Matches in SemOpenAlex for { <https://semopenalex.org/work/W2969789050> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2969789050 abstract "As in many areas with deep learning methods, great success is achieved in object and scene recognition, but for a good result a large number of labeled data is needed. Our aim in this study is to eliminate the need for tagged data collection that requires too much human labor, and to use the abundant images as data set, paired with the object name on the Internet and social media. However, this data is not as clean as manually labeled data, and it does not work well when used directly. In this study, Association with Model Evolution (AME) method is adapted to eliminate noisy data. Data that were automatically collected and cleaned with AME were then used as the experimental set for Convolutional Neural Networks (CNN). It is observed that the performance is increased by 4% with using the AME cleaned data." @default.
- W2969789050 created "2019-08-29" @default.
- W2969789050 creator A5046310570 @default.
- W2969789050 creator A5048195433 @default.
- W2969789050 creator A5057644494 @default.
- W2969789050 creator A5079057791 @default.
- W2969789050 creator A5087967178 @default.
- W2969789050 date "2019-04-01" @default.
- W2969789050 modified "2023-09-26" @default.
- W2969789050 title "Learning Semantic Concepts from Weakly Labeled Data" @default.
- W2969789050 cites W1522734439 @default.
- W2969789050 cites W1897210561 @default.
- W2969789050 cites W1923404803 @default.
- W2969789050 cites W2016053056 @default.
- W2969789050 cites W2097117768 @default.
- W2969789050 cites W2117539524 @default.
- W2969789050 cites W2156303437 @default.
- W2969789050 cites W2163605009 @default.
- W2969789050 cites W2962835968 @default.
- W2969789050 cites W2964121744 @default.
- W2969789050 doi "https://doi.org/10.1109/siu.2019.8806477" @default.
- W2969789050 hasPublicationYear "2019" @default.
- W2969789050 type Work @default.
- W2969789050 sameAs 2969789050 @default.
- W2969789050 citedByCount "0" @default.
- W2969789050 crossrefType "proceedings-article" @default.
- W2969789050 hasAuthorship W2969789050A5046310570 @default.
- W2969789050 hasAuthorship W2969789050A5048195433 @default.
- W2969789050 hasAuthorship W2969789050A5057644494 @default.
- W2969789050 hasAuthorship W2969789050A5079057791 @default.
- W2969789050 hasAuthorship W2969789050A5087967178 @default.
- W2969789050 hasConcept C108583219 @default.
- W2969789050 hasConcept C110875604 @default.
- W2969789050 hasConcept C119857082 @default.
- W2969789050 hasConcept C136764020 @default.
- W2969789050 hasConcept C153180895 @default.
- W2969789050 hasConcept C154945302 @default.
- W2969789050 hasConcept C177264268 @default.
- W2969789050 hasConcept C199360897 @default.
- W2969789050 hasConcept C2776145971 @default.
- W2969789050 hasConcept C2781238097 @default.
- W2969789050 hasConcept C41008148 @default.
- W2969789050 hasConcept C518677369 @default.
- W2969789050 hasConcept C58489278 @default.
- W2969789050 hasConcept C67186912 @default.
- W2969789050 hasConcept C77088390 @default.
- W2969789050 hasConcept C81363708 @default.
- W2969789050 hasConceptScore W2969789050C108583219 @default.
- W2969789050 hasConceptScore W2969789050C110875604 @default.
- W2969789050 hasConceptScore W2969789050C119857082 @default.
- W2969789050 hasConceptScore W2969789050C136764020 @default.
- W2969789050 hasConceptScore W2969789050C153180895 @default.
- W2969789050 hasConceptScore W2969789050C154945302 @default.
- W2969789050 hasConceptScore W2969789050C177264268 @default.
- W2969789050 hasConceptScore W2969789050C199360897 @default.
- W2969789050 hasConceptScore W2969789050C2776145971 @default.
- W2969789050 hasConceptScore W2969789050C2781238097 @default.
- W2969789050 hasConceptScore W2969789050C41008148 @default.
- W2969789050 hasConceptScore W2969789050C518677369 @default.
- W2969789050 hasConceptScore W2969789050C58489278 @default.
- W2969789050 hasConceptScore W2969789050C67186912 @default.
- W2969789050 hasConceptScore W2969789050C77088390 @default.
- W2969789050 hasConceptScore W2969789050C81363708 @default.
- W2969789050 hasLocation W29697890501 @default.
- W2969789050 hasOpenAccess W2969789050 @default.
- W2969789050 hasPrimaryLocation W29697890501 @default.
- W2969789050 hasRelatedWork W2001387620 @default.
- W2969789050 hasRelatedWork W2039216248 @default.
- W2969789050 hasRelatedWork W2107250100 @default.
- W2969789050 hasRelatedWork W2125271533 @default.
- W2969789050 hasRelatedWork W2480562445 @default.
- W2969789050 hasRelatedWork W2618285232 @default.
- W2969789050 hasRelatedWork W2775014820 @default.
- W2969789050 hasRelatedWork W2889174280 @default.
- W2969789050 hasRelatedWork W2896496692 @default.
- W2969789050 hasRelatedWork W2945192907 @default.
- W2969789050 hasRelatedWork W2969955062 @default.
- W2969789050 hasRelatedWork W2982393246 @default.
- W2969789050 hasRelatedWork W2982650666 @default.
- W2969789050 hasRelatedWork W2991538397 @default.
- W2969789050 hasRelatedWork W3009953871 @default.
- W2969789050 hasRelatedWork W3124610200 @default.
- W2969789050 hasRelatedWork W3127946721 @default.
- W2969789050 hasRelatedWork W3129272094 @default.
- W2969789050 hasRelatedWork W3176782276 @default.
- W2969789050 hasRelatedWork W347570665 @default.
- W2969789050 isParatext "false" @default.
- W2969789050 isRetracted "false" @default.
- W2969789050 magId "2969789050" @default.
- W2969789050 workType "article" @default.