Matches in SemOpenAlex for { <https://semopenalex.org/work/W1968923557> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W1968923557 abstract "Over the past years, Multiple Instance Learning (MIL) has proven to be an effective framework for learning with weakly labeled data. Applications of MIL to object detection, however, were limited to handling the uncertainties of manual annotations. In this paper, we propose a new MIL method for object detection that is capable of handling the noisier automatically obtained annotations. Our approach consists in first obtaining confidence estimates over the label space and, second, incorporating these estimates within a new Boosting procedure. We demonstrate the efficiency of our procedure on two detection tasks, namely, horse detection and pedestrian detection, where the training data is primarily annotated by a coarse area of interest detector. We show dramatic improvements over existing MIL methods. In both cases, we demonstrate that an efficient appearance model can be learned using our approach." @default.
- W1968923557 created "2016-06-24" @default.
- W1968923557 creator A5075906727 @default.
- W1968923557 creator A5084446948 @default.
- W1968923557 date "2014-06-01" @default.
- W1968923557 modified "2023-10-12" @default.
- W1968923557 title "Confidence-Rated Multiple Instance Boosting for Object Detection" @default.
- W1968923557 cites W1560331282 @default.
- W1968923557 cites W1678356000 @default.
- W1968923557 cites W2031489346 @default.
- W1968923557 cites W2032194607 @default.
- W1968923557 cites W2066624635 @default.
- W1968923557 cites W2106848050 @default.
- W1968923557 cites W2145169631 @default.
- W1968923557 cites W2161969291 @default.
- W1968923557 cites W2168356304 @default.
- W1968923557 doi "https://doi.org/10.1109/cvpr.2014.312" @default.
- W1968923557 hasPublicationYear "2014" @default.
- W1968923557 type Work @default.
- W1968923557 sameAs 1968923557 @default.
- W1968923557 citedByCount "24" @default.
- W1968923557 countsByYear W19689235572014 @default.
- W1968923557 countsByYear W19689235572015 @default.
- W1968923557 countsByYear W19689235572016 @default.
- W1968923557 countsByYear W19689235572017 @default.
- W1968923557 countsByYear W19689235572018 @default.
- W1968923557 countsByYear W19689235572020 @default.
- W1968923557 countsByYear W19689235572021 @default.
- W1968923557 countsByYear W19689235572022 @default.
- W1968923557 countsByYear W19689235572023 @default.
- W1968923557 crossrefType "proceedings-article" @default.
- W1968923557 hasAuthorship W1968923557A5075906727 @default.
- W1968923557 hasAuthorship W1968923557A5084446948 @default.
- W1968923557 hasConcept C119857082 @default.
- W1968923557 hasConcept C124101348 @default.
- W1968923557 hasConcept C127413603 @default.
- W1968923557 hasConcept C153180895 @default.
- W1968923557 hasConcept C154945302 @default.
- W1968923557 hasConcept C22212356 @default.
- W1968923557 hasConcept C2776151529 @default.
- W1968923557 hasConcept C2777113093 @default.
- W1968923557 hasConcept C2780156472 @default.
- W1968923557 hasConcept C2781238097 @default.
- W1968923557 hasConcept C31972630 @default.
- W1968923557 hasConcept C41008148 @default.
- W1968923557 hasConcept C46686674 @default.
- W1968923557 hasConcept C76155785 @default.
- W1968923557 hasConcept C94915269 @default.
- W1968923557 hasConceptScore W1968923557C119857082 @default.
- W1968923557 hasConceptScore W1968923557C124101348 @default.
- W1968923557 hasConceptScore W1968923557C127413603 @default.
- W1968923557 hasConceptScore W1968923557C153180895 @default.
- W1968923557 hasConceptScore W1968923557C154945302 @default.
- W1968923557 hasConceptScore W1968923557C22212356 @default.
- W1968923557 hasConceptScore W1968923557C2776151529 @default.
- W1968923557 hasConceptScore W1968923557C2777113093 @default.
- W1968923557 hasConceptScore W1968923557C2780156472 @default.
- W1968923557 hasConceptScore W1968923557C2781238097 @default.
- W1968923557 hasConceptScore W1968923557C31972630 @default.
- W1968923557 hasConceptScore W1968923557C41008148 @default.
- W1968923557 hasConceptScore W1968923557C46686674 @default.
- W1968923557 hasConceptScore W1968923557C76155785 @default.
- W1968923557 hasConceptScore W1968923557C94915269 @default.
- W1968923557 hasLocation W19689235571 @default.
- W1968923557 hasOpenAccess W1968923557 @default.
- W1968923557 hasPrimaryLocation W19689235571 @default.
- W1968923557 hasRelatedWork W2100052226 @default.
- W1968923557 hasRelatedWork W2101531944 @default.
- W1968923557 hasRelatedWork W2802018156 @default.
- W1968923557 hasRelatedWork W2914343065 @default.
- W1968923557 hasRelatedWork W2922437833 @default.
- W1968923557 hasRelatedWork W2933098581 @default.
- W1968923557 hasRelatedWork W2963610131 @default.
- W1968923557 hasRelatedWork W4298149443 @default.
- W1968923557 hasRelatedWork W4312696271 @default.
- W1968923557 hasRelatedWork W4313315626 @default.
- W1968923557 isParatext "false" @default.
- W1968923557 isRetracted "false" @default.
- W1968923557 magId "1968923557" @default.
- W1968923557 workType "article" @default.