Matches in SemOpenAlex for { <https://semopenalex.org/work/W2949419314> ?p ?o ?g. }
- W2949419314 abstract "People typically learn through exposure to visual concepts associated with linguistic descriptions. For instance, teaching visual object categories to children is often accompanied by descriptions in text or speech. In a machine learning context, these observations motivates us to ask whether this learning process could be computationally modeled to learn visual classifiers. More specifically, the main question of this work is how to utilize purely textual description of visual classes with no training images, to learn explicit visual classifiers for them. We propose and investigate two baseline formulations, based on regression and domain transfer, that predict a linear classifier. Then, we propose a new constrained optimization formulation that combines a regression function and a knowledge transfer function with additional constraints to predict the parameters of a linear classifier. We also propose a generic kernelized models where a kernel classifier is predicted in the form defined by the representer theorem. The kernelized models allow defining and utilizing any two RKHS (Reproducing Kernel Hilbert Space) kernel functions in the visual space and text space, respectively. We finally propose a kernel function between unstructured text descriptions that builds on distributional semantics, which shows an advantage in our setting and could be useful for other applications. We applied all the studied models to predict visual classifiers on two fine-grained and challenging categorization datasets (CU Birds and Flower Datasets), and the results indicate successful predictions of our final model over several baselines that we designed." @default.
- W2949419314 created "2019-06-27" @default.
- W2949419314 creator A5039640321 @default.
- W2949419314 creator A5084006441 @default.
- W2949419314 creator A5085089542 @default.
- W2949419314 date "2015-12-31" @default.
- W2949419314 modified "2023-10-01" @default.
- W2949419314 title "Write a Classifier: Predicting Visual Classifiers from Unstructured Text" @default.
- W2949419314 cites W1533208079 @default.
- W2949419314 cites W1606612563 @default.
- W2949419314 cites W16591383 @default.
- W2949419314 cites W1797268635 @default.
- W2949419314 cites W1846799578 @default.
- W2949419314 cites W1858383477 @default.
- W2949419314 cites W1865725639 @default.
- W2949419314 cites W1895577753 @default.
- W2949419314 cites W1897761818 @default.
- W2949419314 cites W1905882502 @default.
- W2949419314 cites W1978394996 @default.
- W2949419314 cites W1978920452 @default.
- W2949419314 cites W2019524107 @default.
- W2949419314 cites W2047028564 @default.
- W2949419314 cites W2080171500 @default.
- W2949419314 cites W2081580037 @default.
- W2949419314 cites W2084435358 @default.
- W2949419314 cites W2099501835 @default.
- W2949419314 cites W2103444992 @default.
- W2949419314 cites W2109743529 @default.
- W2949419314 cites W2116339064 @default.
- W2949419314 cites W2122528955 @default.
- W2949419314 cites W2123024445 @default.
- W2949419314 cites W2133774033 @default.
- W2949419314 cites W2144656844 @default.
- W2949419314 cites W2145607950 @default.
- W2949419314 cites W2152984213 @default.
- W2949419314 cites W2153579005 @default.
- W2949419314 cites W2155541015 @default.
- W2949419314 cites W2155853132 @default.
- W2949419314 cites W2157331557 @default.
- W2949419314 cites W2163207321 @default.
- W2949419314 cites W2169738563 @default.
- W2949419314 cites W2950094539 @default.
- W2949419314 cites W2950178297 @default.
- W2949419314 cites W2950276680 @default.
- W2949419314 cites W2950577311 @default.
- W2949419314 cites W2962706528 @default.
- W2949419314 cites W2962835968 @default.
- W2949419314 cites W2963899908 @default.
- W2949419314 cites W652269744 @default.
- W2949419314 cites W93016980 @default.
- W2949419314 hasPublicationYear "2015" @default.
- W2949419314 type Work @default.
- W2949419314 sameAs 2949419314 @default.
- W2949419314 citedByCount "3" @default.
- W2949419314 countsByYear W29494193142017 @default.
- W2949419314 countsByYear W29494193142019 @default.
- W2949419314 countsByYear W29494193142021 @default.
- W2949419314 crossrefType "posted-content" @default.
- W2949419314 hasAuthorship W2949419314A5039640321 @default.
- W2949419314 hasAuthorship W2949419314A5084006441 @default.
- W2949419314 hasAuthorship W2949419314A5085089542 @default.
- W2949419314 hasConcept C114614502 @default.
- W2949419314 hasConcept C119857082 @default.
- W2949419314 hasConcept C122280245 @default.
- W2949419314 hasConcept C12267149 @default.
- W2949419314 hasConcept C134306372 @default.
- W2949419314 hasConcept C153180895 @default.
- W2949419314 hasConcept C154945302 @default.
- W2949419314 hasConcept C172623408 @default.
- W2949419314 hasConcept C204321447 @default.
- W2949419314 hasConcept C33923547 @default.
- W2949419314 hasConcept C41008148 @default.
- W2949419314 hasConcept C62799726 @default.
- W2949419314 hasConcept C74193536 @default.
- W2949419314 hasConcept C75866337 @default.
- W2949419314 hasConcept C80884492 @default.
- W2949419314 hasConcept C94124525 @default.
- W2949419314 hasConcept C95623464 @default.
- W2949419314 hasConceptScore W2949419314C114614502 @default.
- W2949419314 hasConceptScore W2949419314C119857082 @default.
- W2949419314 hasConceptScore W2949419314C122280245 @default.
- W2949419314 hasConceptScore W2949419314C12267149 @default.
- W2949419314 hasConceptScore W2949419314C134306372 @default.
- W2949419314 hasConceptScore W2949419314C153180895 @default.
- W2949419314 hasConceptScore W2949419314C154945302 @default.
- W2949419314 hasConceptScore W2949419314C172623408 @default.
- W2949419314 hasConceptScore W2949419314C204321447 @default.
- W2949419314 hasConceptScore W2949419314C33923547 @default.
- W2949419314 hasConceptScore W2949419314C41008148 @default.
- W2949419314 hasConceptScore W2949419314C62799726 @default.
- W2949419314 hasConceptScore W2949419314C74193536 @default.
- W2949419314 hasConceptScore W2949419314C75866337 @default.
- W2949419314 hasConceptScore W2949419314C80884492 @default.
- W2949419314 hasConceptScore W2949419314C94124525 @default.
- W2949419314 hasConceptScore W2949419314C95623464 @default.
- W2949419314 hasLocation W29494193141 @default.
- W2949419314 hasOpenAccess W2949419314 @default.
- W2949419314 hasPrimaryLocation W29494193141 @default.
- W2949419314 hasRelatedWork W2124678650 @default.
- W2949419314 hasRelatedWork W2128604765 @default.