FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2982024234> ?p ?o ?g. }

• W2982024234 abstract "We explore the task of Canonical Surface Mapping (CSM). Specifically, given an image, we learn to map pixels on the object to their corresponding locations on an abstract 3D model of the category. But how do we learn such a mapping? A supervised approach would require extensive manual labeling which is not scalable beyond a few hand-picked categories. Our key insight is that the CSM task (pixel to 3D), when combined with 3D projection (3D to pixel), completes a cycle. Hence, we can exploit a geometric cycle consistency loss, thereby allowing us to forgo the dense manual supervision. Our approach allows us to train a CSM model for a diverse set of classes, without sparse or dense keypoint annotation, by leveraging only foreground mask labels for training. We show that our predictions also allow us to infer dense correspondence between two images, and compare the performance of our approach against several methods that predict correspondence by leveraging varying amount of supervision." @default.
• W2982024234 created "2019-11-01" @default.
• W2982024234 creator A5029932788 @default.
• W2982024234 creator A5053034244 @default.
• W2982024234 creator A5057446637 @default.
• W2982024234 date "2019-10-01" @default.
• W2982024234 modified "2023-10-17" @default.
• W2982024234 title "Canonical Surface Mapping via Geometric Cycle Consistency" @default.
• W2982024234 cites W1893912098 @default.
• W2982024234 cites W1930710394 @default.
• W2982024234 cites W1967437522 @default.
• W2982024234 cites W1967554269 @default.
• W2982024234 cites W1989191365 @default.
• W2982024234 cites W1991264156 @default.
• W2982024234 cites W1995713470 @default.
• W2982024234 cites W2031489346 @default.
• W2982024234 cites W2066090933 @default.
• W2982024234 cites W2108598243 @default.
• W2982024234 cites W2156094778 @default.
• W2982024234 cites W2237250383 @default.
• W2982024234 cites W2412002662 @default.
• W2982024234 cites W2474531669 @default.
• W2982024234 cites W2520707372 @default.
• W2982024234 cites W2558625610 @default.
• W2982024234 cites W2566265240 @default.
• W2982024234 cites W2604233003 @default.
• W2982024234 cites W2609883120 @default.
• W2982024234 cites W2962793481 @default.
• W2982024234 cites W2962912205 @default.
• W2982024234 cites W2963020784 @default.
• W2982024234 cites W2963150697 @default.
• W2982024234 cites W2963488642 @default.
• W2982024234 cites W2963527086 @default.
• W2982024234 cites W2963739349 @default.
• W2982024234 cites W2963749571 @default.
• W2982024234 cites W2964700958 @default.
• W2982024234 cites W3009720000 @default.
• W2982024234 cites W3106165820 @default.
• W2982024234 cites W4205425515 @default.
• W2982024234 doi "https://doi.org/10.1109/iccv.2019.00229" @default.
• W2982024234 hasPublicationYear "2019" @default.
• W2982024234 type Work @default.
• W2982024234 sameAs 2982024234 @default.
• W2982024234 citedByCount "86" @default.
• W2982024234 countsByYear W29820242342019 @default.
• W2982024234 countsByYear W29820242342020 @default.
• W2982024234 countsByYear W29820242342021 @default.
• W2982024234 countsByYear W29820242342022 @default.
• W2982024234 countsByYear W29820242342023 @default.
• W2982024234 crossrefType "proceedings-article" @default.
• W2982024234 hasAuthorship W2982024234A5029932788 @default.
• W2982024234 hasAuthorship W2982024234A5053034244 @default.
• W2982024234 hasAuthorship W2982024234A5057446637 @default.
• W2982024234 hasBestOaLocation W29820242342 @default.
• W2982024234 hasConcept C11413529 @default.
• W2982024234 hasConcept C153180895 @default.
• W2982024234 hasConcept C154945302 @default.
• W2982024234 hasConcept C160633673 @default.
• W2982024234 hasConcept C162324750 @default.
• W2982024234 hasConcept C165696696 @default.
• W2982024234 hasConcept C177264268 @default.
• W2982024234 hasConcept C187736073 @default.
• W2982024234 hasConcept C199360897 @default.
• W2982024234 hasConcept C26517878 @default.
• W2982024234 hasConcept C2776321320 @default.
• W2982024234 hasConcept C2776436953 @default.
• W2982024234 hasConcept C2780451532 @default.
• W2982024234 hasConcept C2781238097 @default.
• W2982024234 hasConcept C31972630 @default.
• W2982024234 hasConcept C38652104 @default.
• W2982024234 hasConcept C41008148 @default.
• W2982024234 hasConcept C48044578 @default.
• W2982024234 hasConcept C57493831 @default.
• W2982024234 hasConcept C77088390 @default.
• W2982024234 hasConceptScore W2982024234C11413529 @default.
• W2982024234 hasConceptScore W2982024234C153180895 @default.
• W2982024234 hasConceptScore W2982024234C154945302 @default.
• W2982024234 hasConceptScore W2982024234C160633673 @default.
• W2982024234 hasConceptScore W2982024234C162324750 @default.
• W2982024234 hasConceptScore W2982024234C165696696 @default.
• W2982024234 hasConceptScore W2982024234C177264268 @default.
• W2982024234 hasConceptScore W2982024234C187736073 @default.
• W2982024234 hasConceptScore W2982024234C199360897 @default.
• W2982024234 hasConceptScore W2982024234C26517878 @default.
• W2982024234 hasConceptScore W2982024234C2776321320 @default.
• W2982024234 hasConceptScore W2982024234C2776436953 @default.
• W2982024234 hasConceptScore W2982024234C2780451532 @default.
• W2982024234 hasConceptScore W2982024234C2781238097 @default.
• W2982024234 hasConceptScore W2982024234C31972630 @default.
• W2982024234 hasConceptScore W2982024234C38652104 @default.
• W2982024234 hasConceptScore W2982024234C41008148 @default.
• W2982024234 hasConceptScore W2982024234C48044578 @default.
• W2982024234 hasConceptScore W2982024234C57493831 @default.
• W2982024234 hasConceptScore W2982024234C77088390 @default.
• W2982024234 hasLocation W29820242341 @default.
• W2982024234 hasLocation W29820242342 @default.
• W2982024234 hasOpenAccess W2982024234 @default.
• W2982024234 hasPrimaryLocation W29820242341 @default.
• W2982024234 hasRelatedWork W121273120 @default.
• W2982024234 hasRelatedWork W2002009170 @default.

• next