Matches in SemOpenAlex for { <https://semopenalex.org/work/W2101104841> ?p ?o ?g. }
- W2101104841 abstract "Learning to localize objects with minimal supervision is an important problem in computer vision, since large fully annotated datasets are extremely costly to obtain. In this paper, we propose a new method that achieves this goal with only image-level labels of whether the objects are present or not. Our approach combines a discriminative submodular cover problem for automatically discovering a set of positive object windows with a smoothed latent SVM formulation. The latter allows us to leverage efficient quasi-Newton optimization techniques. Our experiments demonstrate that the proposed approach provides a 50% relative improvement in mean average precision over the current state-of-the-art on PASCAL VOC 2007 detection." @default.
- W2101104841 created "2016-06-24" @default.
- W2101104841 creator A5010613767 @default.
- W2101104841 creator A5029105520 @default.
- W2101104841 creator A5049246408 @default.
- W2101104841 creator A5062817741 @default.
- W2101104841 creator A5085451600 @default.
- W2101104841 creator A5085699861 @default.
- W2101104841 date "2014-06-21" @default.
- W2101104841 modified "2023-09-27" @default.
- W2101104841 title "On learning to localize objects with minimal supervision" @default.
- W2101104841 cites W1552060966 @default.
- W2101104841 cites W1570918423 @default.
- W2101104841 cites W1575299770 @default.
- W2101104841 cites W1590510366 @default.
- W2101104841 cites W1603728330 @default.
- W2101104841 cites W1949116567 @default.
- W2101104841 cites W1952794764 @default.
- W2101104841 cites W1964763677 @default.
- W2101104841 cites W1970899458 @default.
- W2101104841 cites W2020477327 @default.
- W2101104841 cites W2029828838 @default.
- W2101104841 cites W2031489346 @default.
- W2101104841 cites W2033832873 @default.
- W2101104841 cites W2037227137 @default.
- W2101104841 cites W2052355211 @default.
- W2101104841 cites W2052916917 @default.
- W2101104841 cites W2055132753 @default.
- W2101104841 cites W2055753778 @default.
- W2101104841 cites W2061629163 @default.
- W2101104841 cites W2084165935 @default.
- W2101104841 cites W2086052791 @default.
- W2101104841 cites W2088049833 @default.
- W2101104841 cites W2093545205 @default.
- W2101104841 cites W2099528205 @default.
- W2101104841 cites W2102605133 @default.
- W2101104841 cites W2108745803 @default.
- W2101104841 cites W2111650570 @default.
- W2101104841 cites W2115628259 @default.
- W2101104841 cites W2117132237 @default.
- W2101104841 cites W2119991813 @default.
- W2101104841 cites W2120369594 @default.
- W2101104841 cites W2127788596 @default.
- W2101104841 cites W2147196093 @default.
- W2101104841 cites W2153565331 @default.
- W2101104841 cites W2155541015 @default.
- W2101104841 cites W2157244733 @default.
- W2101104841 cites W2161246474 @default.
- W2101104841 cites W2164500538 @default.
- W2101104841 cites W2164877691 @default.
- W2101104841 cites W2166765763 @default.
- W2101104841 cites W2167732364 @default.
- W2101104841 cites W2167828171 @default.
- W2101104841 cites W2168356304 @default.
- W2101104841 cites W2168912077 @default.
- W2101104841 cites W2169745058 @default.
- W2101104841 cites W2296319761 @default.
- W2101104841 cites W2952218179 @default.
- W2101104841 cites W3029645440 @default.
- W2101104841 hasPublicationYear "2014" @default.
- W2101104841 type Work @default.
- W2101104841 sameAs 2101104841 @default.
- W2101104841 citedByCount "26" @default.
- W2101104841 countsByYear W21011048412014 @default.
- W2101104841 countsByYear W21011048412015 @default.
- W2101104841 countsByYear W21011048412016 @default.
- W2101104841 countsByYear W21011048412017 @default.
- W2101104841 countsByYear W21011048412018 @default.
- W2101104841 countsByYear W21011048412019 @default.
- W2101104841 countsByYear W21011048412020 @default.
- W2101104841 countsByYear W21011048412021 @default.
- W2101104841 crossrefType "proceedings-article" @default.
- W2101104841 hasAuthorship W2101104841A5010613767 @default.
- W2101104841 hasAuthorship W2101104841A5029105520 @default.
- W2101104841 hasAuthorship W2101104841A5049246408 @default.
- W2101104841 hasAuthorship W2101104841A5062817741 @default.
- W2101104841 hasAuthorship W2101104841A5085451600 @default.
- W2101104841 hasAuthorship W2101104841A5085699861 @default.
- W2101104841 hasBestOaLocation W21011048411 @default.
- W2101104841 hasConcept C107457646 @default.
- W2101104841 hasConcept C154945302 @default.
- W2101104841 hasConcept C41008148 @default.
- W2101104841 hasConceptScore W2101104841C107457646 @default.
- W2101104841 hasConceptScore W2101104841C154945302 @default.
- W2101104841 hasConceptScore W2101104841C41008148 @default.
- W2101104841 hasLocation W21011048411 @default.
- W2101104841 hasLocation W21011048412 @default.
- W2101104841 hasLocation W21011048413 @default.
- W2101104841 hasOpenAccess W2101104841 @default.
- W2101104841 hasPrimaryLocation W21011048411 @default.
- W2101104841 hasRelatedWork W2130043461 @default.
- W2101104841 hasRelatedWork W2350741829 @default.
- W2101104841 hasRelatedWork W2358668433 @default.
- W2101104841 hasRelatedWork W2376932109 @default.
- W2101104841 hasRelatedWork W2382290278 @default.
- W2101104841 hasRelatedWork W2390279801 @default.
- W2101104841 hasRelatedWork W2748952813 @default.
- W2101104841 hasRelatedWork W2899084033 @default.
- W2101104841 hasRelatedWork W4246426965 @default.
- W2101104841 hasRelatedWork W2530322880 @default.