Matches in SemOpenAlex for { <https://semopenalex.org/work/W2044296771> ?p ?o ?g. }
- W2044296771 endingPage "260" @default.
- W2044296771 startingPage "251" @default.
- W2044296771 abstract "This paper investigates a general framework to discover categories of unlabeled scene images according to their appearances (i.e., textures and structures). We jointly solve the two coupled tasks in an unsupervised manner: 1) classifying images without predetermining the number of categories and 2) pursuing generative model for each category. In our method, each image is represented by two types of image descriptors that are effective to capture image appearances from different aspects. By treating each image as a graph vertex, we build up a graph and pose the image categorization as a graph partition process. Specifically, a partitioned subgraph can be regarded as a category of scenes and we define the probabilistic model of graph partition by accumulating the generative models of all separated categories. For efficient inference with the graph, we employ a stochastic cluster sampling algorithm, which is designed based on the Metropolis-Hasting mechanism. During the iterations of inference, the model of each category is analytically updated by a generative learning algorithm. In the experiments, our approach is validated on several challenging databases, and it outperforms other popular state-of-the-art methods. The implementation details and empirical analysis are presented as well." @default.
- W2044296771 created "2016-06-24" @default.
- W2044296771 creator A5003608795 @default.
- W2044296771 creator A5005660495 @default.
- W2044296771 creator A5058965019 @default.
- W2044296771 date "2015-02-01" @default.
- W2044296771 modified "2023-09-25" @default.
- W2044296771 title "Adaptive Scene Category Discovery With Generative Learning and Compositional Sampling" @default.
- W2044296771 cites W1566135517 @default.
- W2044296771 cites W1979936637 @default.
- W2044296771 cites W1984797383 @default.
- W2044296771 cites W1984850228 @default.
- W2044296771 cites W1987835821 @default.
- W2044296771 cites W1994205671 @default.
- W2044296771 cites W1996343625 @default.
- W2044296771 cites W2004284939 @default.
- W2044296771 cites W2020636921 @default.
- W2044296771 cites W2031095833 @default.
- W2044296771 cites W2039051707 @default.
- W2044296771 cites W2041306752 @default.
- W2044296771 cites W2066066981 @default.
- W2044296771 cites W2079930597 @default.
- W2044296771 cites W2102772283 @default.
- W2044296771 cites W2103215849 @default.
- W2044296771 cites W2103658758 @default.
- W2044296771 cites W2107034620 @default.
- W2044296771 cites W2109866462 @default.
- W2044296771 cites W2118527002 @default.
- W2044296771 cites W2130481596 @default.
- W2044296771 cites W2134636339 @default.
- W2044296771 cites W2145291599 @default.
- W2044296771 cites W2151103935 @default.
- W2044296771 cites W2151147209 @default.
- W2044296771 cites W2156890308 @default.
- W2044296771 cites W2160842254 @default.
- W2044296771 cites W2161969291 @default.
- W2044296771 cites W2162915993 @default.
- W2044296771 cites W2163175835 @default.
- W2044296771 cites W2165232124 @default.
- W2044296771 cites W2171323859 @default.
- W2044296771 cites W2172196609 @default.
- W2044296771 cites W2177274842 @default.
- W2044296771 cites W2376316332 @default.
- W2044296771 cites W2548197316 @default.
- W2044296771 doi "https://doi.org/10.1109/tcsvt.2014.2313897" @default.
- W2044296771 hasPublicationYear "2015" @default.
- W2044296771 type Work @default.
- W2044296771 sameAs 2044296771 @default.
- W2044296771 citedByCount "19" @default.
- W2044296771 countsByYear W20442967712015 @default.
- W2044296771 countsByYear W20442967712016 @default.
- W2044296771 countsByYear W20442967712017 @default.
- W2044296771 countsByYear W20442967712018 @default.
- W2044296771 countsByYear W20442967712019 @default.
- W2044296771 crossrefType "journal-article" @default.
- W2044296771 hasAuthorship W2044296771A5003608795 @default.
- W2044296771 hasAuthorship W2044296771A5005660495 @default.
- W2044296771 hasAuthorship W2044296771A5058965019 @default.
- W2044296771 hasBestOaLocation W20442967712 @default.
- W2044296771 hasConcept C115961682 @default.
- W2044296771 hasConcept C119857082 @default.
- W2044296771 hasConcept C132525143 @default.
- W2044296771 hasConcept C153180895 @default.
- W2044296771 hasConcept C154945302 @default.
- W2044296771 hasConcept C167966045 @default.
- W2044296771 hasConcept C2776214188 @default.
- W2044296771 hasConcept C39890363 @default.
- W2044296771 hasConcept C41008148 @default.
- W2044296771 hasConcept C49937458 @default.
- W2044296771 hasConcept C80444323 @default.
- W2044296771 hasConcept C94124525 @default.
- W2044296771 hasConceptScore W2044296771C115961682 @default.
- W2044296771 hasConceptScore W2044296771C119857082 @default.
- W2044296771 hasConceptScore W2044296771C132525143 @default.
- W2044296771 hasConceptScore W2044296771C153180895 @default.
- W2044296771 hasConceptScore W2044296771C154945302 @default.
- W2044296771 hasConceptScore W2044296771C167966045 @default.
- W2044296771 hasConceptScore W2044296771C2776214188 @default.
- W2044296771 hasConceptScore W2044296771C39890363 @default.
- W2044296771 hasConceptScore W2044296771C41008148 @default.
- W2044296771 hasConceptScore W2044296771C49937458 @default.
- W2044296771 hasConceptScore W2044296771C80444323 @default.
- W2044296771 hasConceptScore W2044296771C94124525 @default.
- W2044296771 hasFunder F4320321921 @default.
- W2044296771 hasFunder F4320335787 @default.
- W2044296771 hasIssue "2" @default.
- W2044296771 hasLocation W20442967711 @default.
- W2044296771 hasLocation W20442967712 @default.
- W2044296771 hasOpenAccess W2044296771 @default.
- W2044296771 hasPrimaryLocation W20442967711 @default.
- W2044296771 hasRelatedWork W1944687586 @default.
- W2044296771 hasRelatedWork W2104924585 @default.
- W2044296771 hasRelatedWork W2952148308 @default.
- W2044296771 hasRelatedWork W3011817866 @default.
- W2044296771 hasRelatedWork W3042228302 @default.
- W2044296771 hasRelatedWork W3165012362 @default.
- W2044296771 hasRelatedWork W3179209161 @default.
- W2044296771 hasRelatedWork W3198184493 @default.