Matches in SemOpenAlex for { <https://semopenalex.org/work/W2805932387> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W2805932387 abstract "© 2017. The copyright of this document resides with its authors. We propose a real-time and lightweight multi-task style ConvNet (termed a Factored ConvNet) for human body parsing in images or video. Factored ConvNets have isolated areas which perform known sub-tasks, such as object localization or edge detection. We call this area and sub-task pair an X factor. Unlike multi-task ConvNets which have independent tasks, the Factored ConvNet’s sub-task has direct effect on the main task outcome. In this paper we show how to isolate the X factor of foreground/background (f/b) subtraction from the main task of segmenting human body images into 31 different body part types. Knowledge of this X factor leads to a number of benefits for the Factored ConvNet: 1) Ease of network transfer to other image domains, 2) ability to personalize to humans in video and 3) easy model performance boosts. All achieved by either efficient network update or replacement of the X factor whilst avoiding catastrophic forgetting of previously learnt body part dependencies and structure. We show these benefits on a large dataset of images and also on YouTube videos." @default.
- W2805932387 created "2018-06-13" @default.
- W2805932387 creator A5018207993 @default.
- W2805932387 creator A5057548418 @default.
- W2805932387 creator A5064516143 @default.
- W2805932387 date "2017-01-01" @default.
- W2805932387 modified "2023-09-27" @default.
- W2805932387 title "Real-time factored ConvNets: Extracting the x factor in human parsing" @default.
- W2805932387 doi "https://doi.org/10.17863/cam.21419" @default.
- W2805932387 hasPublicationYear "2017" @default.
- W2805932387 type Work @default.
- W2805932387 sameAs 2805932387 @default.
- W2805932387 citedByCount "1" @default.
- W2805932387 countsByYear W28059323872019 @default.
- W2805932387 crossrefType "proceedings-article" @default.
- W2805932387 hasAuthorship W2805932387A5018207993 @default.
- W2805932387 hasAuthorship W2805932387A5057548418 @default.
- W2805932387 hasAuthorship W2805932387A5064516143 @default.
- W2805932387 hasConcept C119857082 @default.
- W2805932387 hasConcept C153180895 @default.
- W2805932387 hasConcept C154945302 @default.
- W2805932387 hasConcept C160633673 @default.
- W2805932387 hasConcept C162307627 @default.
- W2805932387 hasConcept C162324750 @default.
- W2805932387 hasConcept C186644900 @default.
- W2805932387 hasConcept C187736073 @default.
- W2805932387 hasConcept C199360897 @default.
- W2805932387 hasConcept C2780451532 @default.
- W2805932387 hasConcept C2781039887 @default.
- W2805932387 hasConcept C2781238097 @default.
- W2805932387 hasConcept C31972630 @default.
- W2805932387 hasConcept C32653426 @default.
- W2805932387 hasConcept C41008148 @default.
- W2805932387 hasConceptScore W2805932387C119857082 @default.
- W2805932387 hasConceptScore W2805932387C153180895 @default.
- W2805932387 hasConceptScore W2805932387C154945302 @default.
- W2805932387 hasConceptScore W2805932387C160633673 @default.
- W2805932387 hasConceptScore W2805932387C162307627 @default.
- W2805932387 hasConceptScore W2805932387C162324750 @default.
- W2805932387 hasConceptScore W2805932387C186644900 @default.
- W2805932387 hasConceptScore W2805932387C187736073 @default.
- W2805932387 hasConceptScore W2805932387C199360897 @default.
- W2805932387 hasConceptScore W2805932387C2780451532 @default.
- W2805932387 hasConceptScore W2805932387C2781039887 @default.
- W2805932387 hasConceptScore W2805932387C2781238097 @default.
- W2805932387 hasConceptScore W2805932387C31972630 @default.
- W2805932387 hasConceptScore W2805932387C32653426 @default.
- W2805932387 hasConceptScore W2805932387C41008148 @default.
- W2805932387 hasLocation W28059323871 @default.
- W2805932387 hasOpenAccess W2805932387 @default.
- W2805932387 hasPrimaryLocation W28059323871 @default.
- W2805932387 hasRelatedWork W2017615984 @default.
- W2805932387 hasRelatedWork W2306284509 @default.
- W2805932387 hasRelatedWork W2491457278 @default.
- W2805932387 hasRelatedWork W2565756288 @default.
- W2805932387 hasRelatedWork W2781459369 @default.
- W2805932387 hasRelatedWork W2802056861 @default.
- W2805932387 hasRelatedWork W2918598763 @default.
- W2805932387 hasRelatedWork W2950714698 @default.
- W2805932387 hasRelatedWork W2951781960 @default.
- W2805932387 hasRelatedWork W2951851780 @default.
- W2805932387 hasRelatedWork W2952279306 @default.
- W2805932387 hasRelatedWork W2963814513 @default.
- W2805932387 hasRelatedWork W2963987879 @default.
- W2805932387 hasRelatedWork W2997742385 @default.
- W2805932387 hasRelatedWork W3008930492 @default.
- W2805932387 hasRelatedWork W3037810507 @default.
- W2805932387 hasRelatedWork W3082657012 @default.
- W2805932387 hasRelatedWork W3098883884 @default.
- W2805932387 hasRelatedWork W3170568167 @default.
- W2805932387 hasRelatedWork W3177338182 @default.
- W2805932387 isParatext "false" @default.
- W2805932387 isRetracted "false" @default.
- W2805932387 magId "2805932387" @default.
- W2805932387 workType "article" @default.