Matches in SemOpenAlex for { <https://semopenalex.org/work/W3003641150> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W3003641150 abstract "Object instance recognition and 3D pose estimation are important elements in robot vision technology. State-of-the-art methods improve the accuracy of both instance recognition and pose estimation using multitask learning. These methods use unified balancing parameters to integrate the loss of each task, which means task difficulties are the same for all objects. However, the method we propose can adjust the balancing parameters for each object. This idea is based on the assumption that task difficulties are different for each object, since the distinctiveness of object instances and poses depends on their appearance and shape. Our method sequentially estimates task difficulties for CNN based on the amount of loss change and calculates balancing parameters for each object. Our experiments show that our method improves the accuracy of both object instance recognition and pose estimation compared with state-of-the-art methods using the common LineMOD dataset." @default.
- W3003641150 created "2020-02-07" @default.
- W3003641150 creator A5006365904 @default.
- W3003641150 creator A5035171339 @default.
- W3003641150 creator A5044513038 @default.
- W3003641150 creator A5069602957 @default.
- W3003641150 date "2019-11-01" @default.
- W3003641150 modified "2023-09-27" @default.
- W3003641150 title "Adaptive Loss Balancing for Multitask Learning of Object Instance Recognition and 3D Pose Estimation" @default.
- W3003641150 cites W1526868886 @default.
- W3003641150 cites W1593727536 @default.
- W3003641150 cites W1905829557 @default.
- W3003641150 cites W2041878876 @default.
- W3003641150 cites W2086504823 @default.
- W3003641150 cites W2488101876 @default.
- W3003641150 cites W2777195424 @default.
- W3003641150 cites W2908739874 @default.
- W3003641150 cites W2913340405 @default.
- W3003641150 cites W2962724911 @default.
- W3003641150 cites W2962743139 @default.
- W3003641150 cites W2963188159 @default.
- W3003641150 cites W2963351448 @default.
- W3003641150 cites W2963542991 @default.
- W3003641150 cites W2963775347 @default.
- W3003641150 cites W2964056579 @default.
- W3003641150 cites W2964249569 @default.
- W3003641150 cites W2964342398 @default.
- W3003641150 cites W3101088080 @default.
- W3003641150 doi "https://doi.org/10.1109/iros40897.2019.8968614" @default.
- W3003641150 hasPublicationYear "2019" @default.
- W3003641150 type Work @default.
- W3003641150 sameAs 3003641150 @default.
- W3003641150 citedByCount "0" @default.
- W3003641150 crossrefType "proceedings-article" @default.
- W3003641150 hasAuthorship W3003641150A5006365904 @default.
- W3003641150 hasAuthorship W3003641150A5035171339 @default.
- W3003641150 hasAuthorship W3003641150A5044513038 @default.
- W3003641150 hasAuthorship W3003641150A5069602957 @default.
- W3003641150 hasConcept C119857082 @default.
- W3003641150 hasConcept C127413603 @default.
- W3003641150 hasConcept C153180895 @default.
- W3003641150 hasConcept C154945302 @default.
- W3003641150 hasConcept C15744967 @default.
- W3003641150 hasConcept C201995342 @default.
- W3003641150 hasConcept C2780451532 @default.
- W3003641150 hasConcept C2781238097 @default.
- W3003641150 hasConcept C28006648 @default.
- W3003641150 hasConcept C31972630 @default.
- W3003641150 hasConcept C36613465 @default.
- W3003641150 hasConcept C41008148 @default.
- W3003641150 hasConcept C47385372 @default.
- W3003641150 hasConcept C52102323 @default.
- W3003641150 hasConcept C542102704 @default.
- W3003641150 hasConcept C64876066 @default.
- W3003641150 hasConceptScore W3003641150C119857082 @default.
- W3003641150 hasConceptScore W3003641150C127413603 @default.
- W3003641150 hasConceptScore W3003641150C153180895 @default.
- W3003641150 hasConceptScore W3003641150C154945302 @default.
- W3003641150 hasConceptScore W3003641150C15744967 @default.
- W3003641150 hasConceptScore W3003641150C201995342 @default.
- W3003641150 hasConceptScore W3003641150C2780451532 @default.
- W3003641150 hasConceptScore W3003641150C2781238097 @default.
- W3003641150 hasConceptScore W3003641150C28006648 @default.
- W3003641150 hasConceptScore W3003641150C31972630 @default.
- W3003641150 hasConceptScore W3003641150C36613465 @default.
- W3003641150 hasConceptScore W3003641150C41008148 @default.
- W3003641150 hasConceptScore W3003641150C47385372 @default.
- W3003641150 hasConceptScore W3003641150C52102323 @default.
- W3003641150 hasConceptScore W3003641150C542102704 @default.
- W3003641150 hasConceptScore W3003641150C64876066 @default.
- W3003641150 hasLocation W30036411501 @default.
- W3003641150 hasOpenAccess W3003641150 @default.
- W3003641150 hasPrimaryLocation W30036411501 @default.
- W3003641150 hasRelatedWork W112153112 @default.
- W3003641150 hasRelatedWork W2158703378 @default.
- W3003641150 hasRelatedWork W2770715423 @default.
- W3003641150 hasRelatedWork W2773456899 @default.
- W3003641150 hasRelatedWork W2922451007 @default.
- W3003641150 hasRelatedWork W2953350888 @default.
- W3003641150 hasRelatedWork W2963419873 @default.
- W3003641150 hasRelatedWork W2991647339 @default.
- W3003641150 hasRelatedWork W3001293761 @default.
- W3003641150 hasRelatedWork W3007623510 @default.
- W3003641150 hasRelatedWork W3010795806 @default.
- W3003641150 hasRelatedWork W3090445473 @default.
- W3003641150 hasRelatedWork W3127909800 @default.
- W3003641150 hasRelatedWork W3129240663 @default.
- W3003641150 hasRelatedWork W3143820543 @default.
- W3003641150 hasRelatedWork W3177049179 @default.
- W3003641150 hasRelatedWork W3207597287 @default.
- W3003641150 hasRelatedWork W3213671586 @default.
- W3003641150 hasRelatedWork W344254576 @default.
- W3003641150 hasRelatedWork W3098251352 @default.
- W3003641150 isParatext "false" @default.
- W3003641150 isRetracted "false" @default.
- W3003641150 magId "3003641150" @default.
- W3003641150 workType "article" @default.