Matches in SemOpenAlex for { <https://semopenalex.org/work/W58199462> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W58199462 endingPage "282" @default.
- W58199462 startingPage "272" @default.
- W58199462 abstract "Pedestrian detection is a fundamental problem in video surveillance and has achieved great progress in recent years. However, training a generic detector performing well in a great variety of scenes has been approved to be very difficult. On the other hand, exhausting manual labeling effort for each specific scene to achieve high accuracy of detection is not acceptable especially for video surveillance applications. In order to alleviate the manual labeling effort without scarifying accuracy of detection, we propose a transfer learning framework to automatically train a scene-specific pedestrian detector starting from a pre-trained generic detector. In our framework, sparse coding is proposed to calculate similarities between source samples and a small set of selected target samples by using the former as dictionary. The similarities are later used to calculate weights of source samples. The weights of initially detected target samples are calculated in a similar way but using the selected target dataset as dictionary. By using these weighted samples during re-training process, our framework can efficiently get a scene-specific pedestrian detector. Our experiments on VIRAT dataset show that our trained scene-specific pedestrian detector performs well and it is comparable with the detector trained on a large number of training samples manually labeled from the target scene." @default.
- W58199462 created "2016-06-24" @default.
- W58199462 creator A5011514919 @default.
- W58199462 creator A5026744983 @default.
- W58199462 creator A5036591099 @default.
- W58199462 creator A5041146584 @default.
- W58199462 creator A5056776177 @default.
- W58199462 date "2013-01-01" @default.
- W58199462 modified "2023-09-25" @default.
- W58199462 title "A Sparse Coding Based Transfer Learning Framework for Pedestrian Detection" @default.
- W58199462 cites W1904464160 @default.
- W58199462 cites W2031454541 @default.
- W58199462 cites W2032355985 @default.
- W58199462 cites W2061781238 @default.
- W58199462 cites W2079057609 @default.
- W58199462 cites W2107775979 @default.
- W58199462 cites W2110226872 @default.
- W58199462 cites W2120419212 @default.
- W58199462 cites W2121496627 @default.
- W58199462 cites W2122838776 @default.
- W58199462 cites W2127070222 @default.
- W58199462 cites W2153927146 @default.
- W58199462 cites W2154740476 @default.
- W58199462 cites W4236952561 @default.
- W58199462 doi "https://doi.org/10.1007/978-3-642-35728-2_26" @default.
- W58199462 hasPublicationYear "2013" @default.
- W58199462 type Work @default.
- W58199462 sameAs 58199462 @default.
- W58199462 citedByCount "4" @default.
- W58199462 countsByYear W581994622014 @default.
- W58199462 countsByYear W581994622015 @default.
- W58199462 countsByYear W581994622016 @default.
- W58199462 countsByYear W581994622017 @default.
- W58199462 crossrefType "book-chapter" @default.
- W58199462 hasAuthorship W58199462A5011514919 @default.
- W58199462 hasAuthorship W58199462A5026744983 @default.
- W58199462 hasAuthorship W58199462A5036591099 @default.
- W58199462 hasAuthorship W58199462A5041146584 @default.
- W58199462 hasAuthorship W58199462A5056776177 @default.
- W58199462 hasConcept C105795698 @default.
- W58199462 hasConcept C111919701 @default.
- W58199462 hasConcept C127413603 @default.
- W58199462 hasConcept C150899416 @default.
- W58199462 hasConcept C153180895 @default.
- W58199462 hasConcept C154945302 @default.
- W58199462 hasConcept C177264268 @default.
- W58199462 hasConcept C179518139 @default.
- W58199462 hasConcept C199360897 @default.
- W58199462 hasConcept C22212356 @default.
- W58199462 hasConcept C2777113093 @default.
- W58199462 hasConcept C2780156472 @default.
- W58199462 hasConcept C31972630 @default.
- W58199462 hasConcept C33923547 @default.
- W58199462 hasConcept C41008148 @default.
- W58199462 hasConcept C51632099 @default.
- W58199462 hasConcept C76155785 @default.
- W58199462 hasConcept C77637269 @default.
- W58199462 hasConcept C94915269 @default.
- W58199462 hasConcept C98045186 @default.
- W58199462 hasConceptScore W58199462C105795698 @default.
- W58199462 hasConceptScore W58199462C111919701 @default.
- W58199462 hasConceptScore W58199462C127413603 @default.
- W58199462 hasConceptScore W58199462C150899416 @default.
- W58199462 hasConceptScore W58199462C153180895 @default.
- W58199462 hasConceptScore W58199462C154945302 @default.
- W58199462 hasConceptScore W58199462C177264268 @default.
- W58199462 hasConceptScore W58199462C179518139 @default.
- W58199462 hasConceptScore W58199462C199360897 @default.
- W58199462 hasConceptScore W58199462C22212356 @default.
- W58199462 hasConceptScore W58199462C2777113093 @default.
- W58199462 hasConceptScore W58199462C2780156472 @default.
- W58199462 hasConceptScore W58199462C31972630 @default.
- W58199462 hasConceptScore W58199462C33923547 @default.
- W58199462 hasConceptScore W58199462C41008148 @default.
- W58199462 hasConceptScore W58199462C51632099 @default.
- W58199462 hasConceptScore W58199462C76155785 @default.
- W58199462 hasConceptScore W58199462C77637269 @default.
- W58199462 hasConceptScore W58199462C94915269 @default.
- W58199462 hasConceptScore W58199462C98045186 @default.
- W58199462 hasLocation W581994621 @default.
- W58199462 hasOpenAccess W58199462 @default.
- W58199462 hasPrimaryLocation W581994621 @default.
- W58199462 hasRelatedWork W1561580412 @default.
- W58199462 hasRelatedWork W2024127313 @default.
- W58199462 hasRelatedWork W2028766500 @default.
- W58199462 hasRelatedWork W2045236850 @default.
- W58199462 hasRelatedWork W2054988076 @default.
- W58199462 hasRelatedWork W2129431236 @default.
- W58199462 hasRelatedWork W2142681052 @default.
- W58199462 hasRelatedWork W2350121711 @default.
- W58199462 hasRelatedWork W2748921485 @default.
- W58199462 hasRelatedWork W4241216936 @default.
- W58199462 isParatext "false" @default.
- W58199462 isRetracted "false" @default.
- W58199462 magId "58199462" @default.
- W58199462 workType "book-chapter" @default.