Matches in SemOpenAlex for { <https://semopenalex.org/work/W1782804218> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W1782804218 abstract "Object recognition and localization are important to automatically interpret video and allow better querying on its content. We propose a method for object localization that learns incrementally and addresses four key aspects. Firstly, we show that for certain applications, recognition is feasible with only a few training samples. Secondly, we show that novel objects can be added incrementally without retraining existing objects, which is important for fast interaction. Thirdly, we show that an unbalanced number of positive training samples leads to biased classifier scores that can be corrected by modifying weights. Fourthly, we show that the detector performance can deteriorate due to hard-negative mining for similar or closely related classes (e.g., for Barbie and dress, because the doll is wearing a dress). This can be solved by our hierarchical classification. We introduce a new dataset, which we call TOSO, and use it to demonstrate the effectiveness of the proposed method for the localization and recognition of multiple objects in images." @default.
- W1782804218 created "2016-06-24" @default.
- W1782804218 creator A5007651026 @default.
- W1782804218 creator A5011382635 @default.
- W1782804218 creator A5027326994 @default.
- W1782804218 creator A5027779655 @default.
- W1782804218 creator A5060327141 @default.
- W1782804218 date "2015-10-21" @default.
- W1782804218 modified "2023-09-24" @default.
- W1782804218 title "Incremental concept learning with few training examples and hierarchical classification" @default.
- W1782804218 cites W1511797856 @default.
- W1782804218 cites W1590510366 @default.
- W1782804218 cites W1812648727 @default.
- W1782804218 cites W1979936637 @default.
- W1782804218 cites W1992736075 @default.
- W1782804218 cites W2031489346 @default.
- W1782804218 cites W2116339064 @default.
- W1782804218 cites W2122886155 @default.
- W1782804218 cites W4234859835 @default.
- W1782804218 doi "https://doi.org/10.1117/12.2194438" @default.
- W1782804218 hasPublicationYear "2015" @default.
- W1782804218 type Work @default.
- W1782804218 sameAs 1782804218 @default.
- W1782804218 citedByCount "2" @default.
- W1782804218 countsByYear W17828042182015 @default.
- W1782804218 crossrefType "proceedings-article" @default.
- W1782804218 hasAuthorship W1782804218A5007651026 @default.
- W1782804218 hasAuthorship W1782804218A5011382635 @default.
- W1782804218 hasAuthorship W1782804218A5027326994 @default.
- W1782804218 hasAuthorship W1782804218A5027779655 @default.
- W1782804218 hasAuthorship W1782804218A5060327141 @default.
- W1782804218 hasBestOaLocation W17828042182 @default.
- W1782804218 hasConcept C119857082 @default.
- W1782804218 hasConcept C144133560 @default.
- W1782804218 hasConcept C153180895 @default.
- W1782804218 hasConcept C154945302 @default.
- W1782804218 hasConcept C155202549 @default.
- W1782804218 hasConcept C26517878 @default.
- W1782804218 hasConcept C2776151529 @default.
- W1782804218 hasConcept C2778712577 @default.
- W1782804218 hasConcept C2781238097 @default.
- W1782804218 hasConcept C31972630 @default.
- W1782804218 hasConcept C38652104 @default.
- W1782804218 hasConcept C41008148 @default.
- W1782804218 hasConcept C51632099 @default.
- W1782804218 hasConcept C64876066 @default.
- W1782804218 hasConcept C76155785 @default.
- W1782804218 hasConcept C94915269 @default.
- W1782804218 hasConcept C95623464 @default.
- W1782804218 hasConceptScore W1782804218C119857082 @default.
- W1782804218 hasConceptScore W1782804218C144133560 @default.
- W1782804218 hasConceptScore W1782804218C153180895 @default.
- W1782804218 hasConceptScore W1782804218C154945302 @default.
- W1782804218 hasConceptScore W1782804218C155202549 @default.
- W1782804218 hasConceptScore W1782804218C26517878 @default.
- W1782804218 hasConceptScore W1782804218C2776151529 @default.
- W1782804218 hasConceptScore W1782804218C2778712577 @default.
- W1782804218 hasConceptScore W1782804218C2781238097 @default.
- W1782804218 hasConceptScore W1782804218C31972630 @default.
- W1782804218 hasConceptScore W1782804218C38652104 @default.
- W1782804218 hasConceptScore W1782804218C41008148 @default.
- W1782804218 hasConceptScore W1782804218C51632099 @default.
- W1782804218 hasConceptScore W1782804218C64876066 @default.
- W1782804218 hasConceptScore W1782804218C76155785 @default.
- W1782804218 hasConceptScore W1782804218C94915269 @default.
- W1782804218 hasConceptScore W1782804218C95623464 @default.
- W1782804218 hasLocation W17828042181 @default.
- W1782804218 hasLocation W17828042182 @default.
- W1782804218 hasLocation W17828042183 @default.
- W1782804218 hasOpenAccess W1782804218 @default.
- W1782804218 hasPrimaryLocation W17828042181 @default.
- W1782804218 hasRelatedWork W1528044252 @default.
- W1782804218 hasRelatedWork W175120393 @default.
- W1782804218 hasRelatedWork W1939557789 @default.
- W1782804218 hasRelatedWork W1971759388 @default.
- W1782804218 hasRelatedWork W2007544051 @default.
- W1782804218 hasRelatedWork W2025800131 @default.
- W1782804218 hasRelatedWork W2095705906 @default.
- W1782804218 hasRelatedWork W2608783556 @default.
- W1782804218 hasRelatedWork W2922421953 @default.
- W1782804218 hasRelatedWork W2975200075 @default.
- W1782804218 isParatext "false" @default.
- W1782804218 isRetracted "false" @default.
- W1782804218 magId "1782804218" @default.
- W1782804218 workType "article" @default.