Matches in SemOpenAlex for { <https://semopenalex.org/work/W2892055814> ?p ?o ?g. }
- W2892055814 abstract "This work aims to estimate dense correspondences between the images from same visual class but with different geometries and visual similarities. This task is particularly challenging because (i) most image pairs have large intra-class variations, and (ii)their visual content is similar only on the high-level structure. To address these problems, this paper proposed a multilevel method to estimate per-pixel correspondences from high-level semantic to low-level structural details by the guidance of cycle-consistency. We utilize CNN feature pyramid to represent images level by level. Meanwhile, we introduce cycle-consistency to measure the reliability of flow vector, which further affects the guidance from higher level to lower level. The proposed method has been extensively evaluated on various challenging benchmarks. The results show that our method significantly outperforms the state-of-the-arts in terms of semantic flow accuracy." @default.
- W2892055814 created "2018-09-27" @default.
- W2892055814 creator A5023274785 @default.
- W2892055814 creator A5039262710 @default.
- W2892055814 creator A5059926864 @default.
- W2892055814 creator A5078143614 @default.
- W2892055814 date "2018-10-01" @default.
- W2892055814 modified "2023-09-29" @default.
- W2892055814 title "Cycle-Consistency Based Hierarchical Dense Semantic Correspondence" @default.
- W2892055814 cites W1230023165 @default.
- W2892055814 cites W143551758 @default.
- W2892055814 cites W1762798876 @default.
- W2892055814 cites W1763426478 @default.
- W2892055814 cites W1898560071 @default.
- W2892055814 cites W190007845 @default.
- W2892055814 cites W1926639317 @default.
- W2892055814 cites W1974042113 @default.
- W2892055814 cites W1996140089 @default.
- W2892055814 cites W2014102544 @default.
- W2892055814 cites W2044475502 @default.
- W2892055814 cites W2104408738 @default.
- W2892055814 cites W2109255472 @default.
- W2892055814 cites W2119414364 @default.
- W2892055814 cites W2124861766 @default.
- W2892055814 cites W2137821246 @default.
- W2892055814 cites W2143133882 @default.
- W2892055814 cites W2154504070 @default.
- W2892055814 cites W2166049352 @default.
- W2892055814 cites W2293657101 @default.
- W2892055814 cites W2566812041 @default.
- W2892055814 cites W2593948489 @default.
- W2892055814 cites W2736876108 @default.
- W2892055814 cites W2962835968 @default.
- W2892055814 doi "https://doi.org/10.1109/icip.2018.8451325" @default.
- W2892055814 hasPublicationYear "2018" @default.
- W2892055814 type Work @default.
- W2892055814 sameAs 2892055814 @default.
- W2892055814 citedByCount "1" @default.
- W2892055814 countsByYear W28920558142021 @default.
- W2892055814 crossrefType "proceedings-article" @default.
- W2892055814 hasAuthorship W2892055814A5023274785 @default.
- W2892055814 hasAuthorship W2892055814A5039262710 @default.
- W2892055814 hasAuthorship W2892055814A5059926864 @default.
- W2892055814 hasAuthorship W2892055814A5078143614 @default.
- W2892055814 hasConcept C115961682 @default.
- W2892055814 hasConcept C121332964 @default.
- W2892055814 hasConcept C124101348 @default.
- W2892055814 hasConcept C138885662 @default.
- W2892055814 hasConcept C142575187 @default.
- W2892055814 hasConcept C153180895 @default.
- W2892055814 hasConcept C154945302 @default.
- W2892055814 hasConcept C160633673 @default.
- W2892055814 hasConcept C162324750 @default.
- W2892055814 hasConcept C163258240 @default.
- W2892055814 hasConcept C187736073 @default.
- W2892055814 hasConcept C204321447 @default.
- W2892055814 hasConcept C2524010 @default.
- W2892055814 hasConcept C2776401178 @default.
- W2892055814 hasConcept C2776436953 @default.
- W2892055814 hasConcept C2777212361 @default.
- W2892055814 hasConcept C2780009758 @default.
- W2892055814 hasConcept C2780451532 @default.
- W2892055814 hasConcept C33923547 @default.
- W2892055814 hasConcept C36464697 @default.
- W2892055814 hasConcept C41008148 @default.
- W2892055814 hasConcept C41895202 @default.
- W2892055814 hasConcept C43214815 @default.
- W2892055814 hasConcept C62520636 @default.
- W2892055814 hasConceptScore W2892055814C115961682 @default.
- W2892055814 hasConceptScore W2892055814C121332964 @default.
- W2892055814 hasConceptScore W2892055814C124101348 @default.
- W2892055814 hasConceptScore W2892055814C138885662 @default.
- W2892055814 hasConceptScore W2892055814C142575187 @default.
- W2892055814 hasConceptScore W2892055814C153180895 @default.
- W2892055814 hasConceptScore W2892055814C154945302 @default.
- W2892055814 hasConceptScore W2892055814C160633673 @default.
- W2892055814 hasConceptScore W2892055814C162324750 @default.
- W2892055814 hasConceptScore W2892055814C163258240 @default.
- W2892055814 hasConceptScore W2892055814C187736073 @default.
- W2892055814 hasConceptScore W2892055814C204321447 @default.
- W2892055814 hasConceptScore W2892055814C2524010 @default.
- W2892055814 hasConceptScore W2892055814C2776401178 @default.
- W2892055814 hasConceptScore W2892055814C2776436953 @default.
- W2892055814 hasConceptScore W2892055814C2777212361 @default.
- W2892055814 hasConceptScore W2892055814C2780009758 @default.
- W2892055814 hasConceptScore W2892055814C2780451532 @default.
- W2892055814 hasConceptScore W2892055814C33923547 @default.
- W2892055814 hasConceptScore W2892055814C36464697 @default.
- W2892055814 hasConceptScore W2892055814C41008148 @default.
- W2892055814 hasConceptScore W2892055814C41895202 @default.
- W2892055814 hasConceptScore W2892055814C43214815 @default.
- W2892055814 hasConceptScore W2892055814C62520636 @default.
- W2892055814 hasLocation W28920558141 @default.
- W2892055814 hasOpenAccess W2892055814 @default.
- W2892055814 hasPrimaryLocation W28920558141 @default.
- W2892055814 hasRelatedWork W1964191339 @default.
- W2892055814 hasRelatedWork W1974878844 @default.
- W2892055814 hasRelatedWork W2014055810 @default.
- W2892055814 hasRelatedWork W2124132578 @default.
- W2892055814 hasRelatedWork W2364634124 @default.