Matches in SemOpenAlex for { <https://semopenalex.org/work/W2069481966> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W2069481966 endingPage "2657" @default.
- W2069481966 startingPage "2639" @default.
- W2069481966 abstract "Machine learning techniques have been used extensively to build models for the analysis and retrieval of multimedia data. The explosion of multimedia data on the Web poses a great challenge to such techniques not simply because of the sheer data volume, but also because of the heterogeneity of the data. With data from a wide variety of domains, models trained from one domain do not generalize well to other domains, while at the same time it is prohibitively expensive to build new models for each and every domain due to the high cost for labeling training examples. In this paper, we tackle the heterogeneity challenge in large-scale multimedia data using cross-domain model adaptation for better performance and reduced human cost. Specifically, we investigate the problem of adapting supervised classifiers trained from one or more source domains to a new classifier for a target domain that has only limited labeled examples. The foundation of our work is a general framework for function-level classifier adaptation based on the regularized loss minimization principle, which adapts a classifier by directly modifying its decision function. Under this framework, one can derive concrete adaptation algorithms by plugging in any loss and regularization functions, among which we elaborate on adaptive support vector machines (a-SVM). We further extend this framework for multiclassifier adaptation, namely adapting multiple existing classifiers into a classifier for the target domain, in a way that the contributions of these existing classifiers are automatically determined. We evaluate the proposed approaches in cross-domain semantic concept detection based on TRECVID corpora. The results show that our approaches outperform existing (adaptation and nonadaptation) methods in terms of accuracy and/or efficiency, and adaptation from multiple classifiers offers further benefits." @default.
- W2069481966 created "2016-06-24" @default.
- W2069481966 creator A5015547125 @default.
- W2069481966 creator A5062546146 @default.
- W2069481966 creator A5070954480 @default.
- W2069481966 date "2012-09-01" @default.
- W2069481966 modified "2023-10-02" @default.
- W2069481966 title "A Framework for Classifier Adaptation for Large-Scale Multimedia Data" @default.
- W2069481966 cites W131458779 @default.
- W2069481966 cites W1479807131 @default.
- W2069481966 cites W1483816357 @default.
- W2069481966 cites W1515450954 @default.
- W2069481966 cites W1907380269 @default.
- W2069481966 cites W1973971139 @default.
- W2069481966 cites W1978920452 @default.
- W2069481966 cites W1990079212 @default.
- W2069481966 cites W2002686055 @default.
- W2069481966 cites W2009727399 @default.
- W2069481966 cites W2031602671 @default.
- W2069481966 cites W2050549724 @default.
- W2069481966 cites W2056952330 @default.
- W2069481966 cites W2062903088 @default.
- W2069481966 cites W2071731678 @default.
- W2069481966 cites W2073554061 @default.
- W2069481966 cites W2075728230 @default.
- W2069481966 cites W2090923791 @default.
- W2069481966 cites W2095796510 @default.
- W2069481966 cites W2096479579 @default.
- W2069481966 cites W2097579725 @default.
- W2069481966 cites W2099501835 @default.
- W2069481966 cites W2099971677 @default.
- W2069481966 cites W2101498401 @default.
- W2069481966 cites W2108700067 @default.
- W2069481966 cites W2108807072 @default.
- W2069481966 cites W2120887753 @default.
- W2069481966 cites W2121407213 @default.
- W2069481966 cites W2122838776 @default.
- W2069481966 cites W2125337348 @default.
- W2069481966 cites W2126017203 @default.
- W2069481966 cites W2128053425 @default.
- W2069481966 cites W2131193678 @default.
- W2069481966 cites W2132641846 @default.
- W2069481966 cites W2136979193 @default.
- W2069481966 cites W2143854982 @default.
- W2069481966 cites W2160039895 @default.
- W2069481966 cites W2165698076 @default.
- W2069481966 cites W2913340405 @default.
- W2069481966 cites W2917011293 @default.
- W2069481966 cites W2917727538 @default.
- W2069481966 cites W37045202 @default.
- W2069481966 doi "https://doi.org/10.1109/jproc.2012.2204009" @default.
- W2069481966 hasPublicationYear "2012" @default.
- W2069481966 type Work @default.
- W2069481966 sameAs 2069481966 @default.
- W2069481966 citedByCount "2" @default.
- W2069481966 countsByYear W20694819662013 @default.
- W2069481966 countsByYear W20694819662015 @default.
- W2069481966 crossrefType "journal-article" @default.
- W2069481966 hasAuthorship W2069481966A5015547125 @default.
- W2069481966 hasAuthorship W2069481966A5062546146 @default.
- W2069481966 hasAuthorship W2069481966A5070954480 @default.
- W2069481966 hasConcept C119857082 @default.
- W2069481966 hasConcept C12267149 @default.
- W2069481966 hasConcept C124101348 @default.
- W2069481966 hasConcept C154945302 @default.
- W2069481966 hasConcept C2776135515 @default.
- W2069481966 hasConcept C2776145971 @default.
- W2069481966 hasConcept C2776434776 @default.
- W2069481966 hasConcept C41008148 @default.
- W2069481966 hasConcept C95623464 @default.
- W2069481966 hasConceptScore W2069481966C119857082 @default.
- W2069481966 hasConceptScore W2069481966C12267149 @default.
- W2069481966 hasConceptScore W2069481966C124101348 @default.
- W2069481966 hasConceptScore W2069481966C154945302 @default.
- W2069481966 hasConceptScore W2069481966C2776135515 @default.
- W2069481966 hasConceptScore W2069481966C2776145971 @default.
- W2069481966 hasConceptScore W2069481966C2776434776 @default.
- W2069481966 hasConceptScore W2069481966C41008148 @default.
- W2069481966 hasConceptScore W2069481966C95623464 @default.
- W2069481966 hasIssue "9" @default.
- W2069481966 hasLocation W20694819661 @default.
- W2069481966 hasOpenAccess W2069481966 @default.
- W2069481966 hasPrimaryLocation W20694819661 @default.
- W2069481966 hasRelatedWork W2101819884 @default.
- W2069481966 hasRelatedWork W2107999231 @default.
- W2069481966 hasRelatedWork W258707964 @default.
- W2069481966 hasRelatedWork W2937631562 @default.
- W2069481966 hasRelatedWork W2961085424 @default.
- W2069481966 hasRelatedWork W3017503936 @default.
- W2069481966 hasRelatedWork W3136979370 @default.
- W2069481966 hasRelatedWork W3194539120 @default.
- W2069481966 hasRelatedWork W4205958290 @default.
- W2069481966 hasRelatedWork W4361795583 @default.
- W2069481966 hasVolume "100" @default.
- W2069481966 isParatext "false" @default.
- W2069481966 isRetracted "false" @default.
- W2069481966 magId "2069481966" @default.
- W2069481966 workType "article" @default.