FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W48707324> ?p ?o ?g. }

• W48707324 abstract "Deep Convolutional Neural Networks (CNNs) have gained great success in image classification and object detection. In these fields, the outputs of all layers of CNNs are usually considered as a high dimensional feature vector extracted from an input image and the correspondence between finer level feature vectors and concepts that the input image contains is all-important. However, fewer studies focus on this deserving issue. On considering the correspondence, we propose a novel approach which generates an edited version for each original CNN feature vector by applying the maximum entropy principle to abandon particular vectors. These selected vectors correspond to the unfriendly concepts in each image category. The classifier trained from merged feature sets can significantly improve model generalization of individual categories when training data is limited. The experimental results for classification-based object detection on canonical datasets including VOC 2007 (60.1%), 2010 (56.4%) and 2012 (56.3%) show obvious improvement in mean average precision (mAP) with simple linear support vector machines." @default.
• W48707324 created "2016-06-24" @default.
• W48707324 creator A5003418019 @default.
• W48707324 creator A5049353316 @default.
• W48707324 date "2014-09-24" @default.
• W48707324 modified "2023-10-10" @default.
• W48707324 title "Do More Dropouts in Pool5 Feature Maps for Better Object Detection" @default.
• W48707324 cites W1565402342 @default.
• W48707324 cites W1849277567 @default.
• W48707324 cites W1964005749 @default.
• W48707324 cites W1972515067 @default.
• W48707324 cites W2010181071 @default.
• W48707324 cites W2030536784 @default.
• W48707324 cites W2031489346 @default.
• W48707324 cites W2045798786 @default.
• W48707324 cites W2088049833 @default.
• W48707324 cites W2089468765 @default.
• W48707324 cites W2096175520 @default.
• W48707324 cites W2100495367 @default.
• W48707324 cites W2101926813 @default.
• W48707324 cites W2104854090 @default.
• W48707324 cites W2108598243 @default.
• W48707324 cites W2110226160 @default.
• W48707324 cites W2112247540 @default.
• W48707324 cites W2112796928 @default.
• W48707324 cites W2130306094 @default.
• W48707324 cites W2147800946 @default.
• W48707324 cites W2156547346 @default.
• W48707324 cites W2161969291 @default.
• W48707324 cites W2166127773 @default.
• W48707324 cites W2168356304 @default.
• W48707324 cites W2950124505 @default.
• W48707324 cites W2951638509 @default.
• W48707324 cites W2952390042 @default.
• W48707324 cites W2963542991 @default.
• W48707324 hasPublicationYear "2014" @default.
• W48707324 type Work @default.
• W48707324 sameAs 48707324 @default.
• W48707324 citedByCount "2" @default.
• W48707324 countsByYear W487073242015 @default.
• W48707324 crossrefType "posted-content" @default.
• W48707324 hasAuthorship W48707324A5003418019 @default.
• W48707324 hasAuthorship W48707324A5049353316 @default.
• W48707324 hasConcept C106301342 @default.
• W48707324 hasConcept C120665830 @default.
• W48707324 hasConcept C121332964 @default.
• W48707324 hasConcept C12267149 @default.
• W48707324 hasConcept C134306372 @default.
• W48707324 hasConcept C138885662 @default.
• W48707324 hasConcept C139532973 @default.
• W48707324 hasConcept C153180895 @default.
• W48707324 hasConcept C154945302 @default.
• W48707324 hasConcept C177148314 @default.
• W48707324 hasConcept C192209626 @default.
• W48707324 hasConcept C2776151529 @default.
• W48707324 hasConcept C2776401178 @default.
• W48707324 hasConcept C33923547 @default.
• W48707324 hasConcept C41008148 @default.
• W48707324 hasConcept C41895202 @default.
• W48707324 hasConcept C62520636 @default.
• W48707324 hasConcept C81363708 @default.
• W48707324 hasConcept C83665646 @default.
• W48707324 hasConcept C95623464 @default.
• W48707324 hasConceptScore W48707324C106301342 @default.
• W48707324 hasConceptScore W48707324C120665830 @default.
• W48707324 hasConceptScore W48707324C121332964 @default.
• W48707324 hasConceptScore W48707324C12267149 @default.
• W48707324 hasConceptScore W48707324C134306372 @default.
• W48707324 hasConceptScore W48707324C138885662 @default.
• W48707324 hasConceptScore W48707324C139532973 @default.
• W48707324 hasConceptScore W48707324C153180895 @default.
• W48707324 hasConceptScore W48707324C154945302 @default.
• W48707324 hasConceptScore W48707324C177148314 @default.
• W48707324 hasConceptScore W48707324C192209626 @default.
• W48707324 hasConceptScore W48707324C2776151529 @default.
• W48707324 hasConceptScore W48707324C2776401178 @default.
• W48707324 hasConceptScore W48707324C33923547 @default.
• W48707324 hasConceptScore W48707324C41008148 @default.
• W48707324 hasConceptScore W48707324C41895202 @default.
• W48707324 hasConceptScore W48707324C62520636 @default.
• W48707324 hasConceptScore W48707324C81363708 @default.
• W48707324 hasConceptScore W48707324C83665646 @default.
• W48707324 hasConceptScore W48707324C95623464 @default.
• W48707324 hasLocation W487073241 @default.
• W48707324 hasOpenAccess W48707324 @default.
• W48707324 hasPrimaryLocation W487073241 @default.
• W48707324 hasRelatedWork W1974860420 @default.
• W48707324 hasRelatedWork W2023389745 @default.
• W48707324 hasRelatedWork W2026143247 @default.
• W48707324 hasRelatedWork W2068730032 @default.
• W48707324 hasRelatedWork W2088049833 @default.
• W48707324 hasRelatedWork W2102605133 @default.
• W48707324 hasRelatedWork W2112504244 @default.
• W48707324 hasRelatedWork W2117539524 @default.
• W48707324 hasRelatedWork W2138374532 @default.
• W48707324 hasRelatedWork W2150880280 @default.
• W48707324 hasRelatedWork W2168356304 @default.
• W48707324 hasRelatedWork W2513750347 @default.
• W48707324 hasRelatedWork W2762075645 @default.
• W48707324 hasRelatedWork W2782865505 @default.

• next