FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2747550417> ?p ?o ?g. }

• W2747550417 abstract "Estimating dense visual correspondences between objects with intra-class variation, deformations and background clutter remains a challenging problem. Thanks to the breakthrough of CNNs there are new powerful features available. Despite their easy accessibility and great success, existing semantic flow methods could not significantly benefit from these without extensive additional training. We introduce a novel method for semantic matching with pre-trained CNN features which is based on convolutional feature pyramids and activation guided feature selection. For the final matching we propose a sparse graph matching framework where each salient feature selects among a small subset of nearest neighbors in the target image. To improve our method in the unconstrained setting without bounding box annotations we introduce novel object proposal based matching constraints. Furthermore, we show that the sparse matching can be transformed into a dense correspondence field. Extensive experimental evaluations on benchmark datasets show that our method significantly outperforms existing semantic matching methods." @default.
• W2747550417 created "2017-08-31" @default.
• W2747550417 creator A5008066954 @default.
• W2747550417 creator A5084415727 @default.
• W2747550417 date "2017-07-01" @default.
• W2747550417 modified "2023-09-30" @default.
• W2747550417 title "Deep Semantic Feature Matching" @default.
• W2747550417 cites W1154498256 @default.
• W2747550417 cites W1566946109 @default.
• W2747550417 cites W1578285471 @default.
• W2747550417 cites W1762798876 @default.
• W2747550417 cites W1919709169 @default.
• W2747550417 cites W1958328135 @default.
• W2747550417 cites W1974042113 @default.
• W2747550417 cites W1991264156 @default.
• W2747550417 cites W1991367009 @default.
• W2747550417 cites W1995875735 @default.
• W2747550417 cites W2032997833 @default.
• W2747550417 cites W2079272365 @default.
• W2747550417 cites W2088049833 @default.
• W2747550417 cites W2090518410 @default.
• W2747550417 cites W2103584248 @default.
• W2747550417 cites W2104408738 @default.
• W2747550417 cites W2121660792 @default.
• W2747550417 cites W2124861766 @default.
• W2747550417 cites W2126080861 @default.
• W2747550417 cites W2128409098 @default.
• W2747550417 cites W2137821246 @default.
• W2747550417 cites W213856341 @default.
• W2747550417 cites W2147237076 @default.
• W2747550417 cites W2151103935 @default.
• W2747550417 cites W2154583877 @default.
• W2747550417 cites W2161969291 @default.
• W2747550417 cites W2163819245 @default.
• W2747550417 cites W2165949176 @default.
• W2747550417 cites W2189538311 @default.
• W2747550417 cites W2293657101 @default.
• W2747550417 cites W2474531669 @default.
• W2747550417 cites W4205398292 @default.
• W2747550417 cites W4205425515 @default.
• W2747550417 doi "https://doi.org/10.1109/cvpr.2017.628" @default.
• W2747550417 hasPublicationYear "2017" @default.
• W2747550417 type Work @default.
• W2747550417 sameAs 2747550417 @default.
• W2747550417 citedByCount "80" @default.
• W2747550417 countsByYear W27475504172017 @default.
• W2747550417 countsByYear W27475504172018 @default.
• W2747550417 countsByYear W27475504172019 @default.
• W2747550417 countsByYear W27475504172020 @default.
• W2747550417 countsByYear W27475504172021 @default.
• W2747550417 countsByYear W27475504172022 @default.
• W2747550417 countsByYear W27475504172023 @default.
• W2747550417 crossrefType "proceedings-article" @default.
• W2747550417 hasAuthorship W2747550417A5008066954 @default.
• W2747550417 hasAuthorship W2747550417A5084415727 @default.
• W2747550417 hasConcept C105795698 @default.
• W2747550417 hasConcept C115961682 @default.
• W2747550417 hasConcept C132525143 @default.
• W2747550417 hasConcept C13280743 @default.
• W2747550417 hasConcept C138885662 @default.
• W2747550417 hasConcept C147037132 @default.
• W2747550417 hasConcept C148483581 @default.
• W2747550417 hasConcept C153180895 @default.
• W2747550417 hasConcept C154945302 @default.
• W2747550417 hasConcept C165064840 @default.
• W2747550417 hasConcept C185798385 @default.
• W2747550417 hasConcept C205649164 @default.
• W2747550417 hasConcept C2776401178 @default.
• W2747550417 hasConcept C2778493491 @default.
• W2747550417 hasConcept C2781122975 @default.
• W2747550417 hasConcept C33923547 @default.
• W2747550417 hasConcept C41008148 @default.
• W2747550417 hasConcept C41895202 @default.
• W2747550417 hasConcept C52622490 @default.
• W2747550417 hasConcept C80444323 @default.
• W2747550417 hasConcept C81363708 @default.
• W2747550417 hasConceptScore W2747550417C105795698 @default.
• W2747550417 hasConceptScore W2747550417C115961682 @default.
• W2747550417 hasConceptScore W2747550417C132525143 @default.
• W2747550417 hasConceptScore W2747550417C13280743 @default.
• W2747550417 hasConceptScore W2747550417C138885662 @default.
• W2747550417 hasConceptScore W2747550417C147037132 @default.
• W2747550417 hasConceptScore W2747550417C148483581 @default.
• W2747550417 hasConceptScore W2747550417C153180895 @default.
• W2747550417 hasConceptScore W2747550417C154945302 @default.
• W2747550417 hasConceptScore W2747550417C165064840 @default.
• W2747550417 hasConceptScore W2747550417C185798385 @default.
• W2747550417 hasConceptScore W2747550417C205649164 @default.
• W2747550417 hasConceptScore W2747550417C2776401178 @default.
• W2747550417 hasConceptScore W2747550417C2778493491 @default.
• W2747550417 hasConceptScore W2747550417C2781122975 @default.
• W2747550417 hasConceptScore W2747550417C33923547 @default.
• W2747550417 hasConceptScore W2747550417C41008148 @default.
• W2747550417 hasConceptScore W2747550417C41895202 @default.
• W2747550417 hasConceptScore W2747550417C52622490 @default.
• W2747550417 hasConceptScore W2747550417C80444323 @default.
• W2747550417 hasConceptScore W2747550417C81363708 @default.
• W2747550417 hasLocation W27475504171 @default.
• W2747550417 hasOpenAccess W2747550417 @default.
• W2747550417 hasPrimaryLocation W27475504171 @default.

• next