FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2071519463> ?p ?o ?g. }

• W2071519463 endingPage "871" @default.
• W2071519463 startingPage "860" @default.
• W2071519463 abstract "For automatic object detection tasks, large amounts of training images are usually labeled to achieve more reliable training of the object classifiers; this is cost-expensive since it requires hiring professionals to label large-scale training images. When a large number of object classes come into view, the issue of obtaining a large enough amount of the labeled training images becomes more critical. There are three potential solutions to reduce the burden for image labeling: (1) allowing people to provide the object labels loosely at the image level rather than at the object level (e.g., loosely-tagged images without identifying the exact object locations in the images); (2) harnessing large-scale collaboratively-tagged images that are available on the Internet; and, (3) developing new machine learning algorithms that can directly leverage large-scale collaboratively- or loosely-tagged images for achieving more effective training of a large number of object classifiers. Based on these observations, a multi-task multi-label multiple instance learning (MTML-MIL) algorithm is developed in this paper by leveraging both interobject correlations and large-scale loosely-labeled images for object classifier training. By seamlessly integrating multi-task learning, multi-label learning, and multiple instance learning, our MTML-MIL algorithm can achieve more accurate training of a large number of inter-related object classifiers (where an object network is constructed for determining the inter-related learning tasks directly in the feature space rather than in the label space). Our experimental results have shown that our MTML-MIL algorithm can achieve higher detection accuracy rates for automatic object detection." @default.
• W2071519463 created "2016-06-24" @default.
• W2071519463 creator A5045434740 @default.
• W2071519463 creator A5063145868 @default.
• W2071519463 date "2010-11-01" @default.
• W2071519463 modified "2023-10-16" @default.
• W2071519463 title "Multi-taskmulti-labelmultiple instance learning" @default.
• W2071519463 cites W1507854426 @default.
• W2071519463 cites W1540386283 @default.
• W2071519463 cites W1554039773 @default.
• W2071519463 cites W1964803612 @default.
• W2071519463 cites W1987496434 @default.
• W2071519463 cites W1995282358 @default.
• W2071519463 cites W1997454659 @default.
• W2071519463 cites W2031248101 @default.
• W2071519463 cites W2098020658 @default.
• W2071519463 cites W2098166271 @default.
• W2071519463 cites W2100567627 @default.
• W2071519463 cites W2105842272 @default.
• W2071519463 cites W2106582716 @default.
• W2071519463 cites W2112301665 @default.
• W2071519463 cites W2115694019 @default.
• W2071519463 cites W2117990954 @default.
• W2071519463 cites W2135533176 @default.
• W2071519463 cites W2143854982 @default.
• W2071519463 cites W2144752499 @default.
• W2071519463 cites W2151986602 @default.
• W2071519463 cites W2156935079 @default.
• W2071519463 cites W2157825442 @default.
• W2071519463 cites W2164736477 @default.
• W2071519463 cites W2165232124 @default.
• W2071519463 cites W2166516899 @default.
• W2071519463 cites W2168793192 @default.
• W2071519463 cites W2171188998 @default.
• W2071519463 cites W2171881030 @default.
• W2071519463 doi "https://doi.org/10.1631/jzus.c1001005" @default.
• W2071519463 hasPublicationYear "2010" @default.
• W2071519463 type Work @default.
• W2071519463 sameAs 2071519463 @default.
• W2071519463 citedByCount "5" @default.
• W2071519463 countsByYear W20715194632013 @default.
• W2071519463 countsByYear W20715194632015 @default.
• W2071519463 countsByYear W20715194632016 @default.
• W2071519463 countsByYear W20715194632018 @default.
• W2071519463 countsByYear W20715194632019 @default.
• W2071519463 crossrefType "journal-article" @default.
• W2071519463 hasAuthorship W2071519463A5045434740 @default.
• W2071519463 hasAuthorship W2071519463A5063145868 @default.
• W2071519463 hasConcept C119857082 @default.
• W2071519463 hasConcept C121332964 @default.
• W2071519463 hasConcept C153083717 @default.
• W2071519463 hasConcept C153180895 @default.
• W2071519463 hasConcept C154945302 @default.
• W2071519463 hasConcept C162324750 @default.
• W2071519463 hasConcept C187736073 @default.
• W2071519463 hasConcept C2776151529 @default.
• W2071519463 hasConcept C2778755073 @default.
• W2071519463 hasConcept C2780451532 @default.
• W2071519463 hasConcept C2781238097 @default.
• W2071519463 hasConcept C31972630 @default.
• W2071519463 hasConcept C41008148 @default.
• W2071519463 hasConcept C62520636 @default.
• W2071519463 hasConcept C64876066 @default.
• W2071519463 hasConcept C95623464 @default.
• W2071519463 hasConceptScore W2071519463C119857082 @default.
• W2071519463 hasConceptScore W2071519463C121332964 @default.
• W2071519463 hasConceptScore W2071519463C153083717 @default.
• W2071519463 hasConceptScore W2071519463C153180895 @default.
• W2071519463 hasConceptScore W2071519463C154945302 @default.
• W2071519463 hasConceptScore W2071519463C162324750 @default.
• W2071519463 hasConceptScore W2071519463C187736073 @default.
• W2071519463 hasConceptScore W2071519463C2776151529 @default.
• W2071519463 hasConceptScore W2071519463C2778755073 @default.
• W2071519463 hasConceptScore W2071519463C2780451532 @default.
• W2071519463 hasConceptScore W2071519463C2781238097 @default.
• W2071519463 hasConceptScore W2071519463C31972630 @default.
• W2071519463 hasConceptScore W2071519463C41008148 @default.
• W2071519463 hasConceptScore W2071519463C62520636 @default.
• W2071519463 hasConceptScore W2071519463C64876066 @default.
• W2071519463 hasConceptScore W2071519463C95623464 @default.
• W2071519463 hasIssue "11" @default.
• W2071519463 hasLocation W20715194631 @default.
• W2071519463 hasOpenAccess W2071519463 @default.
• W2071519463 hasPrimaryLocation W20715194631 @default.
• W2071519463 hasRelatedWork W1988485990 @default.
• W2071519463 hasRelatedWork W2007544051 @default.
• W2071519463 hasRelatedWork W2095705906 @default.
• W2071519463 hasRelatedWork W2200925278 @default.
• W2071519463 hasRelatedWork W2334336442 @default.
• W2071519463 hasRelatedWork W2363840281 @default.
• W2071519463 hasRelatedWork W2613077666 @default.
• W2071519463 hasRelatedWork W2732308154 @default.
• W2071519463 hasRelatedWork W2975200075 @default.
• W2071519463 hasRelatedWork W3177406559 @default.
• W2071519463 hasVolume "11" @default.
• W2071519463 isParatext "false" @default.
• W2071519463 isRetracted "false" @default.
• W2071519463 magId "2071519463" @default.

• next