FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2129818882> ?p ?o ?g. }

• W2129818882 endingPage "275" @default.
• W2129818882 startingPage "260" @default.
• W2129818882 abstract "Standard sliding window based object detection requires dense classifier evaluation on densely sampled locations in scale space in order to achieve an accurate localization. To avoid such dense evaluation, selective search based algorithms only evaluate the classifier on a small subset of object proposals. Notwithstanding the demonstrated success, object proposals do not guarantee perfect overlap with the object, leading to a suboptimal detection accuracy. To address this issue, we propose to first relax the dense sampling of the scale space with coarse object proposals generated from bottom-up segmentations. Based on detection results on these proposals, we then conduct a top-down search to more precisely localize the object using supervised descent. This two-stage detection strategy, dubbed location relaxation, is able to localize the object in the continuous parameter space. Furthermore, there is a conflict between accurate object detection and robust object detection. That is because the achievement of the later requires the accommodation of inaccurate and perturbed object locations in the training phase. To address this conflict, we leverage the rich spatial information learned from the Regionlets detection framework to determine where the object is precisely localized. Our proposed approaches are extensively validated on the PASCAL VOC 2007 dataset and a self-collected large scale car dataset. Our method boosts the mean average precision of the current state-of-the-art (41.7 %) to 44.1 % on PASCAL VOC 2007 dataset. To our best knowledge, it is the best performance reported without using outside data (Convolutional neural network based approaches are commonly pre-trained on a large scale outside dataset and fine-tuned on the VOC dataset.)." @default.
• W2129818882 created "2016-06-24" @default.
• W2129818882 creator A5008622229 @default.
• W2129818882 creator A5027540915 @default.
• W2129818882 creator A5029196289 @default.
• W2129818882 creator A5081114810 @default.
• W2129818882 creator A5088559134 @default.
• W2129818882 date "2015-01-01" @default.
• W2129818882 modified "2023-10-03" @default.
• W2129818882 title "Accurate Object Detection with Location Relaxation and Regionlets Re-localization" @default.
• W2129818882 cites W1950935069 @default.
• W2129818882 cites W1994938019 @default.
• W2129818882 cites W1999478155 @default.
• W2129818882 cites W2023014843 @default.
• W2129818882 cites W2037511607 @default.
• W2129818882 cites W2066624635 @default.
• W2129818882 cites W2110226160 @default.
• W2129818882 cites W2113201641 @default.
• W2129818882 cites W2120419212 @default.
• W2129818882 cites W2122853526 @default.
• W2129818882 cites W2129305389 @default.
• W2129818882 cites W2130350952 @default.
• W2129818882 cites W2142037471 @default.
• W2129818882 cites W2147511372 @default.
• W2129818882 cites W2157285372 @default.
• W2129818882 cites W2168356304 @default.
• W2129818882 cites W2534457893 @default.
• W2129818882 cites W2548197316 @default.
• W2129818882 doi "https://doi.org/10.1007/978-3-319-16865-4_17" @default.
• W2129818882 hasPublicationYear "2015" @default.
• W2129818882 type Work @default.
• W2129818882 sameAs 2129818882 @default.
• W2129818882 citedByCount "25" @default.
• W2129818882 countsByYear W21298188822014 @default.
• W2129818882 countsByYear W21298188822015 @default.
• W2129818882 countsByYear W21298188822016 @default.
• W2129818882 countsByYear W21298188822017 @default.
• W2129818882 countsByYear W21298188822018 @default.
• W2129818882 countsByYear W21298188822019 @default.
• W2129818882 countsByYear W21298188822020 @default.
• W2129818882 countsByYear W21298188822021 @default.
• W2129818882 countsByYear W21298188822022 @default.
• W2129818882 crossrefType "book-chapter" @default.
• W2129818882 hasAuthorship W2129818882A5008622229 @default.
• W2129818882 hasAuthorship W2129818882A5027540915 @default.
• W2129818882 hasAuthorship W2129818882A5029196289 @default.
• W2129818882 hasAuthorship W2129818882A5081114810 @default.
• W2129818882 hasAuthorship W2129818882A5088559134 @default.
• W2129818882 hasConcept C153083717 @default.
• W2129818882 hasConcept C153180895 @default.
• W2129818882 hasConcept C154945302 @default.
• W2129818882 hasConcept C199360897 @default.
• W2129818882 hasConcept C2776151529 @default.
• W2129818882 hasConcept C31972630 @default.
• W2129818882 hasConcept C41008148 @default.
• W2129818882 hasConcept C75608658 @default.
• W2129818882 hasConcept C81363708 @default.
• W2129818882 hasConcept C95623464 @default.
• W2129818882 hasConceptScore W2129818882C153083717 @default.
• W2129818882 hasConceptScore W2129818882C153180895 @default.
• W2129818882 hasConceptScore W2129818882C154945302 @default.
• W2129818882 hasConceptScore W2129818882C199360897 @default.
• W2129818882 hasConceptScore W2129818882C2776151529 @default.
• W2129818882 hasConceptScore W2129818882C31972630 @default.
• W2129818882 hasConceptScore W2129818882C41008148 @default.
• W2129818882 hasConceptScore W2129818882C75608658 @default.
• W2129818882 hasConceptScore W2129818882C81363708 @default.
• W2129818882 hasConceptScore W2129818882C95623464 @default.
• W2129818882 hasLocation W21298188821 @default.
• W2129818882 hasOpenAccess W2129818882 @default.
• W2129818882 hasPrimaryLocation W21298188821 @default.
• W2129818882 hasRelatedWork W2059299633 @default.
• W2129818882 hasRelatedWork W2296151615 @default.
• W2129818882 hasRelatedWork W2760011800 @default.
• W2129818882 hasRelatedWork W2784396512 @default.
• W2129818882 hasRelatedWork W2888527098 @default.
• W2129818882 hasRelatedWork W2909428641 @default.
• W2129818882 hasRelatedWork W2964383635 @default.
• W2129818882 hasRelatedWork W2989988688 @default.
• W2129818882 hasRelatedWork W2995914718 @default.
• W2129818882 hasRelatedWork W564581980 @default.
• W2129818882 isParatext "false" @default.
• W2129818882 isRetracted "false" @default.
• W2129818882 magId "2129818882" @default.
• W2129818882 workType "book-chapter" @default.