Matches in SemOpenAlex for { <https://semopenalex.org/work/W2014041954> ?p ?o ?g. }
- W2014041954 abstract "In this paper, we investigate the issue of evaluating efficiently a large set of models on an input image in detection and classification tasks. We show that by formulating the visual task as a large matrix multiplication problem, something that is possible for a broad set of modern detectors and classifiers, we are able to dramatically reduce the rate of growth of computation as the number of models increases. The approach, based on a bilinear separation model, combines standard matrix factorization with a task dependent term which ensures that the resulting smaller size problem maintains performance on the original task. Experiments show that we are able to maintain, or even exceed, the level of performance compared to the default approach of using all the models directly, in both detection and classification tasks. This approach is complementary to other efforts in the literature on speeding up computation through GPU implementation, fast matrix operations, or quantization, in that any of these optimizations can be incorporated." @default.
- W2014041954 created "2016-06-24" @default.
- W2014041954 creator A5064761222 @default.
- W2014041954 creator A5075246991 @default.
- W2014041954 date "2015-01-01" @default.
- W2014041954 modified "2023-10-18" @default.
- W2014041954 title "Efficient Model Evaluation with Bilinear Separation Model" @default.
- W2014041954 cites W1481552826 @default.
- W2014041954 cites W1555385401 @default.
- W2014041954 cites W1574719918 @default.
- W2014041954 cites W1737613372 @default.
- W2014041954 cites W1787735662 @default.
- W2014041954 cites W1964590153 @default.
- W2014041954 cites W1966385142 @default.
- W2014041954 cites W1976618413 @default.
- W2014041954 cites W1978491093 @default.
- W2014041954 cites W1989684337 @default.
- W2014041954 cites W2017691720 @default.
- W2014041954 cites W2031489346 @default.
- W2014041954 cites W2036329542 @default.
- W2014041954 cites W2036989445 @default.
- W2014041954 cites W2044313232 @default.
- W2014041954 cites W2045762391 @default.
- W2014041954 cites W2097202741 @default.
- W2014041954 cites W2097366995 @default.
- W2014041954 cites W2102605133 @default.
- W2014041954 cites W2105880865 @default.
- W2014041954 cites W2108598243 @default.
- W2014041954 cites W2121660792 @default.
- W2014041954 cites W2122146326 @default.
- W2014041954 cites W2128154306 @default.
- W2014041954 cites W2153412052 @default.
- W2014041954 cites W2161969291 @default.
- W2014041954 cites W2162064258 @default.
- W2014041954 cites W2168356304 @default.
- W2014041954 cites W2170653751 @default.
- W2014041954 cites W2618530766 @default.
- W2014041954 cites W3097096317 @default.
- W2014041954 cites W82130502 @default.
- W2014041954 doi "https://doi.org/10.1109/wacv.2015.110" @default.
- W2014041954 hasPublicationYear "2015" @default.
- W2014041954 type Work @default.
- W2014041954 sameAs 2014041954 @default.
- W2014041954 citedByCount "1" @default.
- W2014041954 countsByYear W20140419542015 @default.
- W2014041954 crossrefType "proceedings-article" @default.
- W2014041954 hasAuthorship W2014041954A5064761222 @default.
- W2014041954 hasAuthorship W2014041954A5075246991 @default.
- W2014041954 hasConcept C106487976 @default.
- W2014041954 hasConcept C11413529 @default.
- W2014041954 hasConcept C119857082 @default.
- W2014041954 hasConcept C121332964 @default.
- W2014041954 hasConcept C154945302 @default.
- W2014041954 hasConcept C158693339 @default.
- W2014041954 hasConcept C159985019 @default.
- W2014041954 hasConcept C162324750 @default.
- W2014041954 hasConcept C17349429 @default.
- W2014041954 hasConcept C177264268 @default.
- W2014041954 hasConcept C187736073 @default.
- W2014041954 hasConcept C192562407 @default.
- W2014041954 hasConcept C199360897 @default.
- W2014041954 hasConcept C205203396 @default.
- W2014041954 hasConcept C2780451532 @default.
- W2014041954 hasConcept C28855332 @default.
- W2014041954 hasConcept C31972630 @default.
- W2014041954 hasConcept C41008148 @default.
- W2014041954 hasConcept C42355184 @default.
- W2014041954 hasConcept C45374587 @default.
- W2014041954 hasConcept C62520636 @default.
- W2014041954 hasConcept C84114770 @default.
- W2014041954 hasConceptScore W2014041954C106487976 @default.
- W2014041954 hasConceptScore W2014041954C11413529 @default.
- W2014041954 hasConceptScore W2014041954C119857082 @default.
- W2014041954 hasConceptScore W2014041954C121332964 @default.
- W2014041954 hasConceptScore W2014041954C154945302 @default.
- W2014041954 hasConceptScore W2014041954C158693339 @default.
- W2014041954 hasConceptScore W2014041954C159985019 @default.
- W2014041954 hasConceptScore W2014041954C162324750 @default.
- W2014041954 hasConceptScore W2014041954C17349429 @default.
- W2014041954 hasConceptScore W2014041954C177264268 @default.
- W2014041954 hasConceptScore W2014041954C187736073 @default.
- W2014041954 hasConceptScore W2014041954C192562407 @default.
- W2014041954 hasConceptScore W2014041954C199360897 @default.
- W2014041954 hasConceptScore W2014041954C205203396 @default.
- W2014041954 hasConceptScore W2014041954C2780451532 @default.
- W2014041954 hasConceptScore W2014041954C28855332 @default.
- W2014041954 hasConceptScore W2014041954C31972630 @default.
- W2014041954 hasConceptScore W2014041954C41008148 @default.
- W2014041954 hasConceptScore W2014041954C42355184 @default.
- W2014041954 hasConceptScore W2014041954C45374587 @default.
- W2014041954 hasConceptScore W2014041954C62520636 @default.
- W2014041954 hasConceptScore W2014041954C84114770 @default.
- W2014041954 hasLocation W20140419541 @default.
- W2014041954 hasOpenAccess W2014041954 @default.
- W2014041954 hasPrimaryLocation W20140419541 @default.
- W2014041954 hasRelatedWork W1980837560 @default.
- W2014041954 hasRelatedWork W2023314720 @default.
- W2014041954 hasRelatedWork W2125314656 @default.
- W2014041954 hasRelatedWork W2287143373 @default.
- W2014041954 hasRelatedWork W2924774914 @default.