Matches in SemOpenAlex for { <https://semopenalex.org/work/W2022117997> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W2022117997 abstract "This paper aims at learning discriminative visual words for object localization. These visual words are different from those learned from the generic object recognition which usually contain the negative visual words located on the background. For the purpose of object localization, the approach requires that the positive discriminative visual words mostly lie in the foreground object and the negative ones lie in the background. We firstly rank the visual words by the following three methods: the SVM classifier, the foreground likelihood ratio and the mutual information. Then, we integrate the three ranking results in an optimal combinational way and select the discriminative visual words by maximizing the object hit rate. Moreover, a coarse-to-fine detection framework to locate the object is designed. In the first stage, a branch-and-bound scheme combined with the discriminative visual words is implemented to find candidate object regions. In the second stage, a sliding window classifier is used to find the object location. The experimental results demonstrate that the approach is effective and efficient, and superior to Efficient Subwindow Search scheme." @default.
- W2022117997 created "2016-06-24" @default.
- W2022117997 creator A5030552716 @default.
- W2022117997 creator A5061638835 @default.
- W2022117997 creator A5064548129 @default.
- W2022117997 creator A5076485255 @default.
- W2022117997 date "2012-07-01" @default.
- W2022117997 modified "2023-10-05" @default.
- W2022117997 title "Object localization based on discriminative visual words" @default.
- W2022117997 cites W1880262756 @default.
- W2022117997 cites W2012330712 @default.
- W2022117997 cites W2105303837 @default.
- W2022117997 cites W2106255337 @default.
- W2022117997 cites W2110099550 @default.
- W2022117997 cites W2112301665 @default.
- W2022117997 cites W2113201641 @default.
- W2022117997 cites W2118743891 @default.
- W2022117997 cites W2123579313 @default.
- W2022117997 cites W2124386111 @default.
- W2022117997 cites W2140169211 @default.
- W2022117997 cites W2154422044 @default.
- W2022117997 cites W2161837491 @default.
- W2022117997 cites W2161969291 @default.
- W2022117997 cites W2162708558 @default.
- W2022117997 cites W2163352848 @default.
- W2022117997 cites W2164877691 @default.
- W2022117997 cites W3097096317 @default.
- W2022117997 cites W3146079624 @default.
- W2022117997 cites W66095925 @default.
- W2022117997 doi "https://doi.org/10.1109/icmlc.2012.6359510" @default.
- W2022117997 hasPublicationYear "2012" @default.
- W2022117997 type Work @default.
- W2022117997 sameAs 2022117997 @default.
- W2022117997 citedByCount "0" @default.
- W2022117997 crossrefType "proceedings-article" @default.
- W2022117997 hasAuthorship W2022117997A5030552716 @default.
- W2022117997 hasAuthorship W2022117997A5061638835 @default.
- W2022117997 hasAuthorship W2022117997A5064548129 @default.
- W2022117997 hasAuthorship W2022117997A5076485255 @default.
- W2022117997 hasConcept C153180895 @default.
- W2022117997 hasConcept C154945302 @default.
- W2022117997 hasConcept C2781238097 @default.
- W2022117997 hasConcept C31972630 @default.
- W2022117997 hasConcept C41008148 @default.
- W2022117997 hasConcept C97931131 @default.
- W2022117997 hasConceptScore W2022117997C153180895 @default.
- W2022117997 hasConceptScore W2022117997C154945302 @default.
- W2022117997 hasConceptScore W2022117997C2781238097 @default.
- W2022117997 hasConceptScore W2022117997C31972630 @default.
- W2022117997 hasConceptScore W2022117997C41008148 @default.
- W2022117997 hasConceptScore W2022117997C97931131 @default.
- W2022117997 hasLocation W20221179971 @default.
- W2022117997 hasOpenAccess W2022117997 @default.
- W2022117997 hasPrimaryLocation W20221179971 @default.
- W2022117997 hasRelatedWork W2024160000 @default.
- W2022117997 hasRelatedWork W2061273563 @default.
- W2022117997 hasRelatedWork W2285052147 @default.
- W2022117997 hasRelatedWork W2729514902 @default.
- W2022117997 hasRelatedWork W2743258233 @default.
- W2022117997 hasRelatedWork W2773500201 @default.
- W2022117997 hasRelatedWork W2975200075 @default.
- W2022117997 hasRelatedWork W2998168123 @default.
- W2022117997 hasRelatedWork W4287995534 @default.
- W2022117997 hasRelatedWork W2073139667 @default.
- W2022117997 isParatext "false" @default.
- W2022117997 isRetracted "false" @default.
- W2022117997 magId "2022117997" @default.
- W2022117997 workType "article" @default.