SemOpenAlex |

SemOpenAlex

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2016016818> ?p ?o ?g. }

Showing items 1 to 100 of ±113 with 100 items per page.

W2016016818 abstract "Object category localization is a challenging problem in computer vision. Standard supervised training requires bounding box annotations of object instances. This time-consuming annotation process is sidestepped in weakly supervised learning. In this case, the supervised information is restricted to binary labels that indicate the absence/presence of object instances in the image, without their locations. We follow a multiple-instance learning approach that iteratively trains the detector and infers the object locations in the positive training images. Our main contribution is a multi-fold multiple instance learning procedure, which prevents training from prematurely locking onto erroneous object locations. This procedure is particularly important when high-dimensional representations, such as the Fisher vectors, are used. We present a detailed experimental evaluation using the PASCAL VOC 2007 dataset. Compared to state-of-the-art weakly supervised detectors, our approach better localizes objects in the training images, which translates into improved detection performance." @default.
W2016016818 created "2016-06-24" @default.
W2016016818 creator A5040312210 @default.
W2016016818 creator A5045217258 @default.
W2016016818 creator A5051499142 @default.
W2016016818 date "2014-06-01" @default.
W2016016818 modified "2023-10-15" @default.
W2016016818 title "Multi-fold MIL Training for Weakly Supervised Object Localization" @default.
W2016016818 cites W1966385142 @default.
W2016016818 cites W1973054923 @default.
W2016016818 cites W1976921161 @default.
W2016016818 cites W2020477327 @default.
W2016016818 cites W2027953712 @default.
W2016016818 cites W2031489346 @default.
W2016016818 cites W2037511607 @default.
W2016016818 cites W2039507552 @default.
W2016016818 cites W2061629163 @default.
W2016016818 cites W2079267072 @default.
W2016016818 cites W2088049833 @default.
W2016016818 cites W2099528205 @default.
W2016016818 cites W2106874006 @default.
W2016016818 cites W2107200795 @default.
W2016016818 cites W2110119381 @default.
W2016016818 cites W2112343299 @default.
W2016016818 cites W2120369594 @default.
W2016016818 cites W2123023145 @default.
W2016016818 cites W2127453602 @default.
W2016016818 cites W2128715914 @default.
W2016016818 cites W2130350952 @default.
W2016016818 cites W2138761194 @default.
W2016016818 cites W2168356304 @default.
W2016016818 cites W4237791300 @default.
W2016016818 doi "https://doi.org/10.1109/cvpr.2014.309" @default.
W2016016818 hasPublicationYear "2014" @default.
W2016016818 type Work @default.
W2016016818 sameAs 2016016818 @default.
W2016016818 citedByCount "214" @default.
W2016016818 countsByYear W20160168182014 @default.
W2016016818 countsByYear W20160168182015 @default.
W2016016818 countsByYear W20160168182016 @default.
W2016016818 countsByYear W20160168182017 @default.
W2016016818 countsByYear W20160168182018 @default.
W2016016818 countsByYear W20160168182019 @default.
W2016016818 countsByYear W20160168182020 @default.
W2016016818 countsByYear W20160168182021 @default.
W2016016818 countsByYear W20160168182022 @default.
W2016016818 countsByYear W20160168182023 @default.
W2016016818 crossrefType "proceedings-article" @default.
W2016016818 hasAuthorship W2016016818A5040312210 @default.
W2016016818 hasAuthorship W2016016818A5045217258 @default.
W2016016818 hasAuthorship W2016016818A5051499142 @default.
W2016016818 hasBestOaLocation W20160168182 @default.
W2016016818 hasConcept C115961682 @default.
W2016016818 hasConcept C119857082 @default.
W2016016818 hasConcept C12267149 @default.
W2016016818 hasConcept C136389625 @default.
W2016016818 hasConcept C147037132 @default.
W2016016818 hasConcept C153180895 @default.
W2016016818 hasConcept C154945302 @default.
W2016016818 hasConcept C199360897 @default.
W2016016818 hasConcept C2776151529 @default.
W2016016818 hasConcept C2776321320 @default.
W2016016818 hasConcept C2781238097 @default.
W2016016818 hasConcept C31972630 @default.
W2016016818 hasConcept C41008148 @default.
W2016016818 hasConcept C50644808 @default.
W2016016818 hasConcept C63584917 @default.
W2016016818 hasConcept C64876066 @default.
W2016016818 hasConcept C66905080 @default.
W2016016818 hasConcept C75608658 @default.
W2016016818 hasConcept C76155785 @default.
W2016016818 hasConcept C94915269 @default.
W2016016818 hasConceptScore W2016016818C115961682 @default.
W2016016818 hasConceptScore W2016016818C119857082 @default.
W2016016818 hasConceptScore W2016016818C12267149 @default.
W2016016818 hasConceptScore W2016016818C136389625 @default.
W2016016818 hasConceptScore W2016016818C147037132 @default.
W2016016818 hasConceptScore W2016016818C153180895 @default.
W2016016818 hasConceptScore W2016016818C154945302 @default.
W2016016818 hasConceptScore W2016016818C199360897 @default.
W2016016818 hasConceptScore W2016016818C2776151529 @default.
W2016016818 hasConceptScore W2016016818C2776321320 @default.
W2016016818 hasConceptScore W2016016818C2781238097 @default.
W2016016818 hasConceptScore W2016016818C31972630 @default.
W2016016818 hasConceptScore W2016016818C41008148 @default.
W2016016818 hasConceptScore W2016016818C50644808 @default.
W2016016818 hasConceptScore W2016016818C63584917 @default.
W2016016818 hasConceptScore W2016016818C64876066 @default.
W2016016818 hasConceptScore W2016016818C66905080 @default.
W2016016818 hasConceptScore W2016016818C75608658 @default.
W2016016818 hasConceptScore W2016016818C76155785 @default.
W2016016818 hasConceptScore W2016016818C94915269 @default.
W2016016818 hasLocation W20160168181 @default.
W2016016818 hasLocation W20160168182 @default.
W2016016818 hasLocation W20160168183 @default.
W2016016818 hasLocation W20160168184 @default.
W2016016818 hasLocation W20160168185 @default.
W2016016818 hasOpenAccess W2016016818 @default.
W2016016818 hasPrimaryLocation W20160168181 @default.
W2016016818 hasRelatedWork W1495267108 @default.