Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950872240> ?p ?o ?g. }
- W2950872240 abstract "We propose a new pipeline for optical flow computation, based on Deep Learning techniques. We suggest using a Siamese CNN to independently, and in parallel, compute the descriptors of both images. The learned descriptors are then compared efficiently using the L2 norm and do not require network processing of patch pairs. The success of the method is based on an innovative loss function that computes higher moments of the loss distributions for each training batch. Combined with an Approximate Nearest Neighbor patch matching method and a flow interpolation technique, state of the art performance is obtained on the most challenging and competitive optical flow benchmarks." @default.
- W2950872240 created "2019-06-27" @default.
- W2950872240 creator A5022300129 @default.
- W2950872240 creator A5078102229 @default.
- W2950872240 date "2015-12-06" @default.
- W2950872240 modified "2023-09-27" @default.
- W2950872240 title "PatchBatch: a Batch Augmented Loss for Optical Flow" @default.
- W2950872240 cites W1165382972 @default.
- W2950872240 cites W1563651445 @default.
- W2950872240 cites W1578985305 @default.
- W2950872240 cites W1686810756 @default.
- W2950872240 cites W1690739335 @default.
- W2950872240 cites W1763426478 @default.
- W2950872240 cites W1884238496 @default.
- W2950872240 cites W2129587342 @default.
- W2950872240 cites W2138621090 @default.
- W2950872240 cites W2145940484 @default.
- W2950872240 cites W2150066425 @default.
- W2950872240 cites W2165245371 @default.
- W2950872240 cites W2326743484 @default.
- W2950872240 cites W2949117887 @default.
- W2950872240 cites W2949213045 @default.
- W2950872240 cites W2951054736 @default.
- W2950872240 cites W2951309005 @default.
- W2950872240 cites W2951643333 @default.
- W2950872240 cites W2963502507 @default.
- W2950872240 cites W303181297 @default.
- W2950872240 cites W6908809 @default.
- W2950872240 hasPublicationYear "2015" @default.
- W2950872240 type Work @default.
- W2950872240 sameAs 2950872240 @default.
- W2950872240 citedByCount "0" @default.
- W2950872240 crossrefType "posted-content" @default.
- W2950872240 hasAuthorship W2950872240A5022300129 @default.
- W2950872240 hasAuthorship W2950872240A5078102229 @default.
- W2950872240 hasConcept C105795698 @default.
- W2950872240 hasConcept C113238511 @default.
- W2950872240 hasConcept C11413529 @default.
- W2950872240 hasConcept C115961682 @default.
- W2950872240 hasConcept C137800194 @default.
- W2950872240 hasConcept C14036430 @default.
- W2950872240 hasConcept C153180895 @default.
- W2950872240 hasConcept C154945302 @default.
- W2950872240 hasConcept C155542232 @default.
- W2950872240 hasConcept C165064840 @default.
- W2950872240 hasConcept C17744445 @default.
- W2950872240 hasConcept C191795146 @default.
- W2950872240 hasConcept C199360897 @default.
- W2950872240 hasConcept C199539241 @default.
- W2950872240 hasConcept C2524010 @default.
- W2950872240 hasConcept C33923547 @default.
- W2950872240 hasConcept C38349280 @default.
- W2950872240 hasConcept C41008148 @default.
- W2950872240 hasConcept C43521106 @default.
- W2950872240 hasConcept C45374587 @default.
- W2950872240 hasConcept C78458016 @default.
- W2950872240 hasConcept C86803240 @default.
- W2950872240 hasConceptScore W2950872240C105795698 @default.
- W2950872240 hasConceptScore W2950872240C113238511 @default.
- W2950872240 hasConceptScore W2950872240C11413529 @default.
- W2950872240 hasConceptScore W2950872240C115961682 @default.
- W2950872240 hasConceptScore W2950872240C137800194 @default.
- W2950872240 hasConceptScore W2950872240C14036430 @default.
- W2950872240 hasConceptScore W2950872240C153180895 @default.
- W2950872240 hasConceptScore W2950872240C154945302 @default.
- W2950872240 hasConceptScore W2950872240C155542232 @default.
- W2950872240 hasConceptScore W2950872240C165064840 @default.
- W2950872240 hasConceptScore W2950872240C17744445 @default.
- W2950872240 hasConceptScore W2950872240C191795146 @default.
- W2950872240 hasConceptScore W2950872240C199360897 @default.
- W2950872240 hasConceptScore W2950872240C199539241 @default.
- W2950872240 hasConceptScore W2950872240C2524010 @default.
- W2950872240 hasConceptScore W2950872240C33923547 @default.
- W2950872240 hasConceptScore W2950872240C38349280 @default.
- W2950872240 hasConceptScore W2950872240C41008148 @default.
- W2950872240 hasConceptScore W2950872240C43521106 @default.
- W2950872240 hasConceptScore W2950872240C45374587 @default.
- W2950872240 hasConceptScore W2950872240C78458016 @default.
- W2950872240 hasConceptScore W2950872240C86803240 @default.
- W2950872240 hasLocation W29508722401 @default.
- W2950872240 hasOpenAccess W2950872240 @default.
- W2950872240 hasPrimaryLocation W29508722401 @default.
- W2950872240 hasRelatedWork W1686844825 @default.
- W2950872240 hasRelatedWork W1904063580 @default.
- W2950872240 hasRelatedWork W1966642287 @default.
- W2950872240 hasRelatedWork W2137549153 @default.
- W2950872240 hasRelatedWork W2153986527 @default.
- W2950872240 hasRelatedWork W2293159937 @default.
- W2950872240 hasRelatedWork W2294238219 @default.
- W2950872240 hasRelatedWork W2467255541 @default.
- W2950872240 hasRelatedWork W252513751 @default.
- W2950872240 hasRelatedWork W2802219220 @default.
- W2950872240 hasRelatedWork W2998645105 @default.
- W2950872240 hasRelatedWork W3000966067 @default.
- W2950872240 hasRelatedWork W3004287368 @default.
- W2950872240 hasRelatedWork W3036774376 @default.
- W2950872240 hasRelatedWork W3096841267 @default.
- W2950872240 hasRelatedWork W3109361385 @default.
- W2950872240 hasRelatedWork W3136623851 @default.
- W2950872240 hasRelatedWork W3149304110 @default.