FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3087584369> ?p ?o ?g. }

• W3087584369 endingPage "9124" @default.
• W3087584369 startingPage "9113" @default.
• W3087584369 abstract "The Deep learning of optical flow has been an active area for its empirical success. For the difficulty of obtaining accurate dense correspondence labels, unsupervised learning of optical flow has drawn more and more attention, while the accuracy is still far from satisfaction. By holding the philosophy that better estimation models can be trained with betterapproximated labels, which in turn can be obtained from better estimation models, we propose a self-taught learning framework to continually improve the accuracy using self-generated pseudo labels. The estimated optical flow is first filtered by bidirectional flow consistency validation and occlusion-aware dense labels are then generated by edge-aware interpolation from selected sparse matches. Moreover, by combining reconstruction loss with regression loss on the generated pseudo labels, the performance is further improved. The experimental results demonstrate that our models achieve state-of-the-art results among unsupervised methods on the public KITTI, MPI-Sintel and Flying Chairs datasets." @default.
• W3087584369 created "2020-09-25" @default.
• W3087584369 creator A5004450394 @default.
• W3087584369 creator A5017941427 @default.
• W3087584369 creator A5019708391 @default.
• W3087584369 creator A5025808106 @default.
• W3087584369 creator A5046703129 @default.
• W3087584369 creator A5086706224 @default.
• W3087584369 creator A5087158377 @default.
• W3087584369 date "2020-01-01" @default.
• W3087584369 modified "2023-10-16" @default.
• W3087584369 title "STFlow: Self-Taught Optical Flow Estimation Using Pseudo Labels" @default.
• W3087584369 cites W1578285471 @default.
• W3087584369 cites W1762798876 @default.
• W3087584369 cites W1921093919 @default.
• W3087584369 cites W1951289974 @default.
• W3087584369 cites W1993120651 @default.
• W3087584369 cites W2010625607 @default.
• W3087584369 cites W2050403968 @default.
• W3087584369 cites W2113221323 @default.
• W3087584369 cites W2129587342 @default.
• W3087584369 cites W2131747574 @default.
• W3087584369 cites W2150066425 @default.
• W3087584369 cites W2155302366 @default.
• W3087584369 cites W2158919891 @default.
• W3087584369 cites W2164299365 @default.
• W3087584369 cites W2269094482 @default.
• W3087584369 cites W2286655030 @default.
• W3087584369 cites W2548527721 @default.
• W3087584369 cites W2560474170 @default.
• W3087584369 cites W2890949887 @default.
• W3087584369 cites W2904340070 @default.
• W3087584369 cites W2962864875 @default.
• W3087584369 cites W2963219046 @default.
• W3087584369 cites W2963305757 @default.
• W3087584369 cites W2963317244 @default.
• W3087584369 cites W2963483509 @default.
• W3087584369 cites W2963782415 @default.
• W3087584369 cites W2964140947 @default.
• W3087584369 cites W2964156315 @default.
• W3087584369 cites W2967043539 @default.
• W3087584369 cites W764651262 @default.
• W3087584369 doi "https://doi.org/10.1109/tip.2020.3024015" @default.
• W3087584369 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/32956057" @default.
• W3087584369 hasPublicationYear "2020" @default.
• W3087584369 type Work @default.
• W3087584369 sameAs 3087584369 @default.
• W3087584369 citedByCount "11" @default.
• W3087584369 countsByYear W30875843692020 @default.
• W3087584369 countsByYear W30875843692021 @default.
• W3087584369 countsByYear W30875843692022 @default.
• W3087584369 countsByYear W30875843692023 @default.
• W3087584369 crossrefType "journal-article" @default.
• W3087584369 hasAuthorship W3087584369A5004450394 @default.
• W3087584369 hasAuthorship W3087584369A5017941427 @default.
• W3087584369 hasAuthorship W3087584369A5019708391 @default.
• W3087584369 hasAuthorship W3087584369A5025808106 @default.
• W3087584369 hasAuthorship W3087584369A5046703129 @default.
• W3087584369 hasAuthorship W3087584369A5086706224 @default.
• W3087584369 hasAuthorship W3087584369A5087158377 @default.
• W3087584369 hasBestOaLocation W30875843691 @default.
• W3087584369 hasConcept C108583219 @default.
• W3087584369 hasConcept C115961682 @default.
• W3087584369 hasConcept C119857082 @default.
• W3087584369 hasConcept C137800194 @default.
• W3087584369 hasConcept C153180895 @default.
• W3087584369 hasConcept C154945302 @default.
• W3087584369 hasConcept C155542232 @default.
• W3087584369 hasConcept C162307627 @default.
• W3087584369 hasConcept C2524010 @default.
• W3087584369 hasConcept C2776436953 @default.
• W3087584369 hasConcept C33923547 @default.
• W3087584369 hasConcept C38349280 @default.
• W3087584369 hasConcept C41008148 @default.
• W3087584369 hasConcept C8038995 @default.
• W3087584369 hasConceptScore W3087584369C108583219 @default.
• W3087584369 hasConceptScore W3087584369C115961682 @default.
• W3087584369 hasConceptScore W3087584369C119857082 @default.
• W3087584369 hasConceptScore W3087584369C137800194 @default.
• W3087584369 hasConceptScore W3087584369C153180895 @default.
• W3087584369 hasConceptScore W3087584369C154945302 @default.
• W3087584369 hasConceptScore W3087584369C155542232 @default.
• W3087584369 hasConceptScore W3087584369C162307627 @default.
• W3087584369 hasConceptScore W3087584369C2524010 @default.
• W3087584369 hasConceptScore W3087584369C2776436953 @default.
• W3087584369 hasConceptScore W3087584369C33923547 @default.
• W3087584369 hasConceptScore W3087584369C38349280 @default.
• W3087584369 hasConceptScore W3087584369C41008148 @default.
• W3087584369 hasConceptScore W3087584369C8038995 @default.
• W3087584369 hasFunder F4320306076 @default.
• W3087584369 hasFunder F4320321001 @default.
• W3087584369 hasFunder F4320321885 @default.
• W3087584369 hasLocation W30875843691 @default.
• W3087584369 hasLocation W30875843692 @default.
• W3087584369 hasOpenAccess W3087584369 @default.
• W3087584369 hasPrimaryLocation W30875843691 @default.
• W3087584369 hasRelatedWork W2908875379 @default.
• W3087584369 hasRelatedWork W3044458868 @default.

• next