Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386869688> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W4386869688 endingPage "14" @default.
- W4386869688 startingPage "1" @default.
- W4386869688 abstract "We address the problem of establishing accurate correspondences between two images. We present a flexible framework that can easily adapt to both geometric and semantic matching. Our contribution consists of three parts. Firstly, we propose an end-to-end trainable framework that uses the coarse-to-fine matching strategy to accurately find the correspondences. We generate feature maps in two levels of resolution, enforce the neighbourhood consensus constraint on the coarse feature maps by 4D convolutions and use the resulting correlation map to regulate the matches from the fine feature maps. Secondly, we present three variants of the model with different focuses. Namely, a universal correspondence model named DualRC that is suitable for both geometric and semantic matching, an efficient model named DualRC-L tailored for geometric matching with a lightweight neighbourhood consensus module that significantly accelerates the pipeline for high-resolution input images, and the DualRC-D model in which we propose a novel dynamically adaptive neighbourhood consensus module (DyANC) that dynamically selects the most suitable non-isotropic 4D convolutional kernels with the proper neighbourhood size to account for the scale variation. Last, we thoroughly experiment on public benchmarks for both geometric and semantic matching, showing superior performance in both cases." @default.
- W4386869688 created "2023-09-20" @default.
- W4386869688 creator A5055522006 @default.
- W4386869688 creator A5057306793 @default.
- W4386869688 creator A5067395390 @default.
- W4386869688 creator A5070710525 @default.
- W4386869688 date "2023-01-01" @default.
- W4386869688 modified "2023-10-02" @default.
- W4386869688 title "DualRC: A Dual-Resolution Learning Framework with Neighbourhood Consensus for Visual Correspondences" @default.
- W4386869688 doi "https://doi.org/10.1109/tpami.2023.3316770" @default.
- W4386869688 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37725724" @default.
- W4386869688 hasPublicationYear "2023" @default.
- W4386869688 type Work @default.
- W4386869688 citedByCount "0" @default.
- W4386869688 crossrefType "journal-article" @default.
- W4386869688 hasAuthorship W4386869688A5055522006 @default.
- W4386869688 hasAuthorship W4386869688A5057306793 @default.
- W4386869688 hasAuthorship W4386869688A5067395390 @default.
- W4386869688 hasAuthorship W4386869688A5070710525 @default.
- W4386869688 hasConcept C104317684 @default.
- W4386869688 hasConcept C105795698 @default.
- W4386869688 hasConcept C134306372 @default.
- W4386869688 hasConcept C138885662 @default.
- W4386869688 hasConcept C153180895 @default.
- W4386869688 hasConcept C154945302 @default.
- W4386869688 hasConcept C161677786 @default.
- W4386869688 hasConcept C165064840 @default.
- W4386869688 hasConcept C185592680 @default.
- W4386869688 hasConcept C2524010 @default.
- W4386869688 hasConcept C2776036281 @default.
- W4386869688 hasConcept C2776401178 @default.
- W4386869688 hasConcept C31972630 @default.
- W4386869688 hasConcept C33923547 @default.
- W4386869688 hasConcept C41008148 @default.
- W4386869688 hasConcept C41895202 @default.
- W4386869688 hasConcept C55493867 @default.
- W4386869688 hasConcept C63479239 @default.
- W4386869688 hasConceptScore W4386869688C104317684 @default.
- W4386869688 hasConceptScore W4386869688C105795698 @default.
- W4386869688 hasConceptScore W4386869688C134306372 @default.
- W4386869688 hasConceptScore W4386869688C138885662 @default.
- W4386869688 hasConceptScore W4386869688C153180895 @default.
- W4386869688 hasConceptScore W4386869688C154945302 @default.
- W4386869688 hasConceptScore W4386869688C161677786 @default.
- W4386869688 hasConceptScore W4386869688C165064840 @default.
- W4386869688 hasConceptScore W4386869688C185592680 @default.
- W4386869688 hasConceptScore W4386869688C2524010 @default.
- W4386869688 hasConceptScore W4386869688C2776036281 @default.
- W4386869688 hasConceptScore W4386869688C2776401178 @default.
- W4386869688 hasConceptScore W4386869688C31972630 @default.
- W4386869688 hasConceptScore W4386869688C33923547 @default.
- W4386869688 hasConceptScore W4386869688C41008148 @default.
- W4386869688 hasConceptScore W4386869688C41895202 @default.
- W4386869688 hasConceptScore W4386869688C55493867 @default.
- W4386869688 hasConceptScore W4386869688C63479239 @default.
- W4386869688 hasLocation W43868696881 @default.
- W4386869688 hasLocation W43868696882 @default.
- W4386869688 hasOpenAccess W4386869688 @default.
- W4386869688 hasPrimaryLocation W43868696881 @default.
- W4386869688 hasRelatedWork W1504288058 @default.
- W4386869688 hasRelatedWork W2035976912 @default.
- W4386869688 hasRelatedWork W2167293474 @default.
- W4386869688 hasRelatedWork W2331674254 @default.
- W4386869688 hasRelatedWork W2391245565 @default.
- W4386869688 hasRelatedWork W2541791370 @default.
- W4386869688 hasRelatedWork W2786306966 @default.
- W4386869688 hasRelatedWork W2921707373 @default.
- W4386869688 hasRelatedWork W3094187672 @default.
- W4386869688 hasRelatedWork W4386597354 @default.
- W4386869688 isParatext "false" @default.
- W4386869688 isRetracted "false" @default.
- W4386869688 workType "article" @default.