FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2795245768> ?p ?o ?g. }

• W2795245768 endingPage "2416" @default.
• W2795245768 startingPage "2403" @default.
• W2795245768 abstract "We present a novel spatial hashing based data structure to facilitate 3D shape analysis using convolutional neural networks (CNNs). Our method well utilizes the sparse occupancy of 3D shape boundary and builds hierarchical hash tables for an input model under different resolutions. Based on this data structure, we design two efficient GPU algorithms namely hash2col and col2hash so that the CNN operations like convolution and pooling can be efficiently parallelized. The spatial hashing is nearly minimal, and our data structure is almost of the same size as the raw input. Compared with state-of-the-art octree-based methods, our data structure significantly reduces the memory footprint during the CNN training. As the input geometry features are more compactly packed, CNN operations also run faster with our data structure. The experiment shows that, under the same network structure, our method yields comparable or better benchmarks compared to the state-of-the-art while it has only one-third memory consumption. Such superior memory performance allows the CNN to handle high-resolution shape analysis." @default.
• W2795245768 created "2018-04-06" @default.
• W2795245768 creator A5004008347 @default.
• W2795245768 creator A5027671723 @default.
• W2795245768 creator A5060286507 @default.
• W2795245768 creator A5067760326 @default.
• W2795245768 creator A5077579000 @default.
• W2795245768 date "2020-07-01" @default.
• W2795245768 modified "2023-10-17" @default.
• W2795245768 title "H-CNN: Spatial Hashing Based CNN for 3D Shape Analysis" @default.
• W2795245768 cites W1569512051 @default.
• W2795245768 cites W1629010235 @default.
• W2795245768 cites W1644641054 @default.
• W2795245768 cites W1677182931 @default.
• W2795245768 cites W1745334888 @default.
• W2795245768 cites W1903029394 @default.
• W2795245768 cites W1951806617 @default.
• W2795245768 cites W1994393928 @default.
• W2795245768 cites W2024794876 @default.
• W2795245768 cites W2112796928 @default.
• W2795245768 cites W2115579991 @default.
• W2795245768 cites W2135525032 @default.
• W2795245768 cites W2141200610 @default.
• W2795245768 cites W2143299724 @default.
• W2795245768 cites W2155893237 @default.
• W2795245768 cites W2162559028 @default.
• W2795245768 cites W2183182206 @default.
• W2795245768 cites W2211722331 @default.
• W2795245768 cites W2254644702 @default.
• W2795245768 cites W2293349265 @default.
• W2795245768 cites W2342223463 @default.
• W2795245768 cites W2476548250 @default.
• W2795245768 cites W2518780089 @default.
• W2795245768 cites W2553307952 @default.
• W2795245768 cites W2556802233 @default.
• W2795245768 cites W2558583534 @default.
• W2795245768 cites W2558748708 @default.
• W2795245768 cites W2601564443 @default.
• W2795245768 cites W2737081152 @default.
• W2795245768 cites W2766448241 @default.
• W2795245768 cites W2775216572 @default.
• W2795245768 cites W2962682791 @default.
• W2795245768 cites W2962731536 @default.
• W2795245768 cites W2962928871 @default.
• W2795245768 cites W2963021451 @default.
• W2795245768 cites W2963182550 @default.
• W2795245768 cites W2963721253 @default.
• W2795245768 cites W2964140963 @default.
• W2795245768 cites W3104141662 @default.
• W2795245768 cites W4232201360 @default.
• W2795245768 cites W4243755239 @default.
• W2795245768 cites W4250812768 @default.
• W2795245768 cites W764651262 @default.
• W2795245768 doi "https://doi.org/10.1109/tvcg.2018.2887262" @default.
• W2795245768 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30575540" @default.
• W2795245768 hasPublicationYear "2020" @default.
• W2795245768 type Work @default.
• W2795245768 sameAs 2795245768 @default.
• W2795245768 citedByCount "16" @default.
• W2795245768 countsByYear W27952457682018 @default.
• W2795245768 countsByYear W27952457682019 @default.
• W2795245768 countsByYear W27952457682020 @default.
• W2795245768 countsByYear W27952457682021 @default.
• W2795245768 countsByYear W27952457682022 @default.
• W2795245768 countsByYear W27952457682023 @default.
• W2795245768 crossrefType "journal-article" @default.
• W2795245768 hasAuthorship W2795245768A5004008347 @default.
• W2795245768 hasAuthorship W2795245768A5027671723 @default.
• W2795245768 hasAuthorship W2795245768A5060286507 @default.
• W2795245768 hasAuthorship W2795245768A5067760326 @default.
• W2795245768 hasAuthorship W2795245768A5077579000 @default.
• W2795245768 hasBestOaLocation W27952457682 @default.
• W2795245768 hasConcept C111919701 @default.
• W2795245768 hasConcept C11413529 @default.
• W2795245768 hasConcept C141297171 @default.
• W2795245768 hasConcept C153180895 @default.
• W2795245768 hasConcept C154945302 @default.
• W2795245768 hasConcept C162319229 @default.
• W2795245768 hasConcept C199360897 @default.
• W2795245768 hasConcept C38652104 @default.
• W2795245768 hasConcept C41008148 @default.
• W2795245768 hasConcept C45347329 @default.
• W2795245768 hasConcept C50644808 @default.
• W2795245768 hasConcept C67388219 @default.
• W2795245768 hasConcept C70437156 @default.
• W2795245768 hasConcept C74912251 @default.
• W2795245768 hasConcept C81363708 @default.
• W2795245768 hasConcept C99138194 @default.
• W2795245768 hasConceptScore W2795245768C111919701 @default.
• W2795245768 hasConceptScore W2795245768C11413529 @default.
• W2795245768 hasConceptScore W2795245768C141297171 @default.
• W2795245768 hasConceptScore W2795245768C153180895 @default.
• W2795245768 hasConceptScore W2795245768C154945302 @default.
• W2795245768 hasConceptScore W2795245768C162319229 @default.
• W2795245768 hasConceptScore W2795245768C199360897 @default.
• W2795245768 hasConceptScore W2795245768C38652104 @default.
• W2795245768 hasConceptScore W2795245768C41008148 @default.
• W2795245768 hasConceptScore W2795245768C45347329 @default.

• next