Matches in SemOpenAlex for { <https://semopenalex.org/work/W2186571860> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W2186571860 abstract "Feature selection is essential for effective visual recognition. We propose an efficient joint classifier learning and feature selection method that discovers sparse, compact representations of input features from a vast sea of candidates, with an almost unsupervised formulation. Our method requires only the following knowledge, which we call the emph{feature sign}---whether or not a particular feature has on average stronger values over positive samples than over negatives. We show how this can be estimated using as few as a single labeled training sample per class. Then, using these feature signs, we extend an initial supervised learning problem into an (almost) unsupervised clustering formulation that can incorporate new data without requiring ground truth labels. Our method works both as a feature selection mechanism and as a fully competitive classifier. It has important properties, low computational cost and excellent accuracy, especially in difficult cases of very limited training data. We experiment on large-scale recognition in video and show superior speed and performance to established feature selection approaches such as AdaBoost, Lasso, greedy forward-backward selection, and powerful classifiers such as SVM." @default.
- W2186571860 created "2016-06-24" @default.
- W2186571860 creator A5019018961 @default.
- W2186571860 creator A5066107323 @default.
- W2186571860 creator A5085643229 @default.
- W2186571860 creator A5086392501 @default.
- W2186571860 date "2015-12-01" @default.
- W2186571860 modified "2023-09-28" @default.
- W2186571860 title "Labeling the Features Not the Samples: Efficient Video Classification with Minimal Supervision" @default.
- W2186571860 cites W2153635508 @default.
- W2186571860 cites W2161122111 @default.
- W2186571860 cites W3151142710 @default.
- W2186571860 hasPublicationYear "2015" @default.
- W2186571860 type Work @default.
- W2186571860 sameAs 2186571860 @default.
- W2186571860 citedByCount "2" @default.
- W2186571860 countsByYear W21865718602015 @default.
- W2186571860 countsByYear W21865718602017 @default.
- W2186571860 crossrefType "posted-content" @default.
- W2186571860 hasAuthorship W2186571860A5019018961 @default.
- W2186571860 hasAuthorship W2186571860A5066107323 @default.
- W2186571860 hasAuthorship W2186571860A5085643229 @default.
- W2186571860 hasAuthorship W2186571860A5086392501 @default.
- W2186571860 hasConcept C119857082 @default.
- W2186571860 hasConcept C12267149 @default.
- W2186571860 hasConcept C138885662 @default.
- W2186571860 hasConcept C141404830 @default.
- W2186571860 hasConcept C148483581 @default.
- W2186571860 hasConcept C153180895 @default.
- W2186571860 hasConcept C154945302 @default.
- W2186571860 hasConcept C2776401178 @default.
- W2186571860 hasConcept C41008148 @default.
- W2186571860 hasConcept C41895202 @default.
- W2186571860 hasConcept C73555534 @default.
- W2186571860 hasConcept C83665646 @default.
- W2186571860 hasConcept C95623464 @default.
- W2186571860 hasConceptScore W2186571860C119857082 @default.
- W2186571860 hasConceptScore W2186571860C12267149 @default.
- W2186571860 hasConceptScore W2186571860C138885662 @default.
- W2186571860 hasConceptScore W2186571860C141404830 @default.
- W2186571860 hasConceptScore W2186571860C148483581 @default.
- W2186571860 hasConceptScore W2186571860C153180895 @default.
- W2186571860 hasConceptScore W2186571860C154945302 @default.
- W2186571860 hasConceptScore W2186571860C2776401178 @default.
- W2186571860 hasConceptScore W2186571860C41008148 @default.
- W2186571860 hasConceptScore W2186571860C41895202 @default.
- W2186571860 hasConceptScore W2186571860C73555534 @default.
- W2186571860 hasConceptScore W2186571860C83665646 @default.
- W2186571860 hasConceptScore W2186571860C95623464 @default.
- W2186571860 hasOpenAccess W2186571860 @default.
- W2186571860 hasRelatedWork W1134929056 @default.
- W2186571860 hasRelatedWork W1572104567 @default.
- W2186571860 hasRelatedWork W1972056194 @default.
- W2186571860 hasRelatedWork W1973054923 @default.
- W2186571860 hasRelatedWork W2030470432 @default.
- W2186571860 hasRelatedWork W2040861334 @default.
- W2186571860 hasRelatedWork W2050831067 @default.
- W2186571860 hasRelatedWork W2124426131 @default.
- W2186571860 hasRelatedWork W2497285991 @default.
- W2186571860 hasRelatedWork W2519625522 @default.
- W2186571860 hasRelatedWork W2587813419 @default.
- W2186571860 hasRelatedWork W2808585612 @default.
- W2186571860 hasRelatedWork W2963040580 @default.
- W2186571860 hasRelatedWork W3174921665 @default.
- W2186571860 hasRelatedWork W3191257857 @default.
- W2186571860 hasRelatedWork W3213280554 @default.
- W2186571860 hasRelatedWork W77734418 @default.
- W2186571860 hasRelatedWork W1531652497 @default.
- W2186571860 hasRelatedWork W2247265604 @default.
- W2186571860 hasRelatedWork W2741543704 @default.
- W2186571860 isParatext "false" @default.
- W2186571860 isRetracted "false" @default.
- W2186571860 magId "2186571860" @default.
- W2186571860 workType "article" @default.