Matches in SemOpenAlex for { <https://semopenalex.org/work/W2178711753> ?p ?o ?g. }
- W2178711753 abstract "Deep Models, such as Convolutional Neural Networks (CNNs), are omnipresent in computer vision, as well as, structured models, such as Conditional Random Fields (CRFs). Combining them brings many advantages, foremost the ability to in-cooperate prior knowledge into CNNs, e.g. by explicitly modelling the dependencies between output variables. In this work we present a CRF model were unary factors are dependent on a CNN. Our main contribution is an efficient and scalable, maximum likelihood-based, learning procedure to infer all model parameters jointly. Previous work either concentrated on piecewise-training, or maximum likelihood learning of restricted model families, such as Gaussian CRFs or CRFs with a few variables only. In contrast, we are the first to perform maximum likelihood learning for large-sized factor graphs with non-parametric potentials. We have applied our model to the task of semantic labeling of body parts in depth images. We show that it is superior to selected competing models and learning strategies. Furthermore, we empirically observe that our model can capture shape and context information of relating body parts." @default.
- W2178711753 created "2016-06-24" @default.
- W2178711753 creator A5011803610 @default.
- W2178711753 creator A5034290170 @default.
- W2178711753 creator A5042899882 @default.
- W2178711753 creator A5057948189 @default.
- W2178711753 creator A5062314052 @default.
- W2178711753 creator A5075325937 @default.
- W2178711753 creator A5077676287 @default.
- W2178711753 date "2015-11-16" @default.
- W2178711753 modified "2023-10-16" @default.
- W2178711753 title "Efficient Likelihood Learning of a Generic CNN-CRF Model for Semantic Segmentation." @default.
- W2178711753 cites W1569892065 @default.
- W2178711753 cites W1686810756 @default.
- W2178711753 cites W2020999234 @default.
- W2178711753 cites W2022508996 @default.
- W2178711753 cites W2048971218 @default.
- W2178711753 cites W2064076655 @default.
- W2178711753 cites W2070797946 @default.
- W2178711753 cites W2081136789 @default.
- W2178711753 cites W2102492119 @default.
- W2178711753 cites W2110361616 @default.
- W2178711753 cites W2111077768 @default.
- W2178711753 cites W2116064496 @default.
- W2178711753 cites W2116825644 @default.
- W2178711753 cites W2120340025 @default.
- W2178711753 cites W2137592810 @default.
- W2178711753 cites W2144794286 @default.
- W2178711753 cites W2147880316 @default.
- W2178711753 cites W2161236525 @default.
- W2178711753 cites W2164918853 @default.
- W2178711753 cites W2167219413 @default.
- W2178711753 cites W2186629860 @default.
- W2178711753 cites W2928160594 @default.
- W2178711753 cites W2949588583 @default.
- W2178711753 cites W2950094539 @default.
- W2178711753 cites W2952422028 @default.
- W2178711753 cites W2952632681 @default.
- W2178711753 cites W2964288706 @default.
- W2178711753 cites W986585644 @default.
- W2178711753 hasPublicationYear "2015" @default.
- W2178711753 type Work @default.
- W2178711753 sameAs 2178711753 @default.
- W2178711753 citedByCount "5" @default.
- W2178711753 countsByYear W21787117532016 @default.
- W2178711753 countsByYear W21787117532017 @default.
- W2178711753 countsByYear W21787117532020 @default.
- W2178711753 crossrefType "posted-content" @default.
- W2178711753 hasAuthorship W2178711753A5011803610 @default.
- W2178711753 hasAuthorship W2178711753A5034290170 @default.
- W2178711753 hasAuthorship W2178711753A5042899882 @default.
- W2178711753 hasAuthorship W2178711753A5057948189 @default.
- W2178711753 hasAuthorship W2178711753A5062314052 @default.
- W2178711753 hasAuthorship W2178711753A5075325937 @default.
- W2178711753 hasAuthorship W2178711753A5077676287 @default.
- W2178711753 hasConcept C107673813 @default.
- W2178711753 hasConcept C108583219 @default.
- W2178711753 hasConcept C114614502 @default.
- W2178711753 hasConcept C119857082 @default.
- W2178711753 hasConcept C151730666 @default.
- W2178711753 hasConcept C152565575 @default.
- W2178711753 hasConcept C153180895 @default.
- W2178711753 hasConcept C154945302 @default.
- W2178711753 hasConcept C2775953691 @default.
- W2178711753 hasConcept C2779343474 @default.
- W2178711753 hasConcept C33923547 @default.
- W2178711753 hasConcept C41008148 @default.
- W2178711753 hasConcept C57830394 @default.
- W2178711753 hasConcept C78023250 @default.
- W2178711753 hasConcept C81363708 @default.
- W2178711753 hasConcept C86803240 @default.
- W2178711753 hasConcept C89600930 @default.
- W2178711753 hasConceptScore W2178711753C107673813 @default.
- W2178711753 hasConceptScore W2178711753C108583219 @default.
- W2178711753 hasConceptScore W2178711753C114614502 @default.
- W2178711753 hasConceptScore W2178711753C119857082 @default.
- W2178711753 hasConceptScore W2178711753C151730666 @default.
- W2178711753 hasConceptScore W2178711753C152565575 @default.
- W2178711753 hasConceptScore W2178711753C153180895 @default.
- W2178711753 hasConceptScore W2178711753C154945302 @default.
- W2178711753 hasConceptScore W2178711753C2775953691 @default.
- W2178711753 hasConceptScore W2178711753C2779343474 @default.
- W2178711753 hasConceptScore W2178711753C33923547 @default.
- W2178711753 hasConceptScore W2178711753C41008148 @default.
- W2178711753 hasConceptScore W2178711753C57830394 @default.
- W2178711753 hasConceptScore W2178711753C78023250 @default.
- W2178711753 hasConceptScore W2178711753C81363708 @default.
- W2178711753 hasConceptScore W2178711753C86803240 @default.
- W2178711753 hasConceptScore W2178711753C89600930 @default.
- W2178711753 hasLocation W21787117531 @default.
- W2178711753 hasOpenAccess W2178711753 @default.
- W2178711753 hasPrimaryLocation W21787117531 @default.
- W2178711753 hasRelatedWork W13840495 @default.
- W2178711753 hasRelatedWork W1632600346 @default.
- W2178711753 hasRelatedWork W1653341947 @default.
- W2178711753 hasRelatedWork W1988425574 @default.
- W2178711753 hasRelatedWork W1992699959 @default.
- W2178711753 hasRelatedWork W2029305120 @default.
- W2178711753 hasRelatedWork W2035593643 @default.
- W2178711753 hasRelatedWork W2096046065 @default.