Matches in SemOpenAlex for { <https://semopenalex.org/work/W2099691725> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W2099691725 endingPage "106" @default.
- W2099691725 startingPage "94" @default.
- W2099691725 abstract "It is attractive to formulate problems in computer vision and related fields in term of probabilistic estimation where the probability models are defined over graphs, such as grammars. The graphical structures, and the state variables defined over them, give a rich knowledge representation which can describe the complex structures of objects and images. The probability distributions defined over the graphs capture the statistical variability of these structures. These probability models can be learnt from training data with limited amounts of supervision. But learning these models suffers from the difficulty of evaluating the normalization constant, or partition function, of the probability distributions which can be extremely computationally demanding. This paper shows that by placing bounds on the normalization constant we can obtain computationally tractable approximations. Surprisingly, for certain choices of loss functions, we obtain many of the standard max-margin criteria used in support vector machines (SVMs) and hence we reduce the learning to standard machine learning methods. We show that many machine learning methods can be obtained in this way as approximations to probabilistic methods including multi-class max-margin, ordinal regression, max-margin Markov networks and parsers, multiple-instance learning, and latent SVM. We illustrate this work by computer vision applications including image labeling, object detection and localization, and motion estimation. We speculate that better results can be obtained by using better bounds and approximations." @default.
- W2099691725 created "2016-06-24" @default.
- W2099691725 creator A5015970030 @default.
- W2099691725 creator A5086706224 @default.
- W2099691725 date "2012-02-19" @default.
- W2099691725 modified "2023-09-27" @default.
- W2099691725 title "Probabilistic models of vision and max-margin methods" @default.
- W2099691725 cites W1504372951 @default.
- W2099691725 cites W1528789833 @default.
- W2099691725 cites W1540007258 @default.
- W2099691725 cites W1965080940 @default.
- W2099691725 cites W2008652694 @default.
- W2099691725 cites W2034869517 @default.
- W2099691725 cites W2035720976 @default.
- W2099691725 cites W2045798786 @default.
- W2099691725 cites W2074398519 @default.
- W2099691725 cites W2095844239 @default.
- W2099691725 cites W2107452121 @default.
- W2099691725 cites W2120419212 @default.
- W2099691725 cites W2136922672 @default.
- W2099691725 cites W2138639557 @default.
- W2099691725 cites W2143299724 @default.
- W2099691725 cites W2143386126 @default.
- W2099691725 cites W2147196093 @default.
- W2099691725 cites W2156909104 @default.
- W2099691725 cites W2162188269 @default.
- W2099691725 cites W2168772685 @default.
- W2099691725 cites W2169415915 @default.
- W2099691725 cites W2172803778 @default.
- W2099691725 cites W3169507310 @default.
- W2099691725 cites W4205969993 @default.
- W2099691725 cites W4211064163 @default.
- W2099691725 cites W4211120398 @default.
- W2099691725 cites W4214628345 @default.
- W2099691725 cites W4235011515 @default.
- W2099691725 cites W4247942956 @default.
- W2099691725 cites W4254569673 @default.
- W2099691725 doi "https://doi.org/10.1007/s11460-012-0170-6" @default.
- W2099691725 hasPublicationYear "2012" @default.
- W2099691725 type Work @default.
- W2099691725 sameAs 2099691725 @default.
- W2099691725 citedByCount "1" @default.
- W2099691725 countsByYear W20996917252020 @default.
- W2099691725 crossrefType "journal-article" @default.
- W2099691725 hasAuthorship W2099691725A5015970030 @default.
- W2099691725 hasAuthorship W2099691725A5086706224 @default.
- W2099691725 hasBestOaLocation W20996917252 @default.
- W2099691725 hasConcept C119857082 @default.
- W2099691725 hasConcept C154945302 @default.
- W2099691725 hasConcept C41008148 @default.
- W2099691725 hasConcept C49937458 @default.
- W2099691725 hasConcept C774472 @default.
- W2099691725 hasConceptScore W2099691725C119857082 @default.
- W2099691725 hasConceptScore W2099691725C154945302 @default.
- W2099691725 hasConceptScore W2099691725C41008148 @default.
- W2099691725 hasConceptScore W2099691725C49937458 @default.
- W2099691725 hasConceptScore W2099691725C774472 @default.
- W2099691725 hasIssue "1" @default.
- W2099691725 hasLocation W20996917251 @default.
- W2099691725 hasLocation W20996917252 @default.
- W2099691725 hasOpenAccess W2099691725 @default.
- W2099691725 hasPrimaryLocation W20996917251 @default.
- W2099691725 hasRelatedWork W1501302278 @default.
- W2099691725 hasRelatedWork W1510154836 @default.
- W2099691725 hasRelatedWork W1575659177 @default.
- W2099691725 hasRelatedWork W1603968847 @default.
- W2099691725 hasRelatedWork W1963654597 @default.
- W2099691725 hasRelatedWork W2346076952 @default.
- W2099691725 hasRelatedWork W2909011011 @default.
- W2099691725 hasRelatedWork W3107474891 @default.
- W2099691725 hasRelatedWork W3175603317 @default.
- W2099691725 hasRelatedWork W4290792893 @default.
- W2099691725 hasVolume "7" @default.
- W2099691725 isParatext "false" @default.
- W2099691725 isRetracted "false" @default.
- W2099691725 magId "2099691725" @default.
- W2099691725 workType "article" @default.