default.
- W3109173645 hasAuthorship W3109173645A5008802390 @default.
- W3109173645 hasAuthorship W3109173645A5010726528 @default.
- W3109173645 hasAuthorship W3109173645A5053615892 @default.
- W3109173645 hasAuthorship W3109173645A5058655480 @default.
- W3109173645 hasAuthorship W3109173645A5068160937 @default.
- W3109173645 hasBestOaLocation W31091736452 @default.
- W3109173645 hasConcept C104317684 @default.
- W3109173645 hasConcept C11413529 @default.
- W3109173645 hasConcept C115519274 @default.
- W3109173645 hasConcept C119857082 @default.
- W3109173645 hasConcept C120314980 @default.
- W3109173645 hasConcept C121332964 @default.
- W3109173645 hasConcept C124952713 @default.
- W3109173645 hasConcept C142362112 @default.
- W3109173645 hasConcept C151319957 @default.
- W3109173645 hasConcept C154945302 @default.
- W3109173645 hasConcept C177264268 @default.
- W3109173645 hasConcept C185592680 @default.
- W3109173645 hasConcept C199360897 @default.
- W3109173645 hasConcept C26517878 @default.
- W3109173645 hasConcept C2776760102 @default.
- W3109173645 hasConcept C2780791683 @default.
- W3109173645 hasConcept C31258907 @default.
- W3109173645 hasConcept C38652104 @default.
- W3109173645 hasConcept C41008148 @default.
- W3109173645 hasConcept C45374587 @default.
- W3109173645 hasConcept C55105296 @default.
- W3109173645 hasConcept C55493867 @default.
- W3109173645 hasConcept C62520636 @default.
- W3109173645 hasConcept C80444323 @default.
- W3109173645 hasConceptScore W3109173645C104317684 @default.
- W3109173645 hasConceptScore W3109173645C11413529 @default.
- W3109173645 hasConceptScore W3109173645C115519274 @default.
- W3109173645 hasConceptScore W3109173645C119857082 @default.
- W3109173645 hasConceptScore W3109173645C120314980 @default.
- W3109173645 hasConceptScore W3109173645C121332964 @default.
- W3109173645 hasConceptScore W3109173645C124952713 @default.
- W3109173645 hasConceptScore W3109173645C142362112 @default.
- W3109173645 hasConceptScore W3109173645C151319957 @default.
- W3109173645 hasConceptScore W3109173645C154945302 @default.
- W3109173645 hasConceptScore W3109173645C177264268 @default.
- W3109173645 hasConceptScore W3109173645C185592680 @default.
- W3109173645 hasConceptScore W3109173645C199360897 @default.
- W3109173645 hasConceptScore W3109173645C26517878 @default.
- W3109173645 hasConceptScore W3109173645C2776760102 @default.
- W3109173645 hasConceptScore W3109173645C2780791683 @default.