FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2940581368> ?p ?o ?g. }

• W2940581368 abstract "We propose a simple yet effective method to learn to segment new indoor scenes from video frames: State-of-the-art methods trained on one dataset, even as large as the SUNRGB-D dataset, can perform poorly when applied to images that are not part of the dataset, because of the dataset bias, a common phenomenon in computer vision. To make semantic segmentation more useful in practice, one can exploit geometric constraints. Our main contribution is to show that these constraints can be cast conveniently as semi-supervised terms, which enforce the fact that the same class should be predicted for the projections of the same 3D location in different images. This is interesting as we can exploit general existing techniques developed for semi-supervised learning to efficiently incorporate the constraints. We show that this approach can efficiently and accurately learn to segment target sequences of ScanNet and our own target sequences using only annotations from SUNRGB-D, and geometric relations between the video frames of target sequences." @default.
• W2940581368 created "2019-05-03" @default.
• W2940581368 creator A5042153947 @default.
• W2940581368 creator A5068079834 @default.
• W2940581368 creator A5070382607 @default.
• W2940581368 date "2019-04-29" @default.
• W2940581368 modified "2023-09-27" @default.
• W2940581368 title "Casting Geometric Constraints in Semantic Segmentation as Semi-Supervised Learning" @default.
• W2940581368 cites W125693051 @default.
• W2940581368 cites W1901129140 @default.
• W2940581368 cites W1910657905 @default.
• W2940581368 cites W1923184257 @default.
• W2940581368 cites W1957167950 @default.
• W2940581368 cites W1985238052 @default.
• W2940581368 cites W2108598243 @default.
• W2940581368 cites W2110764733 @default.
• W2940581368 cites W2194775991 @default.
• W2940581368 cites W2300779272 @default.
• W2940581368 cites W2520707372 @default.
• W2940581368 cites W2560023338 @default.
• W2940581368 cites W2592691248 @default.
• W2940581368 cites W2604455318 @default.
• W2940581368 cites W2609883120 @default.
• W2940581368 cites W2619371851 @default.
• W2940581368 cites W2729819393 @default.
• W2940581368 cites W2759366285 @default.
• W2940581368 cites W2786036844 @default.
• W2940581368 cites W2787091153 @default.
• W2940581368 cites W2794387644 @default.
• W2940581368 cites W2806446538 @default.
• W2940581368 cites W2808223045 @default.
• W2940581368 cites W2891778567 @default.
• W2940581368 cites W2909869271 @default.
• W2940581368 cites W2949634581 @default.
• W2940581368 cites W2951713345 @default.
• W2940581368 cites W2952632681 @default.
• W2940581368 cites W2962835968 @default.
• W2940581368 cites W2963654727 @default.
• W2940581368 cites W2963906250 @default.
• W2940581368 cites W2964121744 @default.
• W2940581368 cites W603908379 @default.
• W2940581368 cites W2530816535 @default.
• W2940581368 hasPublicationYear "2019" @default.
• W2940581368 type Work @default.
• W2940581368 sameAs 2940581368 @default.
• W2940581368 citedByCount "0" @default.
• W2940581368 crossrefType "posted-content" @default.
• W2940581368 hasAuthorship W2940581368A5042153947 @default.
• W2940581368 hasAuthorship W2940581368A5068079834 @default.
• W2940581368 hasAuthorship W2940581368A5070382607 @default.
• W2940581368 hasConcept C111472728 @default.
• W2940581368 hasConcept C119857082 @default.
• W2940581368 hasConcept C136389625 @default.
• W2940581368 hasConcept C138885662 @default.
• W2940581368 hasConcept C153180895 @default.
• W2940581368 hasConcept C154945302 @default.
• W2940581368 hasConcept C165696696 @default.
• W2940581368 hasConcept C2777212361 @default.
• W2940581368 hasConcept C2780586882 @default.
• W2940581368 hasConcept C31972630 @default.
• W2940581368 hasConcept C38652104 @default.
• W2940581368 hasConcept C41008148 @default.
• W2940581368 hasConcept C50644808 @default.
• W2940581368 hasConcept C89600930 @default.
• W2940581368 hasConceptScore W2940581368C111472728 @default.
• W2940581368 hasConceptScore W2940581368C119857082 @default.
• W2940581368 hasConceptScore W2940581368C136389625 @default.
• W2940581368 hasConceptScore W2940581368C138885662 @default.
• W2940581368 hasConceptScore W2940581368C153180895 @default.
• W2940581368 hasConceptScore W2940581368C154945302 @default.
• W2940581368 hasConceptScore W2940581368C165696696 @default.
• W2940581368 hasConceptScore W2940581368C2777212361 @default.
• W2940581368 hasConceptScore W2940581368C2780586882 @default.
• W2940581368 hasConceptScore W2940581368C31972630 @default.
• W2940581368 hasConceptScore W2940581368C38652104 @default.
• W2940581368 hasConceptScore W2940581368C41008148 @default.
• W2940581368 hasConceptScore W2940581368C50644808 @default.
• W2940581368 hasConceptScore W2940581368C89600930 @default.
• W2940581368 hasLocation W29405813681 @default.
• W2940581368 hasOpenAccess W2940581368 @default.
• W2940581368 hasPrimaryLocation W29405813681 @default.
• W2940581368 hasRelatedWork W2592414189 @default.
• W2940581368 hasRelatedWork W2896107389 @default.
• W2940581368 hasRelatedWork W2903619461 @default.
• W2940581368 hasRelatedWork W2949275688 @default.
• W2940581368 hasRelatedWork W2958419714 @default.
• W2940581368 hasRelatedWork W2981419144 @default.
• W2940581368 hasRelatedWork W3000695974 @default.
• W2940581368 hasRelatedWork W3009075458 @default.
• W2940581368 hasRelatedWork W3027513153 @default.
• W2940581368 hasRelatedWork W3033270690 @default.
• W2940581368 hasRelatedWork W3034373787 @default.
• W2940581368 hasRelatedWork W3039616371 @default.
• W2940581368 hasRelatedWork W3044881747 @default.
• W2940581368 hasRelatedWork W3113201309 @default.
• W2940581368 hasRelatedWork W3139559957 @default.
• W2940581368 hasRelatedWork W3152236563 @default.
• W2940581368 hasRelatedWork W3162477590 @default.
• W2940581368 hasRelatedWork W3186493773 @default.
• W2940581368 hasRelatedWork W3195226403 @default.

• next